Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Yuanjun Xiong"'
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031250682
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::84ebcc1bc8f19d0ceb88af10bf04d297
https://doi.org/10.1007/978-3-031-25069-9_36
https://doi.org/10.1007/978-3-031-25069-9_36
Publikováno v:
Physical Communication. 58:102046
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d1e9bb0f3b2b92744d54c7d536d20d53
https://doi.org/10.1016/j.phycom.2023.102046
https://doi.org/10.1016/j.phycom.2023.102046
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::07664bfdcafa9926b5d9bc9538fbe49f
https://doi.org/10.1109/iccvw54120.2021.00097
https://doi.org/10.1109/iccvw54120.2021.00097
Autor:
Yifan Xing, Tong He, Tianjun Xiao, Yongxin Wang, Yuanjun Xiong, Wei Xia, David Wipf, Zheng Zhang, Stefano Soatto
We propose a hierarchical graph neural network (GNN) model that learns how to cluster a set of images into an unknown number of identities using a training set of images annotated with labels belonging to a disjoint set of identities. Our hierarchica
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15f68936cbb12451b49fb4cfb3d28f10
http://arxiv.org/abs/2107.01319
http://arxiv.org/abs/2107.01319
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 41:2740-2755
Deep convolutional networks have achieved great success for image recognition. However, for action recognition in videos, their advantage over traditional methods is not so evident. We present a general and flexible video-level framework for learning
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::498d6d34711fe6f38b31bfe8aecb55f2
https://doi.org/10.1109/tpami.2018.2868668
https://doi.org/10.1109/tpami.2018.2868668
Publikováno v:
International Journal of Computer Vision. 128:74-95
This paper addresses an important and challenging task, namely detecting the temporal intervals of actions in untrimmed videos. Specifically, we present a framework called structured segment network (SSN). It is built on temporal proposals of actions
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::db792986ad4ce02fd883da1924868ba1
https://doi.org/10.1007/s11263-019-01211-2
https://doi.org/10.1007/s11263-019-01211-2
Autor:
Wei Xia, Stefano Soatto, Shuo Yang, Sijie Yan, Siqi Deng, Yuanjun Xiong, Meng Wang, Kaustav Kundu
Publikováno v:
CVPR
Reducing inconsistencies in the behavior of different versions of an AI system can be as important in practice as reducing its overall error. In image classification, sample-wise inconsistencies appear as "negative flips": A new model incorrectly pre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8e0bf2a30523a7425fdd2cbd2c3fa96a
https://doi.org/10.1109/cvpr46437.2021.01407
https://doi.org/10.1109/cvpr46437.2021.01407
Autor:
Liming Jiang, Baoying Chen, Peiyu Zhuang, Sili Li, Shen Chen, Taiping Yao, Shouhong Ding, Jilin Li, Feiyue Huang, Liujuan Cao, Rongrong Ji, Zhengkui Guo, Changlei Lu, Ganchao Tan, Wayne Wu, Zhaoyang Liu, Ziwei Liu, Chen Change Loy, Shuo Yang, Yuanjun Xiong, Wei Xia
Publikováno v:
Web of Science
This paper reports methods and results in the DeeperForensics Challenge 2020 on real-world face forgery detection. The challenge employs the DeeperForensics-1.0 dataset, one of the most extensive publicly available real-world face forgery detection d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3b907cf72611c92cfe72bbfa23cd7f64
http://arxiv.org/abs/2102.09471
http://arxiv.org/abs/2102.09471
Publikováno v:
CVPR
We tackle the problem of visual search under resource constraints. Existing systems use the same embedding model to compute representations (embeddings) for the query and gallery images. Such systems inherently face a hard accuracy-efficiency trade-o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4b6ca5009155a60a032f7302fc3aa1db
Publikováno v:
Advances in Computer Vision and Pattern Recognition ISBN: 9783030746964
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8eeb685105a30515e99791429e7d17a6
https://doi.org/10.1007/978-3-030-74697-1_15
https://doi.org/10.1007/978-3-030-74697-1_15