Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Wayne Zhang"'
Autor:
Guangcan Liu, Wayne Zhang
Publikováno v:
IEEE Transactions on Information Theory. 69:650-665
This paper studies the problem of time series forecasting (TSF) from the perspective of compressed sensing. First of all, we convert TSF into a more inclusive problem called tensor completion with arbitrary sampling (TCAS), which is to restore a tens
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d06d71ff1ba763d17c54118ea425b681
https://doi.org/10.1109/tit.2022.3196707
https://doi.org/10.1109/tit.2022.3196707
Autor:
Jingkang Yang, Zheng Ma, Qixun Wang, Xiaofeng Guo, Haofan Wang, Ziwei Liu, Wayne Zhang, Xing Xu, Hai Zhang
Publikováno v:
National Science Review.
The Panoptic Scene Graph Generation (PSG) challenge evaluates computer vision models to identify relations in images beyond object classification and localization, enabling a deeper understanding of scenes for real-world AI applications.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::00e2f950b94144cc7b50b057a6344607
https://doi.org/10.1093/nsr/nwad126
https://doi.org/10.1093/nsr/nwad126
Publikováno v:
IEEE Transactions on Image Processing. 30:8306-8317
Human-object interaction detection that aims at detectinghuman, verb, objecttriplets is critical for the holistic human-centric scene understanding. Existing approaches ignore the modeling of correlations among hierarchical human parts and objects. I
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ad6d85f28c25b4b629d61686faef6c6d
https://doi.org/10.1109/tip.2021.3093784
https://doi.org/10.1109/tip.2021.3093784
Publikováno v:
IEEE Signal Processing Letters. 27:1265-1269
In many applications such as film recommendation, one often encounters the problem of estimating the unseen entries in a partially observed matrix, formally known as matrix completion. Over the past several decades, lots of effective methods have bee
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9d19a716456bae3fe0f54e51875b61be
https://doi.org/10.1109/lsp.2020.3008043
https://doi.org/10.1109/lsp.2020.3008043
Transformers with powerful global relation modeling abilities have been introduced to fundamental computer vision tasks recently. As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image classificat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::58e96c6bd2033cdc953e2a10a7bd3e33
https://ora.ox.ac.uk/objects/uuid:a222054a-8742-4194-96ec-254bc9d1a85a
https://ora.ox.ac.uk/objects/uuid:a222054a-8742-4194-96ec-254bc9d1a85a
Most of the existing Out-Of-Distribution (OOD) detection algorithms depend on single input source: the feature, the logit, or the softmax probability. However, the immense diversity of the OOD examples makes such methods fragile. There are OOD sample
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b2f72a7f2a4234a98667f874300003a7
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198113
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b390d9575caa81a481ecfd2bf5e813fe
https://doi.org/10.1007/978-3-031-19812-0_11
https://doi.org/10.1007/978-3-031-19812-0_11
Publikováno v:
Hong Kong University of Science and Technology
Weakly-Supervised Semantic Segmentation (WSSS) segments objects without a heavy burden of dense annotation. While as a price, generated pseudo-masks exist obvious noisy pixels, which result in sub-optimal segmentation models trained over these pseudo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dc4c30a1ba44e3593f544ad5b8382091
http://arxiv.org/abs/2112.07431
http://arxiv.org/abs/2112.07431
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Current out-of-distribution (OOD) detection benchmarks are commonly built by defining one dataset as in-distribution (ID) and all others as OOD. However, these benchmarks unfortunately introduce some unwanted and impractical goals, e.g., to perfectly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ded5894a56b9134d58ed8a878fcc3088
https://doi.org/10.1109/iccv48922.2021.00819
https://doi.org/10.1109/iccv48922.2021.00819
Publikováno v:
CVPR
One of the main challenges for arbitrary-shaped text detection is to design a good text instance representation that allows networks to learn diverse text geometry variances. Most of existing methods model text instances in image spatial domain via m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::951c53b1ece2e7a326aa34906161d501
http://arxiv.org/abs/2104.10442
http://arxiv.org/abs/2104.10442