狠狠撸shows by User: taniokah

狠狠撸shows by User: taniokah / http://www.slideshare.net/images/logo.gif 狠狠撸shows by User: taniokah / Mon, 02 Sep 2024 08:59:53 GMT 狠狠撸Share feed for 狠狠撸shows by User: taniokah Toward a Dialogue System Using a Large Language Model to Recognize User Emotions with a Camera /slideshow/toward-a-dialogue-system-using-a-large-language-model-to-recognize-user-emotions-with-a-camera/271493008 ro-man2024interaislidev3-240902085953-73a163d4
The performance of ChatGPT? and other LLMs has improved tremendously, and in online environments, they are increasingly likely to be used in a wide variety of situations, such as ChatBot on web pages, call center operations using voice interaction, and dialogue functions using agents. In the offline environment, multimodal dialogue functions are also being realized, such as guidance by Artificial Intelligence agents (AI agents) using tablet terminals and dialogue systems in the form of LLMs mounted on robots. In this multimodal dialogue, mutual emotion recognition between the AI and the user will become important. So far, there have been methods for expressing emotions on the part of the AI agent or for recognizing them using textual or voice information of the user’s utterances, but methods for AI agents to recognize emotions from the user’s facial expressions have not been studied. In this study, we examined whether or not LLM-based AI agents can interact with users according to their emotional states by capturing the user in dialogue with a camera, recognizing emotions from facial expressions, and adding such emotion information to prompts. The results confirmed that AI agents can have conversations according to the emotional state for emotional states with relatively high scores, such as Happy and Angry.]]>
The performance of ChatGPT? and other LLMs has improved tremendously, and in online environments, they are increasingly likely to be used in a wide variety of situations, such as ChatBot on web pages, call center operations using voice interaction, and dialogue functions using agents. In the offline environment, multimodal dialogue functions are also being realized, such as guidance by Artificial Intelligence agents (AI agents) using tablet terminals and dialogue systems in the form of LLMs mounted on robots. In this multimodal dialogue, mutual emotion recognition between the AI and the user will become important. So far, there have been methods for expressing emotions on the part of the AI agent or for recognizing them using textual or voice information of the user’s utterances, but methods for AI agents to recognize emotions from the user’s facial expressions have not been studied. In this study, we examined whether or not LLM-based AI agents can interact with users according to their emotional states by capturing the user in dialogue with a camera, recognizing emotions from facial expressions, and adding such emotion information to prompts. The results confirmed that AI agents can have conversations according to the emotional state for emotional states with relatively high scores, such as Happy and Angry.]]> Mon, 02 Sep 2024 08:59:53 GMT /slideshow/toward-a-dialogue-system-using-a-large-language-model-to-recognize-user-emotions-with-a-camera/271493008 taniokah@slideshare.net(taniokah) Toward a Dialogue System Using a Large Language Model to Recognize User Emotions with a Camera taniokah The performance of ChatGPT? and other LLMs has improved tremendously, and in online environments, they are increasingly likely to be used in a wide variety of situations, such as ChatBot on web pages, call center operations using voice interaction, and dialogue functions using agents. In the offline environment, multimodal dialogue functions are also being realized, such as guidance by Artificial Intelligence agents (AI agents) using tablet terminals and dialogue systems in the form of LLMs mounted on robots. In this multimodal dialogue, mutual emotion recognition between the AI and the user will become important. So far, there have been methods for expressing emotions on the part of the AI agent or for recognizing them using textual or voice information of the user’s utterances, but methods for AI agents to recognize emotions from the user’s facial expressions have not been studied. In this study, we examined whether or not LLM-based AI agents can interact with users according to their emotional states by capturing the user in dialogue with a camera, recognizing emotions from facial expressions, and adding such emotion information to prompts. The results confirmed that AI agents can have conversations according to the emotional state for emotional states with relatively high scores, such as Happy and Angry. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ro-man2024interaislidev3-240902085953-73a163d4-thumbnail.jpg?width=120&height=120&fit=bounds" /> The performance of ChatGPT? and other LLMs has improved tremendously, and in online environments, they are increasingly likely to be used in a wide variety of situations, such as ChatBot on web pages, call center operations using voice interaction, and dialogue functions using agents. In the offline environment, multimodal dialogue functions are also being realized, such as guidance by Artificial Intelligence agents (AI agents) using tablet terminals and dialogue systems in the form of LLMs mounted on robots. In this multimodal dialogue, mutual emotion recognition between the AI and the user will become important. So far, there have been methods for expressing emotions on the part of the AI agent or for recognizing them using textual or voice information of the user’s utterances, but methods for AI agents to recognize emotions from the user’s facial expressions have not been studied. In this study, we examined whether or not LLM-based AI agents can interact with users according to their emotional states by capturing the user in dialogue with a camera, recognizing emotions from facial expressions, and adding such emotion information to prompts. The results confirmed that AI agents can have conversations according to the emotional state for emotional states with relatively high scores, such as Happy and Angry.

Toward a Dialogue System Using a Large Language Model to Recognize User Emotions with a Camera from Hiroki Tanioka

]]> 39 0 https://cdn.slidesharecdn.com/ss_thumbnails/ro-man2024interaislidev3-240902085953-73a163d4-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 笔辞蝉别狈别迟(尘濒5.箩蝉)を用いた投球フォーム推定 /slideshow/posenetml5js/249504932 random-210627095448
闯补惫补厂肠谤颈辫迟(辫5.箩蝉+尘濒5.箩蝉)だけで笔辞蝉别狈别迟を用いた投球フォームを推定してみました。闭闭>
闯补惫补厂肠谤颈辫迟(辫5.箩蝉+尘濒5.箩蝉)だけで笔辞蝉别狈别迟を用いた投球フォームを推定してみました。闭闭> Sun, 27 Jun 2021 09:54:48 GMT /slideshow/posenetml5js/249504932 taniokah@slideshare.net(taniokah) 笔辞蝉别狈别迟(尘濒5.箩蝉)を用いた投球フォーム推定 taniokah 闯补惫补厂肠谤颈辫迟(辫5.箩蝉+尘濒5.箩蝉)だけで笔辞蝉别狈别迟を用いた投球フォームを推定してみました。 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/random-210627095448-thumbnail.jpg?width=120&height=120&fit=bounds" /> 闯补惫补厂肠谤颈辫迟(辫5.箩蝉+尘濒5.箩蝉)だけで笔辞蝉别狈别迟を用いた投球フォームを推定してみました。

笔辞蝉别狈别迟(尘濒5.箩蝉)を用いた投球フォーム推定 from Hiroki Tanioka

]]> 643 0 https://cdn.slidesharecdn.com/ss_thumbnails/random-210627095448-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 おとなのフ?ロク?ラミンク?教室 vol1 /slideshow/vol1-180209842/180209842 programmingforadult-191009032113
大人の皆さんに、小学生向けのプログラミング授业と同じ形式で、プログラミングを学んでいただきました。11名の大人の方々に小学生向けのプログラミング授业を体験していただいた际の资料です。闭闭>
大人の皆さんに、小学生向けのプログラミング授业と同じ形式で、プログラミングを学んでいただきました。11名の大人の方々に小学生向けのプログラミング授业を体験していただいた际の资料です。闭闭> Wed, 09 Oct 2019 03:21:13 GMT /slideshow/vol1-180209842/180209842 taniokah@slideshare.net(taniokah) おとなのフ?ロク?ラミンク?教室 vol1 taniokah 大人の皆さんに、小学生向けのプログラミング授业と同じ形式で、プログラミングを学んでいただきました。11名の大人の方々に小学生向けのプログラミング授业を体験していただいた际の资料です。 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/programmingforadult-191009032113-thumbnail.jpg?width=120&height=120&fit=bounds" /> 大人の皆さんに、小学生向けのプログラミング授业と同じ形式で、プログラミングを学んでいただきました。11名の大人の方々に小学生向けのプログラミング授业を体験していただいた际の资料です。

縺翫→縺ェ縺ョ繝輔ｚ繝ュ繧ッ繧吶Λ繝溘Φ繧ッ繧呎蕗螳、 vol1 from Hiroki Tanioka

]]> 262 1 https://cdn.slidesharecdn.com/ss_thumbnails/programmingforadult-191009032113-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 A Fast Content-Based Image Retrieval Method Using Deep Visual Features /slideshow/a-fast-contentbased-image-retrieval-method-using-deep-visual-features/174471683 icdar-wml-2019taniokah20190921-190921053158
Fast and scalable Content-Based Image Retrieval using visual features is required for document analysis, Medical image analysis, etc. in the present age. Convolutional Neural Network (CNN) activations as features achieved their outstanding performance in this area. Deep Convolutional representations using the softmax function in the output layer are also ones among visual features. However, almost all the image retrieval systems hold their index of visual features on main memory in order to high responsiveness, limiting their applicability for big data applications. In this paper, we propose a fast calculation method of cosine similarity with L2 norm indexed in advance on Elasticsearch. We evaluate our approach with ImageNet Dataset and VGG-16 pre-trained model. The evaluation results show the effectiveness and efficiency of our proposed method.]]>
Fast and scalable Content-Based Image Retrieval using visual features is required for document analysis, Medical image analysis, etc. in the present age. Convolutional Neural Network (CNN) activations as features achieved their outstanding performance in this area. Deep Convolutional representations using the softmax function in the output layer are also ones among visual features. However, almost all the image retrieval systems hold their index of visual features on main memory in order to high responsiveness, limiting their applicability for big data applications. In this paper, we propose a fast calculation method of cosine similarity with L2 norm indexed in advance on Elasticsearch. We evaluate our approach with ImageNet Dataset and VGG-16 pre-trained model. The evaluation results show the effectiveness and efficiency of our proposed method.]]> Sat, 21 Sep 2019 05:31:58 GMT /slideshow/a-fast-contentbased-image-retrieval-method-using-deep-visual-features/174471683 taniokah@slideshare.net(taniokah) A Fast Content-Based Image Retrieval Method Using Deep Visual Features taniokah Fast and scalable Content-Based Image Retrieval using visual features is required for document analysis, Medical image analysis, etc. in the present age. Convolutional Neural Network (CNN) activations as features achieved their outstanding performance in this area. Deep Convolutional representations using the softmax function in the output layer are also ones among visual features. However, almost all the image retrieval systems hold their index of visual features on main memory in order to high responsiveness, limiting their applicability for big data applications. In this paper, we propose a fast calculation method of cosine similarity with L2 norm indexed in advance on Elasticsearch. We evaluate our approach with ImageNet Dataset and VGG-16 pre-trained model. The evaluation results show the effectiveness and efficiency of our proposed method. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/icdar-wml-2019taniokah20190921-190921053158-thumbnail.jpg?width=120&height=120&fit=bounds" /> Fast and scalable Content-Based Image Retrieval using visual features is required for document analysis, Medical image analysis, etc. in the present age. Convolutional Neural Network (CNN) activations as features achieved their outstanding performance in this area. Deep Convolutional representations using the softmax function in the output layer are also ones among visual features. However, almost all the image retrieval systems hold their index of visual features on main memory in order to high responsiveness, limiting their applicability for big data applications. In this paper, we propose a fast calculation method of cosine similarity with L2 norm indexed in advance on Elasticsearch. We evaluate our approach with ImageNet Dataset and VGG-16 pre-trained model. The evaluation results show the effectiveness and efficiency of our proposed method.

A Fast Content-Based Image Retrieval Method Using Deep Visual Features from Hiroki Tanioka

]]> 230 0 https://cdn.slidesharecdn.com/ss_thumbnails/icdar-wml-2019taniokah20190921-190921053158-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 Mentoring without Technical Skills /slideshow/mentoring-without-technical-skills-124569781/124569781 coderdojomentoringguide-181201104856
Mentoring without Technical Skills テクニカルスキルなしで指導する]]>
Mentoring without Technical Skills テクニカルスキルなしで指導する]]> Sat, 01 Dec 2018 10:48:56 GMT /slideshow/mentoring-without-technical-skills-124569781/124569781 taniokah@slideshare.net(taniokah) Mentoring without Technical Skills taniokah Mentoring without Technical Skills テクニカルスキルなしで指導する <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/coderdojomentoringguide-181201104856-thumbnail.jpg?width=120&height=120&fit=bounds" /> Mentoring without Technical Skills テクニカルスキルなしで指導する

Mentoring without Technical Skills from Hiroki Tanioka

]]> 501 3 https://cdn.slidesharecdn.com/ss_thumbnails/coderdojomentoringguide-181201104856-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 グループ学習で学ぶプログラミング ?さあ、いっしょに考えよう！? /slideshow/ss-121018914/121018914 osc2018autumn-181029030740
コンピュータサイエンス、アルゴリズム、デザインパターン、コーディング、開発手法、論理的思考など、あらゆる概念や知識を必要とするプログラミング的思考の習得のために、子ども達は何に取り組めば良いのでしょうか？ITエンジニア、プログラミングスクール、大学教員、CoderDojo、小学校での授業などの経験を通じて得た知見を元に、その答えが日常の中にあることを、具体的な事例を交えてご説明します。 http://coperu.net/forum2018fall]]>
コンピュータサイエンス、アルゴリズム、デザインパターン、コーディング、開発手法、論理的思考など、あらゆる概念や知識を必要とするプログラミング的思考の習得のために、子ども達は何に取り組めば良いのでしょうか？ITエンジニア、プログラミングスクール、大学教員、CoderDojo、小学校での授業などの経験を通じて得た知見を元に、その答えが日常の中にあることを、具体的な事例を交えてご説明します。 http://coperu.net/forum2018fall]]> Mon, 29 Oct 2018 03:07:40 GMT /slideshow/ss-121018914/121018914 taniokah@slideshare.net(taniokah) グループ学習で学ぶプログラミング ?さあ、いっしょに考えよう！? taniokah コンピュータサイエンス、アルゴリズム、デザインパターン、コーディング、開発手法、論理的思考など、あらゆる概念や知識を必要とするプログラミング的思考の習得のために、子ども達は何に取り組めば良いのでしょうか？ITエンジニア、プログラミングスクール、大学教員、CoderDojo、小学校での授業などの経験を通じて得た知見を元に、その答えが日常の中にあることを、具体的な事例を交えてご説明します。 http://coperu.net/forum2018fall <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/osc2018autumn-181029030740-thumbnail.jpg?width=120&height=120&fit=bounds" /> コンピュータサイエンス、アルゴリズム、デザインパターン、コーディング、開発手法、論理的思考など、あらゆる概念や知識を必要とするプログラミング的思考の習得のために、子ども達は何に取り組めば良いのでしょうか？ITエンジニア、プログラミングスクール、大学教員、CoderDojo、小学校での授業などの経験を通じて得た知見を元に、その答えが日常の中にあることを、具体的な事例を交えてご説明します。 http://coperu.net/forum2018fall

グループ学習で学ぶプログラミング ?さあ、いっしょに考えよう！? from Hiroki Tanioka

]]> 164 1 https://cdn.slidesharecdn.com/ss_thumbnails/osc2018autumn-181029030740-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 理想の础滨と现実の机械学习 /slideshow/ai-79038555/79038555 2017-3-170822030036
机械学习分野の技术の进歩により、世はまさに空前の础滨ブームとなっています。このような状况で、市场や経営层から求められる础滨と、现场が取り组む机械学习とのギャップの存在を明らかにし、そのギャップをいかにして埋めるか、そしてこれから取り组むべき础滨と机械学习の方向性について、提案します。闭闭>
机械学习分野の技术の进歩により、世はまさに空前の础滨ブームとなっています。このような状况で、市场や経営层から求められる础滨と、现场が取り组む机械学习とのギャップの存在を明らかにし、そのギャップをいかにして埋めるか、そしてこれから取り组むべき础滨と机械学习の方向性について、提案します。闭闭> Tue, 22 Aug 2017 03:00:36 GMT /slideshow/ai-79038555/79038555 taniokah@slideshare.net(taniokah) 理想の础滨と现実の机械学习 taniokah 机械学习分野の技术の进歩により、世はまさに空前の础滨ブームとなっています。このような状况で、市场や経営层から求められる础滨と、现场が取り组む机械学习とのギャップの存在を明らかにし、そのギャップをいかにして埋めるか、そしてこれから取り组むべき础滨と机械学习の方向性について、提案します。 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/2017-3-170822030036-thumbnail.jpg?width=120&height=120&fit=bounds" /> 机械学习分野の技术の进歩により、世はまさに空前の础滨ブームとなっています。このような状况で、市场や経営层から求められる础滨と、现场が取り组む机械学习とのギャップの存在を明らかにし、そのギャップをいかにして埋めるか、そしてこれから取り组むべき础滨と机械学习の方向性について、提案します。

理想の础滨と现実の机械学习 from Hiroki Tanioka

]]> 299 2 https://cdn.slidesharecdn.com/ss_thumbnails/2017-3-170822030036-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 Super Easy Way of Building Image Search with Keras /slideshow/super-easy-way-of-building-image-search-with-keras/79038488 presentation-170822025737
This paper provides detailed suggestions to create an Image Search Engine with Deep Learning. There are still few attempts with Deep Learning on a search engine. Here is a good idea of an extremely easy way of building an image search with Elasticsearch and Keras on Jupyter Notebook. So, it is demonstrated how an image search engine can be created where Keras is used to extract features from images, and Elasticsearch is used for indexing and retrieval.]]>
This paper provides detailed suggestions to create an Image Search Engine with Deep Learning. There are still few attempts with Deep Learning on a search engine. Here is a good idea of an extremely easy way of building an image search with Elasticsearch and Keras on Jupyter Notebook. So, it is demonstrated how an image search engine can be created where Keras is used to extract features from images, and Elasticsearch is used for indexing and retrieval.]]> Tue, 22 Aug 2017 02:57:37 GMT /slideshow/super-easy-way-of-building-image-search-with-keras/79038488 taniokah@slideshare.net(taniokah) Super Easy Way of Building Image Search with Keras taniokah This paper provides detailed suggestions to create an Image Search Engine with Deep Learning. There are still few attempts with Deep Learning on a search engine. Here is a good idea of an extremely easy way of building an image search with Elasticsearch and Keras on Jupyter Notebook. So, it is demonstrated how an image search engine can be created where Keras is used to extract features from images, and Elasticsearch is used for indexing and retrieval. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/presentation-170822025737-thumbnail.jpg?width=120&height=120&fit=bounds" /> This paper provides detailed suggestions to create an Image Search Engine with Deep Learning. There are still few attempts with Deep Learning on a search engine. Here is a good idea of an extremely easy way of building an image search with Elasticsearch and Keras on Jupyter Notebook. So, it is demonstrated how an image search engine can be created where Keras is used to extract features from images, and Elasticsearch is used for indexing and retrieval.

Super Easy Way of Building Image Search with Keras from Hiroki Tanioka

]]> 328 4 https://cdn.slidesharecdn.com/ss_thumbnails/presentation-170822025737-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 ソフトウェア开発の心得 /slideshow/2-12243928/12243928 2-120401111325-phpapp02
]]>
]]> Sun, 01 Apr 2012 11:13:23 GMT /slideshow/2-12243928/12243928 taniokah@slideshare.net(taniokah) ソフトウェア开発の心得 taniokah <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/2-120401111325-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" />

ソフトウェア开発の心得 from Hiroki Tanioka

]]> 959 3 https://cdn.slidesharecdn.com/ss_thumbnails/2-120401111325-phpapp02-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-taniokah-48x48.jpg?cb=1735206713 I am a Japanese software researcher and developer. Also I can manage research and development project. My research areas include Machine Learning, Natural Language Processing, Information Retrieval, Clustering and Spam Detection. Just a note to tell you that my strongth is acting as intermediary between the research and the others, e.g. transfering from research results to products. Specialties: IT research, project management and personnel training. Intellectual Property Management Skill and union negotiation. Languages: C++, VC++ , Java , JavaScript, PL/SQL(a bit), etc. Platforms: Windows, Linux, Mac(a bit), etc. English: TOEIC score 825 (2010) facebook.com/taniokah https://cdn.slidesharecdn.com/ss_thumbnails/ro-man2024interaislidev3-240902085953-73a163d4-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/toward-a-dialogue-system-using-a-large-language-model-to-recognize-user-emotions-with-a-camera/271493008 Toward a Dialogue Syst... https://cdn.slidesharecdn.com/ss_thumbnails/random-210627095448-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/posenetml5js/249504932 笔辞蝉别狈别迟(尘濒5.箩蝉)を用いた投球フ... https://cdn.slidesharecdn.com/ss_thumbnails/programmingforadult-191009032113-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/vol1-180209842/180209842 おとなのフ?ロク?ラミンク?教室 vol1