Zobrazeno 1 - 10
of 1 994
pro vyhledávání: '"An, Sanping"'
Semi-supervised learning has emerged as a widely adopted technique in the field of medical image segmentation. The existing works either focuses on the construction of consistency constraints or the generation of pseudo labels to provide high-quality
Externí odkaz:
http://arxiv.org/abs/2409.05122
Autor:
Liu, Yuhan, Huang, Qianxin, Hui, Siqi, Fu, Jingwen, Zhou, Sanping, Wu, Kangyi, Li, Pengna, Wang, Jinjun
Homography estimation is the task of determining the transformation from an image pair. Our approach focuses on employing detector-free feature matching methods to address this issue. Previous work has underscored the importance of incorporating sema
Externí odkaz:
http://arxiv.org/abs/2407.13284
Multi-Object Tracking MOT encompasses various tracking scenarios, each characterized by unique traits. Effective trackers should demonstrate a high degree of generalizability across diverse scenarios. However, existing trackers struggle to accommodat
Externí odkaz:
http://arxiv.org/abs/2406.00429
Temporal sentence grounding is a challenging task that aims to localize the moment spans relevant to a language description. Although recent DETR-based models have achieved notable progress by leveraging multiple learnable moment queries, they suffer
Externí odkaz:
http://arxiv.org/abs/2406.00143
With the wide application of knowledge distillation between an ImageNet pre-trained teacher model and a learnable student model, industrial anomaly detection has witnessed a significant achievement in the past few years. The success of knowledge dist
Externí odkaz:
http://arxiv.org/abs/2405.02068
Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to making ambiguo
Externí odkaz:
http://arxiv.org/abs/2404.16416
Noisy label learning aims to learn robust networks under the supervision of noisy labels, which plays a critical role in deep learning. Existing work either conducts sample selection or label correction to deal with noisy labels during the model trai
Externí odkaz:
http://arxiv.org/abs/2404.10499
Unsupervised person re-identification aims to retrieve images of a specified person without identity labels. Many recent unsupervised Re-ID approaches adopt clustering-based methods to measure cross-camera feature similarity to roughly divide images
Externí odkaz:
http://arxiv.org/abs/2403.16450
The crux of semi-supervised temporal action localization (SS-TAL) lies in excavating valuable information from abundant unlabeled videos. However, current approaches predominantly focus on building models that are robust to the error-prone target cla
Externí odkaz:
http://arxiv.org/abs/2403.11189
Pedestrian trajectory prediction is a crucial component in computer vision and robotics, but remains challenging due to the domain shift problem. Previous studies have tried to tackle this problem by leveraging a portion of the trajectory data from t
Externí odkaz:
http://arxiv.org/abs/2403.05810