Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Yunbin Tu"'
Publikováno v:
IEEE Transactions on Image Processing. 32:2620-2635
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::24f73b188bd89d89a022759d974d8f01
https://doi.org/10.1109/tip.2023.3268004
https://doi.org/10.1109/tip.2023.3268004
Publikováno v:
IEEE Transactions on Multimedia. :1-14
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4010fc54a08262d98b3a1a8b51b335ff
https://doi.org/10.1109/tmm.2023.3242142
https://doi.org/10.1109/tmm.2023.3242142
Autor:
Yunbin Tu, Liang Li, Li Su, Shengxiang Gao, Chenggang Yan, Zheng-Jun Zha, Zhengtao Yu, Qingming Huang
Publikováno v:
IEEE Transactions on Image Processing. 31:3565-3577
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0edea4e5d519af45a45502bc178ff16b
https://doi.org/10.1109/tip.2022.3159472
https://doi.org/10.1109/tip.2022.3159472
Change captioning is to describe the semantic change between a pair of similar images in natural language. It is more challenging than general image captioning, because it requires capturing fine-grained change information while being immune to irrel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::934df59c5b4ce42007cb9db6f92866bf
http://arxiv.org/abs/2303.03171
http://arxiv.org/abs/2303.03171
Autor:
Gaoxiang Cong, Liang Li, Zhenhuan Liu, Yunbin Tu, Weijun Qin, Shenyuan Zhang, Chengang Yan, Wenyu Wang, Bin Jiang
Publikováno v:
Proceedings of the 30th ACM International Conference on Multimedia.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c49602bd70b6b50c1e4815c236896cca
https://doi.org/10.1145/3503161.3548206
https://doi.org/10.1145/3503161.3548206
Publikováno v:
Pattern Recognition. 136:109204
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e64fd24e2de31f33d63b81071c9e59ed
https://doi.org/10.1016/j.patcog.2022.109204
https://doi.org/10.1016/j.patcog.2022.109204
Autor:
Yongdong Zhang, Yunbin Tu, Wang Xingzheng, Yongbing Zhang, Xinhong Hao, Chenggang Yan, Qionghai Dai
Publikováno v:
IEEE Transactions on Multimedia. 22:229-241
Video captioning refers to automatic generate natural language sentences, which summarize the video contents. Inspired by the visual attention mechanism of human beings, temporal attention mechanism has been widely used in video description to select
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::79418b12b53f94c25e616b57ab4c99bb
https://doi.org/10.1109/tmm.2019.2924576
https://doi.org/10.1109/tmm.2019.2924576
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 31
Video captioning aims to generate a natural language sentence to describe the main content of a video. Since there are multiple objects in videos, taking full exploration of the spatial and temporal relationships among them is crucial for this task.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1b025288318395d57a0b3ebda4e1ef94
https://pubmed.ncbi.nlm.nih.gov/35324439
https://pubmed.ncbi.nlm.nih.gov/35324439
Autor:
Yunbin, Tu, Liang, Li, Li, Su, Shengxiang, Gao, Chenggang, Yan, Zheng-Jun, Zha, Zhengtao, Yu, Qingming, Huang
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 31
TV show captioning aims to generate a linguistic sentence based on the video and its associated subtitle. Compared to purely video-based captioning, the subtitle can provide the captioning model with useful semantic clues such as actors' sentiments a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::d62c303e9f356ef34e065461144e8f7a
https://pubmed.ncbi.nlm.nih.gov/35312620
https://pubmed.ncbi.nlm.nih.gov/35312620
Change captioning is to use a natural language sentence to describe the fine-grained disagreement between two similar images. Viewpoint change is the most typical distractor in this task, because it changes the scale and location of the objects and o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2ddfd161a37da03b33d1fae2bbc07d66