Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Xiansheng, Hua"'
In this paper, we seek reasons for the two major failure cases in Semantic Segmentation (SS): 1) missing small objects or minor object parts, and 2) mislabeling minor parts of large objects as wrong classes. We have an interesting finding that Failur
Externí odkaz:
http://arxiv.org/abs/2108.09702
Publikováno v:
IEEE Transactions on Multimedia. 24:1247-1252
This special issue provides a premier forum for researchers in multimedia big data to share challenges and recent advancements in learning from noisy multimedia data. The multimedia age and its proliferation of devices and platforms is fueling expone
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87fe4982a2c6813bf9092158d8696612
https://doi.org/10.1109/tmm.2022.3159014
https://doi.org/10.1109/tmm.2022.3159014
Autor:
Pengfei Wang, Daqing Wu, Chong Chen, Kunpeng Liu, Yanjie Fu, Jianqiang Huang, Yuanchun Zhou, Jianfeng Zhan, Xiansheng Hua
Publikováno v:
ACM Transactions on the Web.
Graph clustering has been a hot research topic and is widely used in many fields, such as community detection in social networks. Lots of works combining auto-encoder and graph neural networks have been applied to clustering tasks by utilizing node a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::daee869b223f4a9f03c73e40327aa028
https://doi.org/10.1145/3580521
https://doi.org/10.1145/3580521
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::57939044539330286cca93ec543fcd2c
https://doi.org/10.1109/cvpr52688.2022.00065
https://doi.org/10.1109/cvpr52688.2022.00065
Publikováno v:
IEEE Transactions on Image Processing. 30:5933-5943
Video moment localization, as an important branch of video content analysis, has attracted extensive attention in recent years. However, it is still in its infancy due to the following challenges: cross-modal semantic alignment and localization effic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6403e59e833a7bdb6dafee40514f0845
https://doi.org/10.1109/tip.2021.3090521
https://doi.org/10.1109/tip.2021.3090521
Autor:
Wen Gao, Zhanning Gao, Pan Wang, Lingbo Yang, Xiansheng Hua, Peiran Ren, Siwei Ma, Xinfeng Zhang, Shanshe Wang, Chang Liu
Publikováno v:
IEEE Transactions on Image Processing. 30:2422-2435
Human pose transfer (HPT) is an emerging research topic with huge potential in fashion design, media production, online advertising and virtual reality. For these applications, the visual realism of fine-grained appearance details is crucial for prod
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::84bdc74d114fd4d12177209fe53bdedc
https://doi.org/10.1109/tip.2021.3052364
https://doi.org/10.1109/tip.2021.3052364
Publikováno v:
IEEE Transactions on Image Processing. 28:3162-3176
Being able to cover a wide range of views, pan-tilt-zoom (PTZ) cameras have been widely deployed in visual surveillance systems. To achieve a global-view perception of a surveillance scene, it is necessary to generate its panoramic background image,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6a7ff28529f9e3b2fd6881743feda14e
https://doi.org/10.1109/tip.2019.2894940
https://doi.org/10.1109/tip.2019.2894940
Publikováno v:
Computer Vision – ACCV 2020 ISBN: 9783030695378
ACCV (4)
ACCV (4)
Multi-level feature aggregation and part feature extraction are widely used to boost the performance of person re-identification (Re-ID). Most multi-level feature aggregation methods treat feature maps on different levels equally and use simple local
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c04d3737889326d097caaf96b3df3ee7
https://doi.org/10.1007/978-3-030-69538-5_9
https://doi.org/10.1007/978-3-030-69538-5_9
Publikováno v:
MobiCom: International Conference on Mobile Computing & Networking; 2021, p188-200, 13p
Publikováno v:
ICIP
Person re-identification (Person ReID) is a challenging task due to the large variations in camera viewpoint, lighting, resolution, and human pose. Recently, with the advancement of deep learning technologies, the performance of Person ReID has been
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::18357bdd66c30b437b9b8ef0ad066b34
http://arxiv.org/abs/1804.08866
http://arxiv.org/abs/1804.08866