Zobrazeno 1 - 10
of 382
pro vyhledávání: '"Lin, Yen‐Yu"'
Recent advances in vision-language models (VLMs) have made significant progress in downstream tasks that require quantitative concepts such as facial age estimation and image quality assessment, enabling VLMs to explore applications like image rankin
Externí odkaz:
http://arxiv.org/abs/2412.06760
Adverse weather image restoration aims to remove unwanted degraded artifacts, such as haze, rain, and snow, caused by adverse weather conditions. Existing methods achieve remarkable results for addressing single-weather conditions. However, they face
Externí odkaz:
http://arxiv.org/abs/2410.08177
Learning a discriminative model to distinguish a target from its surrounding distractors is essential to generic visual object tracking. Dynamic target representation adaptation against distractors is challenging due to the limited discriminative cap
Externí odkaz:
http://arxiv.org/abs/2409.18901
One common belief is that with complex models and pre-training on large-scale datasets, transformer-based methods for referring expression comprehension (REC) perform much better than existing graph-based methods. We observe that since most graph-bas
Externí odkaz:
http://arxiv.org/abs/2409.03385
Autor:
He, Jin-Ting, Tsai, Fu-Jen, Wu, Jia-Hao, Peng, Yan-Tsung, Tsai, Chung-Chi, Lin, Chia-Wen, Lin, Yen-Yu
Dynamic scene video deblurring aims to remove undesirable blurry artifacts captured during the exposure process. Although previous video deblurring methods have achieved impressive results, they suffer from significant performance drops due to the do
Externí odkaz:
http://arxiv.org/abs/2407.09059
Autor:
Wu, Ji-Jia, Chang, Andy Chia-Hao, Chuang, Chieh-Yu, Chen, Chun-Pei, Liu, Yu-Lun, Chen, Min-Hung, Hu, Hou-Ning, Chuang, Yung-Yu, Lin, Yen-Yu
This paper addresses text-supervised semantic segmentation, aiming to learn a model capable of segmenting arbitrary visual concepts within images by using only image-text pairs without dense annotations. Existing methods have demonstrated that contra
Externí odkaz:
http://arxiv.org/abs/2404.04231
Autor:
Tsai, Fu-Jen, Peng, Yan-Tsung, Chang, Chen-Yu, Li, Chan-Yu, Lin, Yen-Yu, Tsai, Chung-Chi, Lin, Chia-Wen
Video restoration is a low-level vision task that seeks to restore clean, sharp videos from quality-degraded frames. One would use the temporal information from adjacent frames to make video restoration successful. Recently, the success of the Transf
Externí odkaz:
http://arxiv.org/abs/2312.14502
Image deblurring aims to remove undesired blurs from an image captured in a dynamic scene. Much research has been dedicated to improving deblurring performance through model architectural designs. However, there is little work on data augmentation fo
Externí odkaz:
http://arxiv.org/abs/2312.10998
This paper proposes a cross-modal distillation framework, PartDistill, which transfers 2D knowledge from vision-language models (VLMs) to facilitate 3D shape part segmentation. PartDistill addresses three major challenges in this task: the lack of 3D
Externí odkaz:
http://arxiv.org/abs/2312.04016
Semi-supervised object detection is crucial for 3D scene understanding, efficiently addressing the limitation of acquiring large-scale 3D bounding box annotations. Existing methods typically employ a teacher-student framework with pseudo-labeling to
Externí odkaz:
http://arxiv.org/abs/2312.02966