Đăng nhập
 
Tìm kiếm nâng cao
 
Tên bài báo
Tác giả
Năm xuất bản
Tóm tắt
Lĩnh vực
Phân loại
Số tạp chí
 

Bản tin định kỳ
Báo cáo thường niên
Tạp chí khoa học ĐHCT
Tạp chí tiếng anh ĐHCT
Tạp chí trong nước
Tạp chí quốc tế
Kỷ yếu HN trong nước
Kỷ yếu HN quốc tế
Book chapter
Bài báo - Tạp chí
(2021) Trang: 63-69
Tạp chí: The 7th International Conference on Fuzzy Systems and Data Mining, 26-29/10/2021
Liên kết: 10.3233/FAIA210176

This paper discusses a facial expression recognition model and a description generation model to build descriptive sentences for images and facial expressions of people in images. Our study shows that YOLOv5 achieves better results than a traditional CNN for all emotions on the KDEF dataset. In particular, the accuracies of the CNN and YOLOv5 models for emotion recognition are 0.853 and 0.938, respectively. A model for generating descriptions for images based on a merged architecture is proposed using VGG16 with the descriptions encoded over an LSTM model. YOLOv5 is also used to recognize dominant colors of objects in the images and correct the color words in the descriptions generated if it is necessary. If the description contains words referring to a person, we recognize the emotion of the person in the image. Finally, we combine the results of all models to create sentences that describe the visual content and the human emotions in the images. Experimental results on the Flickr8k dataset in Vietnamese achieve BLEU-1, BLEU-2, BLEU-3, BLEU-4 scores of 0.628; 0.425; 0.280; and 0.174, respectively.

 
Các bài báo khác
1781 (2023) Trang: 124-137
Tạp chí: Communications in Computer and Information Science, InInternational Advanced Computing Conference 2022
(2023) Trang: 92-99
Tạp chí: Association for Computational Linguistics (ACL 2023), In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, 2023
(2023) Trang: 488-493
Tạp chí: RIVF International Conference on Computing and Communication Technologies, Vietnam, 20-22/12, 2022
(2023) Trang: 1-5
Tạp chí: 2022 6th International Conference on Natural Language Processing and Information Retrieval, Thailand
Nguyen Thai-Nghe, Thanh-Nghi Do, Peter Haddawy (2023) Trang: 200-207
Tạp chí: Communications in Computer and Information Science, ISDS 2023
Thi Dieu Linh Nguyen, Elena Verdú, Anh Ngoc Le, Maria Ganzha (2023) Trang: 34-39
Tạp chí: Lecture Notes in Networks and Systems
124 (2022) Trang: 85-96
Tạp chí: Lecture Notes on Data Engineering and Communications Technologies
Tran Khanh Dang, Josef Küng, Tai M. Chung (2022) Trang: 714-722
Tạp chí: Communications in Computer and Information Science
Tran Khanh Dang, Josef Küng, Tai M. Chung (2022) Trang: 377-392
Tạp chí: Communications in Computer and Information Science
26 (2022) Trang: 1313–1322
Tạp chí: Computacion y Sistemas
(2020) Trang: 144–148
Tạp chí: The 4th International Conference on Natural Language Processing and Information Retrieval, Online, 18-20/12/2020
(2021) Trang: 427-435
Tạp chí: International Conference on Future Data and Security Engineering, online 24-26/11/2021
(2019) Trang: 468-475
Tạp chí: Hội nghị khoa học Quốc gia Nghiên cứu cơ bản về ứng dụng công nghệ thông tin (FAIR), Đại học Huế, 7-8/6/2019
Tran Khanh DangJosef KüngMakoto TakizawaTai M. Chung (2020) Trang: 443-451
Tạp chí: Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications
(2019) Trang: 110-114
Tạp chí: International Conference on Natural Language Processing and Information Retrieval, Tokushima, Japan, June 28-30, 2019
(2016) Trang: 861-870
Tác giả: Lâm Nhựt Khang
Tạp chí: FAIR, Can Tho 4-5/8/2016
(2014) Trang: 3077-3078
Tác giả: Lâm Nhựt Khang
Tạp chí: AAAI, Québec City, Québec, Canada, July 27–31, 2014
(2015) Trang: 2174-2180
Tạp chí: AAAI, Austin, Texas, USA, January 25–30, 2015,
(2014) Trang: 106-111
Tạp chí: ACL, Baltimore, Maryland, USA, June 22-27, 2014
(2014) Trang: 54-62
Tạp chí: ACL- ComputEL, Baltimore, Maryland, USA, June 22-27, 2014
(2013) Trang: 524-528
Tạp chí: The Conference of the NAACL- HLT. Atlanta, Georgia, USA. 9-14 June 2013
(2017) Trang: 1007-1014
Tạp chí: FAIR, Da Nang17-18/8/2017
 


Vietnamese | English






 
 
Vui lòng chờ...