English | 繁體

Search in the results

UM

Browse/Search Results:  1-10 of 23 Help

Selected(0)Clear Items/Page:    Sort:
Revisiting Few-Shot Object Detection with Vision-Language Models Conference paper
Madan, Anish, Peri, Neehar, KONG, SHU, Ramanan, Deva. Revisiting Few-Shot Object Detection with Vision-Language Models[C], 2024.
Authors:  Madan, Anish;  Peri, Neehar;  KONG, SHU;  Ramanan, Deva
Adobe PDF | Favorite |  | Submit date：2024/11/17
CriSp: Leveraging Tread Depth Maps for Enhanced Crime-Scene Shoeprint Matching Conference paper
Shafique, Samia, Kong, Shu, Fowlkes, Charless. CriSp: Leveraging Tread Depth Maps for Enhanced Crime-Scene Shoeprint Matching[C], 2024.
Authors:  Shafique, Samia;  Kong, Shu;  Fowlkes, Charless
Adobe PDF | Favorite |  | Submit date：2024/11/17
Improving Knowledge Distillation via Regularizing Feature Direction and Norm Journal article
Wang, Yuzhu, Cheng, Lechao, Duan, Manni, Wang, Yongheng, Feng, Zunlei, KONG, SHU. Improving Knowledge Distillation via Regularizing Feature Direction and Norm[J]. Springer Nature, 2024.
Authors:  Wang, Yuzhu;  Cheng, Lechao;  Duan, Manni;  Wang, Yongheng;  Feng, Zunlei; et al.
Adobe PDF | Favorite |  | Submit date：2024/11/17
Lidar Panoptic Segmentation in an Open World Journal article
Chakravarthy, Anirudh S., Ganesina, Meghana Reddy, Hu, Peiyun, Leal-Taixé, Laura, Kong, Shu, Ramanan, Deva, Osep, Aljosa. Lidar Panoptic Segmentation in an Open World[J]. International Journal of Computer Vision, 2024.
Authors:  Chakravarthy, Anirudh S.;  Ganesina, Meghana Reddy;  Hu, Peiyun;  Leal-Taixé, Laura;  Kong, Shu; et al.
Adobe PDF | Favorite | TC[WOS]:0 TC[Scopus]:0  IF:11.6/14.5 | Submit date：2024/10/10
Lidar Panoptic Segmentation  Open World Segmentation  Lidar Scene Understanding  
Boosting Image Restoration via Priors from Pre-Trained Models Conference paper
Xu, Xiaogang, Kong, Shu, Hu, Tao, Liu, Zhe, Bao, Hujun. Boosting Image Restoration via Priors from Pre-Trained Models[C]:IEEE Computer Society, 2024, 2900-2909.
Authors:  Xu, Xiaogang;  Kong, Shu;  Hu, Tao;  Liu, Zhe;  Bao, Hujun
Favorite | TC[Scopus]:2 | Submit date：2024/11/05
Computer Vision  Shape  Computational Modeling  Noise Reduction  Training Data  Boosting  Data Models  Pre-trained Models  Image Restoration  Spatial-varying Enhancement  Channel-spatial Attention  
Instance Tracking in 3D Scenes from Egocentric Videos Conference paper
Zhao, Yunhan, Haoyu Ma, Shu Kong, Charless Fowlkes. Instance Tracking in 3D Scenes from Egocentric Videos[C]:IEEE Computer Society, 2024, 21933-21944.
Authors:  Zhao, Yunhan;  Haoyu Ma;  Shu Kong;  Charless Fowlkes
Adobe PDF | Favorite | TC[Scopus]:0 | Submit date：2024/06/20
Three-dimensional Displays  Protocols  Annotations  Benchmark Testing  Cameras  Sensors  Pattern Recognition  Egocentric Videos  Instance TrackIng In 3d  
Towards Unstructured Unlabeled Optical Mocap: A Video Helps! Conference paper
Milef, Nicholas, Keyser, John, KONG SHU. Towards Unstructured Unlabeled Optical Mocap: A Video Helps![C]:Association for Computing Machinery, Inc, 2024, 201050.
Authors:  Milef, Nicholas;  Keyser, John;  KONG SHU
Adobe PDF | Favorite | TC[WOS]:0 TC[Scopus]:0 | Submit date：2024/06/20
Human Body Reconstruction  Motion Capture  Partial-body Reconstruction  
Alpha-CLIP: A CLIP Model Focusing on Wherever You Want Conference paper
Sun, Zeyi, Fang, Ye, Wu, Tong, Zhang, Pan, Zang, Yuhang, KONG SHU, Xiong, Yuanjun, Lin, Dahua, Wang, Jiaqi. Alpha-CLIP: A CLIP Model Focusing on Wherever You Want[C], 2024.
Authors:  Sun, Zeyi;  Fang, Ye;  Wu, Tong;  Zhang, Pan;  Zang, Yuhang; et al.
Adobe PDF | Favorite |  | Submit date：2024/06/20
The Neglected Tails of Vision-Language Models Conference paper
Parashar, Shubham, Lin, Zhiqiu, Liu, Tian, Dong, Xiangjue, Li, Yanan, Ramanan, Deva, Caverlee, James, KONG, SHU. The Neglected Tails of Vision-Language Models[C], 2024.
Authors:  Parashar, Shubham;  Lin, Zhiqiu;  Liu, Tian;  Dong, Xiangjue;  Li, Yanan; et al.
Adobe PDF | Favorite |  | Submit date：2024/06/20
Boosting Image Restoration via Priors from Pre-trained Models Conference paper
Xu, Xiaogang, KONG SHU, Hu, Tao, Liu, Zhe, Bao, Hujun. Boosting Image Restoration via Priors from Pre-trained Models[C], 2024.
Authors:  Xu, Xiaogang;  KONG SHU;  Hu, Tao;  Liu, Zhe;  Bao, Hujun
Adobe PDF | Favorite |  | Submit date：2024/06/20