�ݺ�ߣshows by User: jieboluo1

�ݺ�ߣshows by User: jieboluo1 / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: jieboluo1 / Fri, 09 Jul 2021 12:18:17 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: jieboluo1 Vision and Language: Past, Present and Future /slideshow/vision-and-language-the-past-present-and-future-249672075/249672075 icme2021keynote-210709121817
ICME 2021 Keynote]]>
ICME 2021 Keynote]]> Fri, 09 Jul 2021 12:18:17 GMT /slideshow/vision-and-language-the-past-present-and-future-249672075/249672075 jieboluo1@slideshare.net(jieboluo1) Vision and Language: Past, Present and Future jieboluo1 ICME 2021 Keynote <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/icme2021keynote-210709121817-thumbnail.jpg?width=120&height=120&fit=bounds" /> ICME 2021 Keynote

Vision and Language: Past, Present and Future from Goergen Institute for Data Science

]]> 832 0 https://cdn.slidesharecdn.com/ss_thumbnails/icme2021keynote-210709121817-thumbnail.jpg?width=120&height=120&fit=bounds document Black http://activitystrea.ms/schema/1.0/post

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

0 Learning with Unpaired Data /slideshow/learning-with-unpaired-data/240103294 learningwithunpaireddata-201214153139
Many learning tasks can be summarized as learning a mapping from a structured input to a structured output, such as machine translation, image captioning, image style transfer, and image dehazing. Such mappings are usually learned on paired training data, where an input sample and its corresponding output are both provided. Collecting paired training data often involves expensive human annotation, and the scale of paired training data is therefore often limited. As a result, the generalization ability of models trained on paired data is also limited. One way to mitigate this issue is learning with unpaired data, which is far less expensive to collect. Taking machine translation as an example, the unpaired training data can be collected separately from newspapers in the source language and target language without any annotation. The challenge of unpaired learning turns into how to align the unpaired data. With carefully designed objectives, unpaired learning has achieved remarkable progress on several tasks. This talk will cover the data collection and training methods of several unpaired learning tasks to illustrate the power of learning with unpaired data. ]]>
Many learning tasks can be summarized as learning a mapping from a structured input to a structured output, such as machine translation, image captioning, image style transfer, and image dehazing. Such mappings are usually learned on paired training data, where an input sample and its corresponding output are both provided. Collecting paired training data often involves expensive human annotation, and the scale of paired training data is therefore often limited. As a result, the generalization ability of models trained on paired data is also limited. One way to mitigate this issue is learning with unpaired data, which is far less expensive to collect. Taking machine translation as an example, the unpaired training data can be collected separately from newspapers in the source language and target language without any annotation. The challenge of unpaired learning turns into how to align the unpaired data. With carefully designed objectives, unpaired learning has achieved remarkable progress on several tasks. This talk will cover the data collection and training methods of several unpaired learning tasks to illustrate the power of learning with unpaired data. ]]> Mon, 14 Dec 2020 15:31:39 GMT /slideshow/learning-with-unpaired-data/240103294 jieboluo1@slideshare.net(jieboluo1) Learning with Unpaired Data jieboluo1 Many learning tasks can be summarized as learning a mapping from a structured input to a structured output, such as machine translation, image captioning, image style transfer, and image dehazing. Such mappings are usually learned on paired training data, where an input sample and its corresponding output are both provided. Collecting paired training data often involves expensive human annotation, and the scale of paired training data is therefore often limited. As a result, the generalization ability of models trained on paired data is also limited. One way to mitigate this issue is learning with unpaired data, which is far less expensive to collect. Taking machine translation as an example, the unpaired training data can be collected separately from newspapers in the source language and target language without any annotation. The challenge of unpaired learning turns into how to align the unpaired data. With carefully designed objectives, unpaired learning has achieved remarkable progress on several tasks. This talk will cover the data collection and training methods of several unpaired learning tasks to illustrate the power of learning with unpaired data. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/learningwithunpaireddata-201214153139-thumbnail.jpg?width=120&height=120&fit=bounds" /> Many learning tasks can be summarized as learning a mapping from a structured input to a structured output, such as machine translation, image captioning, image style transfer, and image dehazing. Such mappings are usually learned on paired training data, where an input sample and its corresponding output are both provided. Collecting paired training data often involves expensive human annotation, and the scale of paired training data is therefore often limited. As a result, the generalization ability of models trained on paired data is also limited. One way to mitigate this issue is learning with unpaired data, which is far less expensive to collect. Taking machine translation as an example, the unpaired training data can be collected separately from newspapers in the source language and target language without any annotation. The challenge of unpaired learning turns into how to align the unpaired data. With carefully designed objectives, unpaired learning has achieved remarkable progress on several tasks. This talk will cover the data collection and training methods of several unpaired learning tasks to illustrate the power of learning with unpaired data.

Learning with Unpaired Data from Goergen Institute for Data Science

]]> 176 0 https://cdn.slidesharecdn.com/ss_thumbnails/learningwithunpaireddata-201214153139-thumbnail.jpg?width=120&height=120&fit=bounds document Black http://activitystrea.ms/schema/1.0/post

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

0 How to properly review AI papers? /slideshow/how-to-properly-review-ai-papers/236771555 howtoproperlyreviewaipapers-200710022751
With the explosive growth in AI related fields, top conferences and journals are struggling to keep up with the tremendous amount of paper submissions. More and more new or inexprienced reviewers are rising to the ocassion. How to become a good reviewer and contribute to the health and growth of the field we all invest in? We will share our perspectives and suggestions. ]]>
With the explosive growth in AI related fields, top conferences and journals are struggling to keep up with the tremendous amount of paper submissions. More and more new or inexprienced reviewers are rising to the ocassion. How to become a good reviewer and contribute to the health and growth of the field we all invest in? We will share our perspectives and suggestions. ]]> Fri, 10 Jul 2020 02:27:50 GMT /slideshow/how-to-properly-review-ai-papers/236771555 jieboluo1@slideshare.net(jieboluo1) How to properly review AI papers? jieboluo1 With the explosive growth in AI related fields, top conferences and journals are struggling to keep up with the tremendous amount of paper submissions. More and more new or inexprienced reviewers are rising to the ocassion. How to become a good reviewer and contribute to the health and growth of the field we all invest in? We will share our perspectives and suggestions. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/howtoproperlyreviewaipapers-200710022751-thumbnail.jpg?width=120&height=120&fit=bounds" /> With the explosive growth in AI related fields, top conferences and journals are struggling to keep up with the tremendous amount of paper submissions. More and more new or inexprienced reviewers are rising to the ocassion. How to become a good reviewer and contribute to the health and growth of the field we all invest in? We will share our perspectives and suggestions.

How to properly review AI papers? from Goergen Institute for Data Science

]]> 650 0 https://cdn.slidesharecdn.com/ss_thumbnails/howtoproperlyreviewaipapers-200710022751-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 Video + Language 2019 /slideshow/video-language-2019/144755688 videolanguage-190510092940
Version 3.0]]>
Version 3.0]]> Fri, 10 May 2019 09:29:40 GMT /slideshow/video-language-2019/144755688 jieboluo1@slideshare.net(jieboluo1) Video + Language 2019 jieboluo1 Version 3.0 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/videolanguage-190510092940-thumbnail.jpg?width=120&height=120&fit=bounds" /> Version 3.0

Video + Language 2019 from Goergen Institute for Data Science

]]> 163 3 https://cdn.slidesharecdn.com/ss_thumbnails/videolanguage-190510092940-thumbnail.jpg?width=120&height=120&fit=bounds document Black http://activitystrea.ms/schema/1.0/post

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

0 Video + Language /slideshow/video-language/144741534 videolanguage-190510064950
Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques.]]>
Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques.]]> Fri, 10 May 2019 06:49:50 GMT /slideshow/video-language/144741534 jieboluo1@slideshare.net(jieboluo1) Video + Language jieboluo1 Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/videolanguage-190510064950-thumbnail.jpg?width=120&height=120&fit=bounds" /> Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques.

Video + Language from Goergen Institute for Data Science

]]> 122 4 https://cdn.slidesharecdn.com/ss_thumbnails/videolanguage-190510064950-thumbnail.jpg?width=120&height=120&fit=bounds document Black http://activitystrea.ms/schema/1.0/post

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

0 When E-commerce Meets Social Media: Identifying Business on WeChat Moment Using Bilateral-Attention LSTM /slideshow/when-ecommerce-meets-social-media-identifying-business-on-wechat-moment-using-bilateralattention-lstm/95091293 www2018-wechat-180426095314
Cognitive Computing Track @WWW 2018 (The Web Conference) Lyon, France April 26, 2018]]>
Cognitive Computing Track @WWW 2018 (The Web Conference) Lyon, France April 26, 2018]]> Thu, 26 Apr 2018 09:53:14 GMT /slideshow/when-ecommerce-meets-social-media-identifying-business-on-wechat-moment-using-bilateralattention-lstm/95091293 jieboluo1@slideshare.net(jieboluo1) When E-commerce Meets Social Media: Identifying Business on WeChat Moment Using Bilateral-Attention LSTM jieboluo1 Cognitive Computing Track @WWW 2018 (The Web Conference) Lyon, France April 26, 2018 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/www2018-wechat-180426095314-thumbnail.jpg?width=120&height=120&fit=bounds" /> Cognitive Computing Track @WWW 2018 (The Web Conference) Lyon, France April 26, 2018

When E-commerce Meets Social Media: Identifying Business on WeChat Moment Using Bilateral-Attention LSTM from Goergen Institute for Data Science

]]> 192 4 https://cdn.slidesharecdn.com/ss_thumbnails/www2018-wechat-180426095314-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 Computer Vision++: Where Do We Go from Here? /slideshow/computer-vision-where-do-we-go-from-here/76530104 cv-170531161656
A speech given at the 2017 Tencent AI Lab Forum, and 2017 Global AI Technology Conference (GAITC) ]]>
A speech given at the 2017 Tencent AI Lab Forum, and 2017 Global AI Technology Conference (GAITC) ]]> Wed, 31 May 2017 16:16:56 GMT /slideshow/computer-vision-where-do-we-go-from-here/76530104 jieboluo1@slideshare.net(jieboluo1) Computer Vision++: Where Do We Go from Here? jieboluo1 A speech given at the 2017 Tencent AI Lab Forum, and 2017 Global AI Technology Conference (GAITC) <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/cv-170531161656-thumbnail.jpg?width=120&height=120&fit=bounds" /> A speech given at the 2017 Tencent AI Lab Forum, and 2017 Global AI Technology Conference (GAITC)

Computer Vision++: Where Do We Go from Here? from Goergen Institute for Data Science

]]> 435 5 https://cdn.slidesharecdn.com/ss_thumbnails/cv-170531161656-thumbnail.jpg?width=120&height=120&fit=bounds document Black http://activitystrea.ms/schema/1.0/post

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

0 A Selfie is Worth a Thousand Words: Mining Personal Patterns behind User Selfie-posting Behaviours /slideshow/a-selfie-is-worth-a-thousand-words-mining-personal-patterns-behind-user-selfieposting-behaviours/74867330 www-selfie-170411060523
Presented at WWW 2017 Perth, Australia]]>
Presented at WWW 2017 Perth, Australia]]> Tue, 11 Apr 2017 06:05:23 GMT /slideshow/a-selfie-is-worth-a-thousand-words-mining-personal-patterns-behind-user-selfieposting-behaviours/74867330 jieboluo1@slideshare.net(jieboluo1) A Selfie is Worth a Thousand Words: Mining Personal Patterns behind User Selfie-posting Behaviours jieboluo1 Presented at WWW 2017 Perth, Australia <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/www-selfie-170411060523-thumbnail.jpg?width=120&height=120&fit=bounds" /> Presented at WWW 2017 Perth, Australia

A Selfie is Worth a Thousand Words: Mining Personal Patterns behind User Selfie-posting Behaviours from Goergen Institute for Data Science

]]> 211 5 https://cdn.slidesharecdn.com/ss_thumbnails/www-selfie-170411060523-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 When Fashion Meets Big Data: Discriminative Mining of Best Selling Clothing Features /slideshow/when-fashion-meets-big-data-discriminative-mining-of-best-selling-clothing-features/74867176 www-fashion-170411060155
Presented at WWW 2017 Perth, Australia]]>
Presented at WWW 2017 Perth, Australia]]> Tue, 11 Apr 2017 06:01:55 GMT /slideshow/when-fashion-meets-big-data-discriminative-mining-of-best-selling-clothing-features/74867176 jieboluo1@slideshare.net(jieboluo1) When Fashion Meets Big Data: Discriminative Mining of Best Selling Clothing Features jieboluo1 Presented at WWW 2017 Perth, Australia <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/www-fashion-170411060155-thumbnail.jpg?width=120&height=120&fit=bounds" /> Presented at WWW 2017 Perth, Australia

When Fashion Meets Big Data: Discriminative Mining of Best Selling Clothing Features from Goergen Institute for Data Science

]]> 678 3 https://cdn.slidesharecdn.com/ss_thumbnails/www-fashion-170411060155-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 Big Data Better Life /slideshow/big-data-better-life/74860135 bigdatabetterlife-uts2017-170411035412
Distinguished Visiting Scholar Lecture University of Technology Sydney]]>
Distinguished Visiting Scholar Lecture University of Technology Sydney]]> Tue, 11 Apr 2017 03:54:11 GMT /slideshow/big-data-better-life/74860135 jieboluo1@slideshare.net(jieboluo1) Big Data Better Life jieboluo1 Distinguished Visiting Scholar Lecture University of Technology Sydney <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/bigdatabetterlife-uts2017-170411035412-thumbnail.jpg?width=120&height=120&fit=bounds" /> Distinguished Visiting Scholar Lecture University of Technology Sydney

Big Data Better Life from Goergen Institute for Data Science

]]> 646 13 https://cdn.slidesharecdn.com/ss_thumbnails/bigdatabetterlife-uts2017-170411035412-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 Social Multimedia as Sensors /slideshow/social-multimedia-as-sensors/67384856 socialmultimediaassensorskdd2016a-161019034715
KDD 2016 Tutorial, part of Collective Sensemaking via Social Sensors)]]>
KDD 2016 Tutorial, part of Collective Sensemaking via Social Sensors)]]> Wed, 19 Oct 2016 03:47:15 GMT /slideshow/social-multimedia-as-sensors/67384856 jieboluo1@slideshare.net(jieboluo1) Social Multimedia as Sensors jieboluo1 KDD 2016 Tutorial, part of Collective Sensemaking via Social Sensors) <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/socialmultimediaassensorskdd2016a-161019034715-thumbnail.jpg?width=120&height=120&fit=bounds" /> KDD 2016 Tutorial, part of Collective Sensemaking via Social Sensors)

Social Multimedia as Sensors from Goergen Institute for Data Science

]]> 218 5 https://cdn.slidesharecdn.com/ss_thumbnails/socialmultimediaassensorskdd2016a-161019034715-thumbnail.jpg?width=120&height=120&fit=bounds document Black http://activitystrea.ms/schema/1.0/post

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

0 Forever Young: A Tribute to the Grandmaster through a recount of Personal Journey /slideshow/forever-young-a-tribute-to-the-grandmaster-through-a-recount-of-personal-journey/66636013 foreveryoung-short-161002033437
The talk at the Huang Symposium to celebrate Tom Huang's 80th Birthday]]>
The talk at the Huang Symposium to celebrate Tom Huang's 80th Birthday]]> Sun, 02 Oct 2016 03:34:37 GMT /slideshow/forever-young-a-tribute-to-the-grandmaster-through-a-recount-of-personal-journey/66636013 jieboluo1@slideshare.net(jieboluo1) Forever Young: A Tribute to the Grandmaster through a recount of Personal Journey jieboluo1 The talk at the Huang Symposium to celebrate Tom Huang's 80th Birthday <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/foreveryoung-short-161002033437-thumbnail.jpg?width=120&height=120&fit=bounds" /> The talk at the Huang Symposium to celebrate Tom Huang's 80th Birthday

Forever Young: A Tribute to the Grandmaster through a recount of Personal Journey from Goergen Institute for Data Science

]]> 247 6 https://cdn.slidesharecdn.com/ss_thumbnails/foreveryoung-short-161002033437-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 Video+Language: From Classification to Description /slideshow/videolanguage-from-classification-to-description/66264181 videolanguage-compimage-160921153334
Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on understanding videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning techniques, researchers in both computer vision and multimedia communities are now striving to bridge videos with natural language, which can be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques, including video-language alignment and video captioning. ]]>
Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on understanding videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning techniques, researchers in both computer vision and multimedia communities are now striving to bridge videos with natural language, which can be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques, including video-language alignment and video captioning. ]]> Wed, 21 Sep 2016 15:33:33 GMT /slideshow/videolanguage-from-classification-to-description/66264181 jieboluo1@slideshare.net(jieboluo1) Video+Language: From Classification to Description jieboluo1 Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on understanding videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning techniques, researchers in both computer vision and multimedia communities are now striving to bridge videos with natural language, which can be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques, including video-language alignment and video captioning. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/videolanguage-compimage-160921153334-thumbnail.jpg?width=120&height=120&fit=bounds" /> Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on understanding videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning techniques, researchers in both computer vision and multimedia communities are now striving to bridge videos with natural language, which can be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques, including video-language alignment and video captioning.

Video+Language: From Classification to Description from Goergen Institute for Data Science

]]> 368 6 https://cdn.slidesharecdn.com/ss_thumbnails/videolanguage-compimage-160921153334-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 Video + Language: Where Does Domain Knowledge Fit in?� /slideshow/video-language-where-does-domain-knowledge-fit-in-63957544/63957544 ijcai-domainknowledge-slideshare2-160712164333
Does deep learning solve all the machine learning problems? Where would domain knowledge fit in? While it is common in medical data analytics to incorporate domain knowledge, we focus on one emerging area in computer vision and language processing, video+language, to answer these questions. Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning and knowledge graph techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques, including video entity linking, video-language alignment, and video captioning, and discuss how domain knowledge can fit in to improve the performance. ]]>
Does deep learning solve all the machine learning problems? Where would domain knowledge fit in? While it is common in medical data analytics to incorporate domain knowledge, we focus on one emerging area in computer vision and language processing, video+language, to answer these questions. Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning and knowledge graph techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques, including video entity linking, video-language alignment, and video captioning, and discuss how domain knowledge can fit in to improve the performance. ]]> Tue, 12 Jul 2016 16:43:33 GMT /slideshow/video-language-where-does-domain-knowledge-fit-in-63957544/63957544 jieboluo1@slideshare.net(jieboluo1) Video + Language: Where Does Domain Knowledge Fit in?� jieboluo1 Does deep learning solve all the machine learning problems? Where would domain knowledge fit in? While it is common in medical data analytics to incorporate domain knowledge, we focus on one emerging area in computer vision and language processing, video+language, to answer these questions. Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning and knowledge graph techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques, including video entity linking, video-language alignment, and video captioning, and discuss how domain knowledge can fit in to improve the performance. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ijcai-domainknowledge-slideshare2-160712164333-thumbnail.jpg?width=120&height=120&fit=bounds" /> Does deep learning solve all the machine learning problems? Where would domain knowledge fit in? While it is common in medical data analytics to incorporate domain knowledge, we focus on one emerging area in computer vision and language processing, video+language, to answer these questions. Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning and knowledge graph techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques, including video entity linking, video-language alignment, and video captioning, and discuss how domain knowledge can fit in to improve the performance.

Video + Language: Where Does Domain Knowledge Fit in? from Goergen Institute for Data Science

]]> 704 5 https://cdn.slidesharecdn.com/ss_thumbnails/ijcai-domainknowledge-slideshare2-160712164333-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 Video + Language: Where Does Domain Knowledge Fit in?� /jieboluo1/video-language-where-does-domain-knowledge-fit-in ijcai-domainknowledge-slideshare2-160712163325
Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning and knowledge graph techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques, including video entity linking, video-language alignment, and video captioning, and discuss how domain knowledge can fit in to improve the performance. ]]>
Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning and knowledge graph techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques, including video entity linking, video-language alignment, and video captioning, and discuss how domain knowledge can fit in to improve the performance. ]]> Tue, 12 Jul 2016 16:33:25 GMT /jieboluo1/video-language-where-does-domain-knowledge-fit-in jieboluo1@slideshare.net(jieboluo1) Video + Language: Where Does Domain Knowledge Fit in?� jieboluo1 Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning and knowledge graph techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques, including video entity linking, video-language alignment, and video captioning, and discuss how domain knowledge can fit in to improve the performance. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ijcai-domainknowledge-slideshare2-160712163325-thumbnail.jpg?width=120&height=120&fit=bounds" /> Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning and knowledge graph techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques, including video entity linking, video-language alignment, and video captioning, and discuss how domain knowledge can fit in to improve the performance.

Video + Language: Where Does Domain Knowledge Fit in? from Goergen Institute for Data Science

]]> 242 4 https://cdn.slidesharecdn.com/ss_thumbnails/ijcai-domainknowledge-slideshare2-160712163325-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 https://cdn.slidesharecdn.com/profile-photo-jieboluo1-48x48.jpg?cb=1643126728 Jiebo Luo is a Professor of Computer Science Department at the University of Rochester. Prior to that, he was a Senior Principal Scientist with Kodak Research. He received a BS degree and an MS degree in Electrical Engineering from the University of Science and Technology of China in 1989 and 1992, respectively, and a PhD degree in Electrical Engineering from the University of Rochester in 1995. Dr. Luo has been actively involved in numerous technical conferences, including serving as a program co-chair of the 2012 IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) and 2010 ACM Multimedia Conference, general chair of the 2018 ACM Multimedia Conference. www.cs.rochester.edu/u/jluo/ https://cdn.slidesharecdn.com/ss_thumbnails/icme2021keynote-210709121817-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/vision-and-language-the-past-present-and-future-249672075/249672075 Vision and Language: P... https://cdn.slidesharecdn.com/ss_thumbnails/learningwithunpaireddata-201214153139-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/learning-with-unpaired-data/240103294 Learning with Unpaired... https://cdn.slidesharecdn.com/ss_thumbnails/howtoproperlyreviewaipapers-200710022751-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/how-to-properly-review-ai-papers/236771555 How to properly review...