Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Kaihua Tang"'
Autor:
Kaihua Tang, Xiaoting Li, Jianwen Mo, Yixuan Chen, Chengyu Huang, Ting Li, Tianjian Luo, Zhijian Zhong, Yongqiang Jiang, Dengfeng Yang, Weiliang Mo
Publikováno v:
Scientific Reports, Vol 13, Iss 1, Pp 1-12 (2023)
Abstract The prevalence and mortality of hepatocellular carcinoma (HCC) are still increasing. This study aimed to identify potential therapeutic targets related to patient prognosis. Data were downloaded from TCGA, GSE25097, GSE36376, and GSE76427 da
Externí odkaz:
https://doaj.org/article/3b2561559d9f4261be846f9d1d566fca
Publikováno v:
IEEE Transactions on Multimedia. 24:1266-1276
Scene graphs connect individual objects with visual relationships. They serve as a comprehensive scene representation for downstream multimodal tasks. However, by exploring recent progress in Scene Graph Generation (SGG), we find that the performance
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0025333253795bcb7d3c958dea859551
https://doi.org/10.1109/tmm.2021.3062543
https://doi.org/10.1109/tmm.2021.3062543
Autor:
Xin Li, Chunyan Gong, Kaihua Tang, Yang Li, Kaiwen Zou, Yan Qian, Rui Tao, Li Huang, Lindong Liu
Publikováno v:
Translational Neuroscience
Translational Neuroscience, Vol 12, Iss 1, Pp 103-113 (2021)
Translational Neuroscience, Vol 12, Iss 1, Pp 103-113 (2021)
Background Spinal cord injury (SCI) is the most serious complication of spinal injury, often leading to severe dysfunction of the limbs below the injured segment. Conventional therapy approaches are becoming less and less effective, and gene therapy
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e195f7dca94373a1f493b83961dc4f6
http://europepmc.org/articles/PMC7925972
http://europepmc.org/articles/PMC7925972
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198052
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7c94b70ed182533d683112a18a513f23
https://doi.org/10.1007/978-3-031-19806-9_6
https://doi.org/10.1007/978-3-031-19806-9_6
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200526
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::80dfdded18bbe45c5f3d516cd9e24f8a
https://doi.org/10.1007/978-3-031-20053-3_41
https://doi.org/10.1007/978-3-031-20053-3_41
Publikováno v:
CVPR
We propose a causal framework to explain the catastrophic forgetting in Class-Incremental Learning (CIL) and then derive a novel distillation method that is orthogonal to the existing anti-forgetting techniques, such as data replay and feature/label
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::69b2ef623685965feb44c99b72148c98
https://doi.org/10.1109/cvpr46437.2021.00395
https://doi.org/10.1109/cvpr46437.2021.00395
Publikováno v:
CVPR
Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data. We propose a "divide&conquer" strategy for the challenging LVIS task: divide the whole data into balanced parts and then apply incremental l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::27606b5e84d8f6b763231f52932e7d76
Publikováno v:
CVPR
Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e.g., collapsing diverse "human walk on / sit on / lay on beach" into "human on beach". Given such SGG, the down-stream tasks such as VQA c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c307f3df4130516b69407183df573940
Publikováno v:
CVPR
We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual Q&A. Our visual context tree model, dubbed VCTree, has two key advantages
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::58bd72bab49d6b46e7b48778f7957894
https://doi.org/10.1109/cvpr.2019.00678
https://doi.org/10.1109/cvpr.2019.00678
Publikováno v:
CVPR
We propose Scene Graph Auto-Encoder (SGAE) that incorporates the language inductive bias into the encoder-decoder image captioning framework for more human-like captions. Intuitively, we humans use the inductive bias to compose collocations and conte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02e11c7860228b25a27f142ccc7e6a41
http://arxiv.org/abs/1812.02378
http://arxiv.org/abs/1812.02378