�ݺ�ߣshows by User: NoTubeProject

�ݺ�ߣshows by User: NoTubeProject / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: NoTubeProject / Thu, 19 Sep 2024 14:18:16 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: NoTubeProject Finding video shots for immersive journalism through text-to-video search /slideshow/finding-video-shots-for-immersive-journalism-through-text-to-video-search/271900232 cbmi2024presentation-240919141816-af202648
Video assets from archives or online platforms can provide relevant content for embedding into immersive scenes or for generation of 3D objects or scenes. However, XR content creators lack tools to find relevant video segments for their chosen topic. In this paper, we explore the use case of journalists creating immersive experiences for news stories and their need to find related video material to create and populate a 3D scene. An innovative approach creates text and video embeddings and matches textual input queries to relevant video shots. This is provided via a Web dashboard for search and retrieval across video collections, with selected shots forming the input to content creation tools to generate and populate an immersive scene, meaning journalists do not need specialist knowledge to communicate stories via XR.]]>
Video assets from archives or online platforms can provide relevant content for embedding into immersive scenes or for generation of 3D objects or scenes. However, XR content creators lack tools to find relevant video segments for their chosen topic. In this paper, we explore the use case of journalists creating immersive experiences for news stories and their need to find related video material to create and populate a 3D scene. An innovative approach creates text and video embeddings and matches textual input queries to relevant video shots. This is provided via a Web dashboard for search and retrieval across video collections, with selected shots forming the input to content creation tools to generate and populate an immersive scene, meaning journalists do not need specialist knowledge to communicate stories via XR.]]> Thu, 19 Sep 2024 14:18:16 GMT /slideshow/finding-video-shots-for-immersive-journalism-through-text-to-video-search/271900232 NoTubeProject@slideshare.net(NoTubeProject) Finding video shots for immersive journalism through text-to-video search NoTubeProject Video assets from archives or online platforms can provide relevant content for embedding into immersive scenes or for generation of 3D objects or scenes. However, XR content creators lack tools to find relevant video segments for their chosen topic. In this paper, we explore the use case of journalists creating immersive experiences for news stories and their need to find related video material to create and populate a 3D scene. An innovative approach creates text and video embeddings and matches textual input queries to relevant video shots. This is provided via a Web dashboard for search and retrieval across video collections, with selected shots forming the input to content creation tools to generate and populate an immersive scene, meaning journalists do not need specialist knowledge to communicate stories via XR. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/cbmi2024presentation-240919141816-af202648-thumbnail.jpg?width=120&height=120&fit=bounds" /> Video assets from archives or online platforms can provide relevant content for embedding into immersive scenes or for generation of 3D objects or scenes. However, XR content creators lack tools to find relevant video segments for their chosen topic. In this paper, we explore the use case of journalists creating immersive experiences for news stories and their need to find related video material to create and populate a 3D scene. An innovative approach creates text and video embeddings and matches textual input queries to relevant video shots. This is provided via a Web dashboard for search and retrieval across video collections, with selected shots forming the input to content creation tools to generate and populate an immersive scene, meaning journalists do not need specialist knowledge to communicate stories via XR.

Finding video shots for immersive journalism through text-to-video search from MODUL Technology GmbH

]]> 17 0 https://cdn.slidesharecdn.com/ss_thumbnails/cbmi2024presentation-240919141816-af202648-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 LEARNING SUSTAINABLE MOBILITY BEHAVIOUR IN POST-PANDEMIC VIENNA /slideshow/learning-sustainable-mobility-behaviour-in-post-pandemic-vienna/271900065 fl9371-240919141149-206b5f1e
Sustainable mobility behaviour is a difficult goal to reach, as people are not willing to change their habits simply because it might help the environment. One method to change their mind is to create various incentives. Before doing this, however, it is important to understand their behaviour. This paper is focused on understanding people’s activity (e.g., next trip prediction, classification of their activity) based on their recent trip data collected through a mobility app. The early experiments show that a classical method based on gradient boosting leads to better results that more state if the art deep learning methods for these tasks.]]>
Sustainable mobility behaviour is a difficult goal to reach, as people are not willing to change their habits simply because it might help the environment. One method to change their mind is to create various incentives. Before doing this, however, it is important to understand their behaviour. This paper is focused on understanding people’s activity (e.g., next trip prediction, classification of their activity) based on their recent trip data collected through a mobility app. The early experiments show that a classical method based on gradient boosting leads to better results that more state if the art deep learning methods for these tasks.]]> Thu, 19 Sep 2024 14:11:49 GMT /slideshow/learning-sustainable-mobility-behaviour-in-post-pandemic-vienna/271900065 NoTubeProject@slideshare.net(NoTubeProject) LEARNING SUSTAINABLE MOBILITY BEHAVIOUR IN POST-PANDEMIC VIENNA NoTubeProject Sustainable mobility behaviour is a difficult goal to reach, as people are not willing to change their habits simply because it might help the environment. One method to change their mind is to create various incentives. Before doing this, however, it is important to understand their behaviour. This paper is focused on understanding people’s activity (e.g., next trip prediction, classification of their activity) based on their recent trip data collected through a mobility app. The early experiments show that a classical method based on gradient boosting leads to better results that more state if the art deep learning methods for these tasks. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/fl9371-240919141149-206b5f1e-thumbnail.jpg?width=120&height=120&fit=bounds" /> Sustainable mobility behaviour is a difficult goal to reach, as people are not willing to change their habits simply because it might help the environment. One method to change their mind is to create various incentives. Before doing this, however, it is important to understand their behaviour. This paper is focused on understanding people’s activity (e.g., next trip prediction, classification of their activity) based on their recent trip data collected through a mobility app. The early experiments show that a classical method based on gradient boosting leads to better results that more state if the art deep learning methods for these tasks.

LEARNING SUSTAINABLE MOBILITY BEHAVIOUR IN POST-PANDEMIC VIENNA from MODUL Technology GmbH

]]> 24 0 https://cdn.slidesharecdn.com/ss_thumbnails/fl9371-240919141149-206b5f1e-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 How distinct and aligned with UGC is European capitals’ DMO branding on Instagram? /slideshow/how-distinct-and-aligned-with-ugc-is-european-capitals-dmo-branding-on-instagram/265768981 enter2024presentationljb-240124160421-22891e86
Destination positioning: do DMOs promote their destination distinctly in their visual marketing? Destination branding: does tourist photography align with how DMOs promote the destination? ]]>
Destination positioning: do DMOs promote their destination distinctly in their visual marketing? Destination branding: does tourist photography align with how DMOs promote the destination? ]]> Wed, 24 Jan 2024 16:04:21 GMT /slideshow/how-distinct-and-aligned-with-ugc-is-european-capitals-dmo-branding-on-instagram/265768981 NoTubeProject@slideshare.net(NoTubeProject) How distinct and aligned with UGC is European capitals’ DMO branding on Instagram? NoTubeProject Destination positioning: do DMOs promote their destination distinctly in their visual marketing? Destination branding: does tourist photography align with how DMOs promote the destination? <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/enter2024presentationljb-240124160421-22891e86-thumbnail.jpg?width=120&height=120&fit=bounds" /> Destination positioning: do DMOs promote their destination distinctly in their visual marketing? Destination branding: does tourist photography align with how DMOs promote the destination?

How distinct and aligned with UGC is European capitals’ DMO branding on Instagram? from MODUL Technology GmbH

]]> 9 0 https://cdn.slidesharecdn.com/ss_thumbnails/enter2024presentationljb-240124160421-22891e86-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Framing Few Shot Knowledge Graph Completion with Large Language Models /slideshow/framing-few-shot-knowledge-graph-completion-with-large-language-models/261236734 nlp4kgc-semanticsbrasoveanunixonweichselbraunscharl-230921094603-8fd54eec
Knowledge Graph Completion (KGC) from text involves identifying known or unknown entities (nodes) as well as relations (edges) among these entities. Recent work has started to explore the use of Large Language Models (LLMs) for entity detection and relation extraction, due to their Natural Language Understanding (NLU) capabilities. However, LLM performance varies across models and depends on the quality of the prompt engineering. We examine specific relation extraction cases and present a set of examples collected from well-known resources in a small corpus. We provide a set of annotations and identify various issues that occur when using different LLMs for this task. As LLMs will remain a focal point of future KGC research, we conclude with suggestions for improving the KGC process. ]]>
Knowledge Graph Completion (KGC) from text involves identifying known or unknown entities (nodes) as well as relations (edges) among these entities. Recent work has started to explore the use of Large Language Models (LLMs) for entity detection and relation extraction, due to their Natural Language Understanding (NLU) capabilities. However, LLM performance varies across models and depends on the quality of the prompt engineering. We examine specific relation extraction cases and present a set of examples collected from well-known resources in a small corpus. We provide a set of annotations and identify various issues that occur when using different LLMs for this task. As LLMs will remain a focal point of future KGC research, we conclude with suggestions for improving the KGC process. ]]> Thu, 21 Sep 2023 09:46:02 GMT /slideshow/framing-few-shot-knowledge-graph-completion-with-large-language-models/261236734 NoTubeProject@slideshare.net(NoTubeProject) Framing Few Shot Knowledge Graph Completion with Large Language Models NoTubeProject Knowledge Graph Completion (KGC) from text involves identifying known or unknown entities (nodes) as well as relations (edges) among these entities. Recent work has started to explore the use of Large Language Models (LLMs) for entity detection and relation extraction, due to their Natural Language Understanding (NLU) capabilities. However, LLM performance varies across models and depends on the quality of the prompt engineering. We examine specific relation extraction cases and present a set of examples collected from well-known resources in a small corpus. We provide a set of annotations and identify various issues that occur when using different LLMs for this task. As LLMs will remain a focal point of future KGC research, we conclude with suggestions for improving the KGC process. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/nlp4kgc-semanticsbrasoveanunixonweichselbraunscharl-230921094603-8fd54eec-thumbnail.jpg?width=120&height=120&fit=bounds" /> Knowledge Graph Completion (KGC) from text involves identifying known or unknown entities (nodes) as well as relations (edges) among these entities. Recent work has started to explore the use of Large Language Models (LLMs) for entity detection and relation extraction, due to their Natural Language Understanding (NLU) capabilities. However, LLM performance varies across models and depends on the quality of the prompt engineering. We examine specific relation extraction cases and present a set of examples collected from well-known resources in a small corpus. We provide a set of annotations and identify various issues that occur when using different LLMs for this task. As LLMs will remain a focal point of future KGC research, we conclude with suggestions for improving the KGC process.

Framing Few Shot Knowledge Graph Completion with Large Language Models from MODUL Technology GmbH

]]> 163 0 https://cdn.slidesharecdn.com/ss_thumbnails/nlp4kgc-semanticsbrasoveanunixonweichselbraunscharl-230921094603-8fd54eec-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Unsupervised Topic Modeling with BERTopic for Coarse and Fine-Grained News Classification /slideshow/unsupervised-topic-modeling-with-bertopic-for-coarse-and-finegrained-news-classification/258516948 iwann2023coarsefineclassification-230620135311-3c0aace3
Transformer models have achieved state-of-the-art results for news classification tasks, but remain difficult to modify to yield the desired class probabilities in a multi-class setting. Using a neural topic model to create dense topic clusters helps with generating these class probabilities. The presented work uses the BERTopic clustered embeddings model as a preprocessor to eliminate documents that do not belong to any distinct cluster or topic. By combining the resulting embeddings with a Sentence Transformer fine-tuned with SetFit, we obtain a prompt-free framework that demonstrates competitive performance even with few-shot labeled data. Our findings show that incorporating BERTopic in the preprocessing stage leads to a notable improvement in the classification accuracy of news documents. Furthermore, our method outperforms hybrid approaches that combine text and images for news document classification.]]>
Transformer models have achieved state-of-the-art results for news classification tasks, but remain difficult to modify to yield the desired class probabilities in a multi-class setting. Using a neural topic model to create dense topic clusters helps with generating these class probabilities. The presented work uses the BERTopic clustered embeddings model as a preprocessor to eliminate documents that do not belong to any distinct cluster or topic. By combining the resulting embeddings with a Sentence Transformer fine-tuned with SetFit, we obtain a prompt-free framework that demonstrates competitive performance even with few-shot labeled data. Our findings show that incorporating BERTopic in the preprocessing stage leads to a notable improvement in the classification accuracy of news documents. Furthermore, our method outperforms hybrid approaches that combine text and images for news document classification.]]> Tue, 20 Jun 2023 13:53:11 GMT /slideshow/unsupervised-topic-modeling-with-bertopic-for-coarse-and-finegrained-news-classification/258516948 NoTubeProject@slideshare.net(NoTubeProject) Unsupervised Topic Modeling with BERTopic for Coarse and Fine-Grained News Classification NoTubeProject Transformer models have achieved state-of-the-art results for news classification tasks, but remain difficult to modify to yield the desired class probabilities in a multi-class setting. Using a neural topic model to create dense topic clusters helps with generating these class probabilities. The presented work uses the BERTopic clustered embeddings model as a preprocessor to eliminate documents that do not belong to any distinct cluster or topic. By combining the resulting embeddings with a Sentence Transformer fine-tuned with SetFit, we obtain a prompt-free framework that demonstrates competitive performance even with few-shot labeled data. Our findings show that incorporating BERTopic in the preprocessing stage leads to a notable improvement in the classification accuracy of news documents. Furthermore, our method outperforms hybrid approaches that combine text and images for news document classification. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/iwann2023coarsefineclassification-230620135311-3c0aace3-thumbnail.jpg?width=120&height=120&fit=bounds" /> Transformer models have achieved state-of-the-art results for news classification tasks, but remain difficult to modify to yield the desired class probabilities in a multi-class setting. Using a neural topic model to create dense topic clusters helps with generating these class probabilities. The presented work uses the BERTopic clustered embeddings model as a preprocessor to eliminate documents that do not belong to any distinct cluster or topic. By combining the resulting embeddings with a Sentence Transformer fine-tuned with SetFit, we obtain a prompt-free framework that demonstrates competitive performance even with few-shot labeled data. Our findings show that incorporating BERTopic in the preprocessing stage leads to a notable improvement in the classification accuracy of news documents. Furthermore, our method outperforms hybrid approaches that combine text and images for news document classification.

Unsupervised Topic Modeling with BERTopic for Coarse and Fine-Grained News Classification from MODUL Technology GmbH

]]> 409 0 https://cdn.slidesharecdn.com/ss_thumbnails/iwann2023coarsefineclassification-230620135311-3c0aace3-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Breaking New Ground with EPOCH: AI and Web Intelligence Transform Price Forecasting /slideshow/breaking-new-ground-with-epoch-ai-and-web-intelligence-transform-price-forecasting/257699626 epochwp3-230505125211-13fcfaa2
The FFG funded project EPOCH, coordinated by MODUL Technology, demonstrated the groundbreaking use of machine learning/AI approaches to time series forecasting combined with Web intelligence - the analysis of topics and trends in online news and social media over time.]]>
The FFG funded project EPOCH, coordinated by MODUL Technology, demonstrated the groundbreaking use of machine learning/AI approaches to time series forecasting combined with Web intelligence - the analysis of topics and trends in online news and social media over time.]]> Fri, 05 May 2023 12:52:11 GMT /slideshow/breaking-new-ground-with-epoch-ai-and-web-intelligence-transform-price-forecasting/257699626 NoTubeProject@slideshare.net(NoTubeProject) Breaking New Ground with EPOCH: AI and Web Intelligence Transform Price Forecasting NoTubeProject The FFG funded project EPOCH, coordinated by MODUL Technology, demonstrated the groundbreaking use of machine learning/AI approaches to time series forecasting combined with Web intelligence - the analysis of topics and trends in online news and social media over time. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/epochwp3-230505125211-13fcfaa2-thumbnail.jpg?width=120&height=120&fit=bounds" /> The FFG funded project EPOCH, coordinated by MODUL Technology, demonstrated the groundbreaking use of machine learning/AI approaches to time series forecasting combined with Web intelligence - the analysis of topics and trends in online news and social media over time.

Breaking New Ground with EPOCH: AI and Web Intelligence Transform Price Forecasting from MODUL Technology GmbH

]]> 12 0 https://cdn.slidesharecdn.com/ss_thumbnails/epochwp3-230505125211-13fcfaa2-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 New Opportunities for Understanding Tourist Photography.pptx /slideshow/new-opportunities-for-understanding-tourist-photographypptx/257560403 newopportunitiesforunderstandingtouristphotography-230425145023-1c9cd3d2
Developments in AI such as neural networks, deep learning and AGI have meant that computational understanding of images and videos appears easier than ever. However for tourism and destination marketing it is important to consider how to fine tune models to meet the needs of touristic understanding of user photography.]]>
Developments in AI such as neural networks, deep learning and AGI have meant that computational understanding of images and videos appears easier than ever. However for tourism and destination marketing it is important to consider how to fine tune models to meet the needs of touristic understanding of user photography.]]> Tue, 25 Apr 2023 14:50:22 GMT /slideshow/new-opportunities-for-understanding-tourist-photographypptx/257560403 NoTubeProject@slideshare.net(NoTubeProject) New Opportunities for Understanding Tourist Photography.pptx NoTubeProject Developments in AI such as neural networks, deep learning and AGI have meant that computational understanding of images and videos appears easier than ever. However for tourism and destination marketing it is important to consider how to fine tune models to meet the needs of touristic understanding of user photography. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/newopportunitiesforunderstandingtouristphotography-230425145023-1c9cd3d2-thumbnail.jpg?width=120&height=120&fit=bounds" /> Developments in AI such as neural networks, deep learning and AGI have meant that computational understanding of images and videos appears easier than ever. However for tourism and destination marketing it is important to consider how to fine tune models to meet the needs of touristic understanding of user photography.

New Opportunities for Understanding Tourist Photography.pptx from MODUL Technology GmbH

]]> 50 0 https://cdn.slidesharecdn.com/ss_thumbnails/newopportunitiesforunderstandingtouristphotography-230425145023-1c9cd3d2-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 How do destinations relate to one another? A study of visual destination branding on Instagram /slideshow/how-do-destinations-relate-to-one-another-a-study-of-visual-destination-branding-on-instagram/255390281 enter2023lyndonnixon-230118105214-ee136a72
Destination marketers are aware that online communication about their des-tination is increasingly dependent on visual media rather than text, due to the growing popularity of social networks such as Instagram. An accurate understanding of how the destination is being presented to users in this me-dium is critical for digital marketing activities, e.g. to know if the desired destination brand is present or if visitors focus on other aspects of the desti-nation than those being promoted in marketing. Unlike text mining, which has well established techniques to extract keywords and associations from text corpora, a consistent approach to understanding the content of images and expressing the resulting destination brand is lacking. This paper presents a visual classifier trained and fine-tuned specifically for destination brand measurement from images using 18 visual classes. It presents an exploratory study of how different destinations are being presented visually on Instagram and discusses how these insights could be used by destination marketers to adapt and improve their digital marketing.]]>
Destination marketers are aware that online communication about their des-tination is increasingly dependent on visual media rather than text, due to the growing popularity of social networks such as Instagram. An accurate understanding of how the destination is being presented to users in this me-dium is critical for digital marketing activities, e.g. to know if the desired destination brand is present or if visitors focus on other aspects of the desti-nation than those being promoted in marketing. Unlike text mining, which has well established techniques to extract keywords and associations from text corpora, a consistent approach to understanding the content of images and expressing the resulting destination brand is lacking. This paper presents a visual classifier trained and fine-tuned specifically for destination brand measurement from images using 18 visual classes. It presents an exploratory study of how different destinations are being presented visually on Instagram and discusses how these insights could be used by destination marketers to adapt and improve their digital marketing.]]> Wed, 18 Jan 2023 10:52:14 GMT /slideshow/how-do-destinations-relate-to-one-another-a-study-of-visual-destination-branding-on-instagram/255390281 NoTubeProject@slideshare.net(NoTubeProject) How do destinations relate to one another? A study of visual destination branding on Instagram NoTubeProject Destination marketers are aware that online communication about their des-tination is increasingly dependent on visual media rather than text, due to the growing popularity of social networks such as Instagram. An accurate understanding of how the destination is being presented to users in this me-dium is critical for digital marketing activities, e.g. to know if the desired destination brand is present or if visitors focus on other aspects of the desti-nation than those being promoted in marketing. Unlike text mining, which has well established techniques to extract keywords and associations from text corpora, a consistent approach to understanding the content of images and expressing the resulting destination brand is lacking. This paper presents a visual classifier trained and fine-tuned specifically for destination brand measurement from images using 18 visual classes. It presents an exploratory study of how different destinations are being presented visually on Instagram and discusses how these insights could be used by destination marketers to adapt and improve their digital marketing. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/enter2023lyndonnixon-230118105214-ee136a72-thumbnail.jpg?width=120&height=120&fit=bounds" /> Destination marketers are aware that online communication about their des-tination is increasingly dependent on visual media rather than text, due to the growing popularity of social networks such as Instagram. An accurate understanding of how the destination is being presented to users in this me-dium is critical for digital marketing activities, e.g. to know if the desired destination brand is present or if visitors focus on other aspects of the desti-nation than those being promoted in marketing. Unlike text mining, which has well established techniques to extract keywords and associations from text corpora, a consistent approach to understanding the content of images and expressing the resulting destination brand is lacking. This paper presents a visual classifier trained and fine-tuned specifically for destination brand measurement from images using 18 visual classes. It presents an exploratory study of how different destinations are being presented visually on Instagram and discusses how these insights could be used by destination marketers to adapt and improve their digital marketing.

How do destinations relate to one another? A study of visual destination branding on Instagram from MODUL Technology GmbH

]]> 22 0 https://cdn.slidesharecdn.com/ss_thumbnails/enter2023lyndonnixon-230118105214-ee136a72-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Do DMOs promote the right aspects of the destination? A study of Instagram photography with a visual classifier. /slideshow/do-dmos-promote-the-right-aspects-of-the-destination-a-study-of-instagram-photography-with-a-visual-classifier/250988955 copyofenter2022ppttemplate-220113092640
As global travel emerges from the pandemic, pent up interest in travel will lead to consumers making their choice between global destinations. Insta-gram is a key source of destination inspiration. DMO marketing success on this channel relies on projecting a destination image that resonates with this target group. However, usual text-based marketing intelligence on this channel does not work as content is consumed first and foremost as a visual projection. The author has built a deep learning based visual classifier for destination image measure-ment from photos. In this paper, we compare projected and perceived destination images in Instagram photography for four of the most Instagrammed destinations worldwide. We find that whereas the projected destination image aligns well to the perceived image, there are specific aspects of the destinations that are of more interest to Instagrammers than reflected in the current destination marketing.]]>
As global travel emerges from the pandemic, pent up interest in travel will lead to consumers making their choice between global destinations. Insta-gram is a key source of destination inspiration. DMO marketing success on this channel relies on projecting a destination image that resonates with this target group. However, usual text-based marketing intelligence on this channel does not work as content is consumed first and foremost as a visual projection. The author has built a deep learning based visual classifier for destination image measure-ment from photos. In this paper, we compare projected and perceived destination images in Instagram photography for four of the most Instagrammed destinations worldwide. We find that whereas the projected destination image aligns well to the perceived image, there are specific aspects of the destinations that are of more interest to Instagrammers than reflected in the current destination marketing.]]> Thu, 13 Jan 2022 09:26:39 GMT /slideshow/do-dmos-promote-the-right-aspects-of-the-destination-a-study-of-instagram-photography-with-a-visual-classifier/250988955 NoTubeProject@slideshare.net(NoTubeProject) Do DMOs promote the right aspects of the destination? A study of Instagram photography with a visual classifier. NoTubeProject As global travel emerges from the pandemic, pent up interest in travel will lead to consumers making their choice between global destinations. Insta-gram is a key source of destination inspiration. DMO marketing success on this channel relies on projecting a destination image that resonates with this target group. However, usual text-based marketing intelligence on this channel does not work as content is consumed first and foremost as a visual projection. The author has built a deep learning based visual classifier for destination image measure-ment from photos. In this paper, we compare projected and perceived destination images in Instagram photography for four of the most Instagrammed destinations worldwide. We find that whereas the projected destination image aligns well to the perceived image, there are specific aspects of the destinations that are of more interest to Instagrammers than reflected in the current destination marketing. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/copyofenter2022ppttemplate-220113092640-thumbnail.jpg?width=120&height=120&fit=bounds" /> As global travel emerges from the pandemic, pent up interest in travel will lead to consumers making their choice between global destinations. Insta-gram is a key source of destination inspiration. DMO marketing success on this channel relies on projecting a destination image that resonates with this target group. However, usual text-based marketing intelligence on this channel does not work as content is consumed first and foremost as a visual projection. The author has built a deep learning based visual classifier for destination image measure-ment from photos. In this paper, we compare projected and perceived destination images in Instagram photography for four of the most Instagrammed destinations worldwide. We find that whereas the projected destination image aligns well to the perceived image, there are specific aspects of the destinations that are of more interest to Instagrammers than reflected in the current destination marketing.

Do DMOs promote the right aspects of the destination? A study of Instagram photography with a visual classifier. from MODUL Technology GmbH

]]> 208 0 https://cdn.slidesharecdn.com/ss_thumbnails/copyofenter2022ppttemplate-220113092640-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 The Impact of Social Media on perceived Destination Image: case of Mexico City on Instagram /slideshow/the-impact-of-social-media-on-perceived-destination-image-case-of-mexico-city-on-instagram/129985910 enter2019-190131094807
This presentation considers if, and to what extent, visual social media can change the viewer’s perceived image of a tourism destination as well as which types of visual content are most effective in projecting a destination image. The results from an online survey, which compared three different test groups and their image of Mexico City, showed that UGC images from Instagram, as well as random Google images, were more effective at improving destination image than the UGC images reposted by a DMO. Additionally, the study used image annotations to determine which features in images were most important in terms of their contribution to an improvement in overall destination image, presenting a re-usable set of visual features for future work on using annotations in the measurement of visual destination image. ]]>
This presentation considers if, and to what extent, visual social media can change the viewer’s perceived image of a tourism destination as well as which types of visual content are most effective in projecting a destination image. The results from an online survey, which compared three different test groups and their image of Mexico City, showed that UGC images from Instagram, as well as random Google images, were more effective at improving destination image than the UGC images reposted by a DMO. Additionally, the study used image annotations to determine which features in images were most important in terms of their contribution to an improvement in overall destination image, presenting a re-usable set of visual features for future work on using annotations in the measurement of visual destination image. ]]> Thu, 31 Jan 2019 09:48:07 GMT /slideshow/the-impact-of-social-media-on-perceived-destination-image-case-of-mexico-city-on-instagram/129985910 NoTubeProject@slideshare.net(NoTubeProject) The Impact of Social Media on perceived Destination Image: case of Mexico City on Instagram NoTubeProject This presentation considers if, and to what extent, visual social media can change the viewer’s perceived image of a tourism destination as well as which types of visual content are most effective in projecting a destination image. The results from an online survey, which compared three different test groups and their image of Mexico City, showed that UGC images from Instagram, as well as random Google images, were more effective at improving destination image than the UGC images reposted by a DMO. Additionally, the study used image annotations to determine which features in images were most important in terms of their contribution to an improvement in overall destination image, presenting a re-usable set of visual features for future work on using annotations in the measurement of visual destination image. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/enter2019-190131094807-thumbnail.jpg?width=120&height=120&fit=bounds" /> This presentation considers if, and to what extent, visual social media can change the viewer’s perceived image of a tourism destination as well as which types of visual content are most effective in projecting a destination image. The results from an online survey, which compared three different test groups and their image of Mexico City, showed that UGC images from Instagram, as well as random Google images, were more effective at improving destination image than the UGC images reposted by a DMO. Additionally, the study used image annotations to determine which features in images were most important in terms of their contribution to an improvement in overall destination image, presenting a re-usable set of visual features for future work on using annotations in the measurement of visual destination image.

The Impact of Social Media on perceived Destination Image: case of Mexico City on Instagram from MODUL Technology GmbH

]]> 326 4 https://cdn.slidesharecdn.com/ss_thumbnails/enter2019-190131094807-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 The Impact of Social Media on perceived Destination Image:�the case of Mexico City on Instagram /slideshow/the-impact-of-social-media-on-perceived-destination-imagethe-case-of-mexico-city-on-instagram-119027724/119027724 ifittspain2018-181010190754
This presentation considers if, and to what extent, social media can change the viewer’s image of a tourism destination as well as which types of visual content are most effective. The results from an online survey, which compared three different test groups and their image of Mexico City, showed that UGC images from Instagram, as well as random Google images, were more effective at improving destination image than UGC images reposted by a DMO. Additionally, the study used image annotation to determine which features in images were most important in terms of their contribution to an improvement in overall destination image. ]]>
This presentation considers if, and to what extent, social media can change the viewer’s image of a tourism destination as well as which types of visual content are most effective. The results from an online survey, which compared three different test groups and their image of Mexico City, showed that UGC images from Instagram, as well as random Google images, were more effective at improving destination image than UGC images reposted by a DMO. Additionally, the study used image annotation to determine which features in images were most important in terms of their contribution to an improvement in overall destination image. ]]> Wed, 10 Oct 2018 19:07:54 GMT /slideshow/the-impact-of-social-media-on-perceived-destination-imagethe-case-of-mexico-city-on-instagram-119027724/119027724 NoTubeProject@slideshare.net(NoTubeProject) The Impact of Social Media on perceived Destination Image:�the case of Mexico City on Instagram NoTubeProject This presentation considers if, and to what extent, social media can change the viewer’s image of a tourism destination as well as which types of visual content are most effective. The results from an online survey, which compared three different test groups and their image of Mexico City, showed that UGC images from Instagram, as well as random Google images, were more effective at improving destination image than UGC images reposted by a DMO. Additionally, the study used image annotation to determine which features in images were most important in terms of their contribution to an improvement in overall destination image. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ifittspain2018-181010190754-thumbnail.jpg?width=120&height=120&fit=bounds" /> This presentation considers if, and to what extent, social media can change the viewer’s image of a tourism destination as well as which types of visual content are most effective. The results from an online survey, which compared three different test groups and their image of Mexico City, showed that UGC images from Instagram, as well as random Google images, were more effective at improving destination image than UGC images reposted by a DMO. Additionally, the study used image annotation to determine which features in images were most important in terms of their contribution to an improvement in overall destination image.

The Impact of Social Media on perceived Destination Image: the case of Mexico City on Instagram from MODUL Technology GmbH

]]> 547 5 https://cdn.slidesharecdn.com/ss_thumbnails/ifittspain2018-181010190754-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 How Instagram influences Visual Destination Image - a case study of Jordan and Costa Rica /slideshow/how-instagram-influences-visual-destination-image-a-case-study-of-jordan-and-costa-rica-81847212/81847212 enter2017presentation-171110100701
The Social Web is increasingly taking up the daily time of consumers and is becoming a primary source of impressions about tourism destinations. The recent shift towards more visual content, as evidenced in the fast growing social network Instagram being largely a photo sharing site, means that DMOs need to consider how photos of their destinations can be influencing consumers’ destination image. We present what may be the first study on how the selection of images from a social media site (Instagram) to promote a destination can be used to influence destination image. As a basis for our study, we have selected the DMO channels of Jordan and Costa Rica in Instagram. Through focus groups and a Likert-scale survey, we draw first conclusions on which types of photos are most effective to positively promote a destination and how the consumers’ previous image of a destination could affect this]]>
The Social Web is increasingly taking up the daily time of consumers and is becoming a primary source of impressions about tourism destinations. The recent shift towards more visual content, as evidenced in the fast growing social network Instagram being largely a photo sharing site, means that DMOs need to consider how photos of their destinations can be influencing consumers’ destination image. We present what may be the first study on how the selection of images from a social media site (Instagram) to promote a destination can be used to influence destination image. As a basis for our study, we have selected the DMO channels of Jordan and Costa Rica in Instagram. Through focus groups and a Likert-scale survey, we draw first conclusions on which types of photos are most effective to positively promote a destination and how the consumers’ previous image of a destination could affect this]]> Fri, 10 Nov 2017 10:07:01 GMT /slideshow/how-instagram-influences-visual-destination-image-a-case-study-of-jordan-and-costa-rica-81847212/81847212 NoTubeProject@slideshare.net(NoTubeProject) How Instagram influences Visual Destination Image - a case study of Jordan and Costa Rica NoTubeProject The Social Web is increasingly taking up the daily time of consumers and is becoming a primary source of impressions about tourism destinations. The recent shift towards more visual content, as evidenced in the fast growing social network Instagram being largely a photo sharing site, means that DMOs need to consider how photos of their destinations can be influencing consumers’ destination image. We present what may be the first study on how the selection of images from a social media site (Instagram) to promote a destination can be used to influence destination image. As a basis for our study, we have selected the DMO channels of Jordan and Costa Rica in Instagram. Through focus groups and a Likert-scale survey, we draw first conclusions on which types of photos are most effective to positively promote a destination and how the consumers’ previous image of a destination could affect this <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/enter2017presentation-171110100701-thumbnail.jpg?width=120&height=120&fit=bounds" /> The Social Web is increasingly taking up the daily time of consumers and is becoming a primary source of impressions about tourism destinations. The recent shift towards more visual content, as evidenced in the fast growing social network Instagram being largely a photo sharing site, means that DMOs need to consider how photos of their destinations can be influencing consumers’ destination image. We present what may be the first study on how the selection of images from a social media site (Instagram) to promote a destination can be used to influence destination image. As a basis for our study, we have selected the DMO channels of Jordan and Costa Rica in Instagram. Through focus groups and a Likert-scale survey, we draw first conclusions on which types of photos are most effective to positively promote a destination and how the consumers’ previous image of a destination could affect this

How Instagram influences Visual Destination Image - a case study of Jordan and Costa Rica from MODUL Technology GmbH

]]> 685 4 https://cdn.slidesharecdn.com/ss_thumbnails/enter2017presentation-171110100701-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Media mining for smarter tourism /slideshow/media-mining-for-smarter-tourism/81752766 smartertourism-171108114425
I address the rapid increase in non-textual content being shared online around tourism destinations and how this necesitates new media technologies for tourism stakeholders such as DMOs. Current platforms for "tourism intelligence" (providing actionable insights to tourism marketers based on online analysis of the discussions and content around their destinations) rely on text; to add images and videos at scale we would need accurate machine annotation. My talk will provide initial insights into this field of study and hopefully encourage a greater consideration of how to handle multimedia in future tourism research. ]]>
I address the rapid increase in non-textual content being shared online around tourism destinations and how this necesitates new media technologies for tourism stakeholders such as DMOs. Current platforms for "tourism intelligence" (providing actionable insights to tourism marketers based on online analysis of the discussions and content around their destinations) rely on text; to add images and videos at scale we would need accurate machine annotation. My talk will provide initial insights into this field of study and hopefully encourage a greater consideration of how to handle multimedia in future tourism research. ]]> Wed, 08 Nov 2017 11:44:25 GMT /slideshow/media-mining-for-smarter-tourism/81752766 NoTubeProject@slideshare.net(NoTubeProject) Media mining for smarter tourism NoTubeProject I address the rapid increase in non-textual content being shared online around tourism destinations and how this necesitates new media technologies for tourism stakeholders such as DMOs. Current platforms for "tourism intelligence" (providing actionable insights to tourism marketers based on online analysis of the discussions and content around their destinations) rely on text; to add images and videos at scale we would need accurate machine annotation. My talk will provide initial insights into this field of study and hopefully encourage a greater consideration of how to handle multimedia in future tourism research. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/smartertourism-171108114425-thumbnail.jpg?width=120&height=120&fit=bounds" /> I address the rapid increase in non-textual content being shared online around tourism destinations and how this necesitates new media technologies for tourism stakeholders such as DMOs. Current platforms for "tourism intelligence" (providing actionable insights to tourism marketers based on online analysis of the discussions and content around their destinations) rely on text; to add images and videos at scale we would need accurate machine annotation. My talk will provide initial insights into this field of study and hopefully encourage a greater consideration of how to handle multimedia in future tourism research.

Media mining for smarter tourism from MODUL Technology GmbH

]]> 444 2 https://cdn.slidesharecdn.com/ss_thumbnails/smartertourism-171108114425-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 NoTube: Pattern-based Recommendations (part 3) /slideshow/notube-patternbased-recommendations-part-3/12195188 wp3-part3-120328112157-phpapp01
]]>
]]> Wed, 28 Mar 2012 11:21:54 GMT /slideshow/notube-patternbased-recommendations-part-3/12195188 NoTubeProject@slideshare.net(NoTubeProject) NoTube: Pattern-based Recommendations (part 3) NoTubeProject <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/wp3-part3-120328112157-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" />

NoTube: Pattern-based Recommendations (part 3) from MODUL Technology GmbH

]]> 605 3 https://cdn.slidesharecdn.com/ss_thumbnails/wp3-part3-120328112157-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 NoTube: Pattern-based Recommendations (part 1) /slideshow/notube-patternbased-recommendations-part-1-12195163/12195163 wp3-part1-120328111958-phpapp02
]]>
]]> Wed, 28 Mar 2012 11:19:57 GMT /slideshow/notube-patternbased-recommendations-part-1-12195163/12195163 NoTubeProject@slideshare.net(NoTubeProject) NoTube: Pattern-based Recommendations (part 1) NoTubeProject <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/wp3-part1-120328111958-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" />

NoTube: Pattern-based Recommendations (part 1) from MODUL Technology GmbH

]]> 550 3 https://cdn.slidesharecdn.com/ss_thumbnails/wp3-part1-120328111958-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 NoTube: Pattern-based Recommendations (part 1) /slideshow/notube-patternbased-recommendations-part-1/12195153 wp3-part2a-120328111849-phpapp02
]]>
]]> Wed, 28 Mar 2012 11:18:47 GMT /slideshow/notube-patternbased-recommendations-part-1/12195153 NoTubeProject@slideshare.net(NoTubeProject) NoTube: Pattern-based Recommendations (part 1) NoTubeProject <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/wp3-part2a-120328111849-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" />

NoTube: Pattern-based Recommendations (part 1) from MODUL Technology GmbH

]]> 953 5 https://cdn.slidesharecdn.com/ss_thumbnails/wp3-part2a-120328111849-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 NoTube: Recommendations (Collaborative) /slideshow/notube-recommendations-collaborative/12190614 wp3-part3-120328055059-phpapp02
]]>
]]> Wed, 28 Mar 2012 05:50:58 GMT /slideshow/notube-recommendations-collaborative/12190614 NoTubeProject@slideshare.net(NoTubeProject) NoTube: Recommendations (Collaborative) NoTubeProject <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/wp3-part3-120328055059-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" />

NoTube: Recommendations (Collaborative) from MODUL Technology GmbH

]]> 507 3 https://cdn.slidesharecdn.com/ss_thumbnails/wp3-part3-120328055059-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 NoTube: User Profiling (Beancounter) /slideshow/notube-user-profiling-beancounter/12190606 wp3-part1-120328055006-phpapp01
]]>
]]> Wed, 28 Mar 2012 05:50:03 GMT /slideshow/notube-user-profiling-beancounter/12190606 NoTubeProject@slideshare.net(NoTubeProject) NoTube: User Profiling (Beancounter) NoTubeProject <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/wp3-part1-120328055006-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" />

NoTube: User Profiling (Beancounter) from MODUL Technology GmbH

]]> 829 3 https://cdn.slidesharecdn.com/ss_thumbnails/wp3-part1-120328055006-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 14 no tube dissemination and showcases [compatibility mode] /slideshow/14-no-tube-dissemination-and-showcases-compatibility-mode/12177517 14notubedisseminationandshowcasescompatibilitymode-120327105120-phpapp01
]]>
]]> Tue, 27 Mar 2012 10:51:19 GMT /slideshow/14-no-tube-dissemination-and-showcases-compatibility-mode/12177517 NoTubeProject@slideshare.net(NoTubeProject) 14 no tube dissemination and showcases [compatibility mode] NoTubeProject <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/14notubedisseminationandshowcasescompatibilitymode-120327105120-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" />

14 no tube dissemination and showcases [compatibility mode] from MODUL Technology GmbH

]]> 481 3 https://cdn.slidesharecdn.com/ss_thumbnails/14notubedisseminationandshowcasescompatibilitymode-120327105120-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 NoTube: BBC show case /slideshow/13-no-tube-wp7c-bbc-show-case/12177462 13notubewp7cbbcshowcase-120327104738-phpapp01
]]>
]]> Tue, 27 Mar 2012 10:47:36 GMT /slideshow/13-no-tube-wp7c-bbc-show-case/12177462 NoTubeProject@slideshare.net(NoTubeProject) NoTube: BBC show case NoTubeProject <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/13notubewp7cbbcshowcase-120327104738-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" />

NoTube: BBC show case from MODUL Technology GmbH

]]> 391 4 https://cdn.slidesharecdn.com/ss_thumbnails/13notubewp7cbbcshowcase-120327104738-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://cdn.slidesharecdn.com/profile-photo-NoTubeProject-48x48.jpg?cb=1746705871 MODUL Technology GmbH is your partner in innovative solutions for media and data collection, annotation and linking, integrating extracted and external knowledge into existing workflows and powering new and extended user interfaces and applications such as: news event or topic detection, social media retrieval and analysis, multimedia linking with related information and content, predictive analytics for future events and topics. www.modultech.eu/ https://cdn.slidesharecdn.com/ss_thumbnails/cbmi2024presentation-240919141816-af202648-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/finding-video-shots-for-immersive-journalism-through-text-to-video-search/271900232 Finding video shots fo... https://cdn.slidesharecdn.com/ss_thumbnails/fl9371-240919141149-206b5f1e-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/learning-sustainable-mobility-behaviour-in-post-pandemic-vienna/271900065 LEARNING SUSTAINABLE M... https://cdn.slidesharecdn.com/ss_thumbnails/enter2024presentationljb-240124160421-22891e86-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/how-distinct-and-aligned-with-ugc-is-european-capitals-dmo-branding-on-instagram/265768981 How distinct and align...