Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Kekai Sheng"'
Autor:
Yifan Xu, Huapeng Wei, Minxuan Lin, Yingying Deng, Kekai Sheng, Mengdan Zhang, Fan Tang, Weiming Dong, Feiyue Huang, Changsheng Xu
Publikováno v:
Computational Visual Media, Vol 8, Iss 1, Pp 33-62 (2021)
Abstract Transformers, the dominant architecture for natural language processing, have also recently attracted much attention from computational visual media researchers due to their capacity for long-range representation and high performance. Transf
Externí odkaz:
https://doaj.org/article/d01a2c8e47a144a68732982eec7751f7
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 18:1-16
Big progress has been achieved in domain adaptation in decades. Existing works are always based on an ideal assumption that testing target domain are i.i.d. with training target domains. However, due to unpredictable corruptions (e.g., noise and blur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3c30051596e1cc4f1234ff68049853d
https://doi.org/10.1145/3501800
https://doi.org/10.1145/3501800
Autor:
Yingying Deng, Fan Tang, Changsheng Xu, Huapeng Wei, Mengdan Zhang, Kekai Sheng, Yifan Xu, Minxuan Lin, Feiyue Huang, Weiming Dong
Publikováno v:
Computational Visual Media, Vol 8, Iss 1, Pp 33-62 (2021)
Transformers, the dominant architecture for natural language processing, have also recently attracted much attention from computational visual media researchers due to their capacity for long-range representation and high performance. Transformers ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7a6223265de3dd953f060f2d317684d8
https://doi.org/10.1007/s41095-021-0247-3
https://doi.org/10.1007/s41095-021-0247-3
Publikováno v:
Computational Visual Media. 7:139-152
Distinguishing aesthetically pleasing food photos from others is an important visual analysis task for social media and ranking systems related to food. Nevertheless, aesthetic assessment of food images remains a challenging and relatively unexplored
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb8fd05a9c5e45b7e224b01f0419a050
https://doi.org/10.1007/s41095-020-0193-5
https://doi.org/10.1007/s41095-020-0193-5
Publikováno v:
IEEE Transactions on Image Processing. 29:7904-7916
Direct regression and anchor are the two mainly effective and prevailing mechanisms in the paradigm of scene text detection. However, the use of direct regression-based methods may be challenging during optimization without the help of anchors as ref
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ffa9e127374885976dfb0fbb2ee32ad7
https://doi.org/10.1109/tip.2020.3008863
https://doi.org/10.1109/tip.2020.3008863
Autor:
Peixian Chen, Mengdan Zhang, Yunhang Shen, Kekai Sheng, Yuting Gao, Xing Sun, Ke Li, Chunhua Shen
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200793
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b494f0c3685e6f4c3114ac80bee6abe8
https://doi.org/10.1007/978-3-031-20080-9_5
https://doi.org/10.1007/978-3-031-20080-9_5
Autor:
Bohong Chen, Mingbao Lin, Kekai Sheng, Mengdan Zhang, Peixian Chen, Ke Li, Liujuan Cao, Rongrong Ji
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031197994
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3ab9520a38c90226506eba39c2a9dd50
https://doi.org/10.1007/978-3-031-19800-7_15
https://doi.org/10.1007/978-3-031-19800-7_15
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200649
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fc046cd296173072740b796c650efca0
https://doi.org/10.1007/978-3-031-20065-6_20
https://doi.org/10.1007/978-3-031-20065-6_20
Recently, Vision Transformer (ViT) has achieved remarkable success in several computer vision tasks. The progresses are highly relevant to the architecture design, then it is worthwhile to propose Transformer Architecture Search (TAS) to search for b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4955f93ec3c4ce252aa35f7c0143f458
Autor:
Yifan Xu, Zhijie Zhang, Mengdan Zhang, Kekai Sheng, Ke Li, Weiming Dong, Liqing Zhang, Changsheng Xu, Xing Sun
Vision transformers (ViTs) have recently received explosive popularity, but the huge computational cost is still a severe issue. Since the computation complexity of ViT is quadratic with respect to the input sequence length, a mainstream paradigm for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f87a0269ac1efe2e8dc822cecd42ef14
http://arxiv.org/abs/2108.01390
http://arxiv.org/abs/2108.01390