Zobrazeno 1 - 10
of 388
pro vyhledávání: '"Tang, ZhenMin"'
Optical flow is an easily conceived and precious cue for advancing unsupervised video object segmentation (UVOS). Most of the previous methods directly extract and fuse the motion and appearance features for segmenting target objects in the UVOS sett
Externí odkaz:
http://arxiv.org/abs/2207.08485
Person Re-Identification (ReID) matches pedestrians across disjoint cameras. Existing ReID methods adopting real-value feature descriptors have achieved high accuracy, but they are low in efficiency due to the slow Euclidean distance computation as w
Externí odkaz:
http://arxiv.org/abs/2207.05933
Publikováno v:
In Image and Vision Computing November 2024 151
Publikováno v:
In Information Fusion June 2024 106
Autor:
Yao, Yazhou, Chen, Tao, Xie, Guosen, Zhang, Chuanyi, Shen, Fumin, Wu, Qi, Tang, Zhenmin, Zhang, Jian
Semantic segmentation aims to classify every pixel of an input image. Considering the difficulty of acquiring dense labels, researchers have recently been resorting to weak labels to alleviate the annotation burden of segmentation. However, existing
Externí odkaz:
http://arxiv.org/abs/2103.14581
Due to the memorization effect in Deep Neural Networks (DNNs), training with noisy labels usually results in inferior model performance. Existing state-of-the-art methods primarily adopt a sample selection strategy, which selects small-loss samples f
Externí odkaz:
http://arxiv.org/abs/2103.13029
Publikováno v:
IEEE Transactions on Multimedia, 2021
One-shot semantic image segmentation aims to segment the object regions for the novel class with only one annotated image. Recent works adopt the episodic training strategy to mimic the expected situation at testing time. However, these existing appr
Externí odkaz:
http://arxiv.org/abs/2102.10935
Autor:
Liu, Huafeng, Zhang, Chuanyi, Yao, Yazhou, Wei, Xiushen, Shen, Fumin, Zhang, Jian, Tang, Zhenmin
Publikováno v:
IEEE Transactions on Multimedia, 2021
Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention. However, t
Externí odkaz:
http://arxiv.org/abs/2101.09412
Constructing fine-grained image datasets typically requires domain-specific expert knowledge, which is not always available for crowd-sourcing platform annotators. Accordingly, learning directly from web images becomes an alternative method for fine-
Externí odkaz:
http://arxiv.org/abs/2008.02438
Publikováno v:
In Signal Processing August 2023 209