CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 视频内容安全
Browse Items

Browse/Search Results:  1-10 of 368 Help

Filters                
Selected(0)Clear Items/Page:    Sort:
Multi-Correlation Siamese Transformer Network With Dense Connection for 3D Single Object Tracking 期刊论文
IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 卷号: 8, 期号: 12, 页码: 8066-8073
Authors:  Feng, Shihao;  Liang, Pengpeng;  Gao, Jin;  Cheng, Erkang
Favorite  |  View/Download:83/0  |  Submit date:2023/12/21
3D object tracking  Point cloud  Transformer  
A Closer Look at Self-Supervised Lightweight Vision Transformers 会议论文
, Honolulu, Hawaii, USA, 2023-7
Authors:  Wang, Shaoru;  Gao, Jin;  Li, Zeming;  Zhang, Xiaoqin;  Weiming, Hu
Adobe PDF(3478Kb)  |  Favorite  |  View/Download:204/64  |  Submit date:2023/09/20
Vision Transformer  Self-supervised Learning  Lightweight Networks  Knowledge Distillation  
RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation 会议论文
, New York, 2020-2
Authors:  Wang, Shaoru;  Gong, Yongchao;  Xing, Junliang;  Huang, Lichao;  Huang, Chang;  Hu, Weiming
Adobe PDF(1860Kb)  |  Favorite  |  View/Download:84/21  |  Submit date:2023/09/20
目标检测  实例分割  
Cascaded Decoding and Multi-Stage Inference for Spatio-Temporal Video Grounding 会议论文
, Lisbon, Portugal, 2022-10
Authors:  Li Yang;  Peixuan Wu;  Chunfeng Yuan;  Bing Li;  Weiming Hu
Adobe PDF(1313Kb)  |  Favorite  |  View/Download:149/39  |  Submit date:2023/07/06
Improving Visual Grounding With Visual-Linguistic Verification and Iterative Reasoning 会议论文
, New Orleans, Louisiana, 2022-6
Authors:  Li Yang;  Yan Xu;  Chunfeng Yuan;  Wei Liu;  Bing Li;  Weiming Hu
Adobe PDF(2060Kb)  |  Favorite  |  View/Download:158/46  |  Submit date:2023/06/26
Learning from the raw domain: cross modality distillation for compressed video action recognition 会议论文
, Rhodes, Greece, 2023.6
Authors:  Yufan Liu;  Jiajiong Cao;  Weiming Bai;  Bing Li;  Weiming Hu
Adobe PDF(411Kb)  |  Favorite  |  View/Download:280/94  |  Submit date:2023/05/06
Learning to predict salient faces: a novel visual-audio saliency model 会议论文
, Virtual conference, 2020.8.23-2020.8.28
Authors:  Yufan Liu;  Minglang Qiao;  Mai Xu;  Bing Li;  Weiming Hu;  Ali Borji
Adobe PDF(4223Kb)  |  Favorite  |  View/Download:94/14  |  Submit date:2023/05/06
TranSkeleton: Hierarchical Spatial-Temporal Transformer for Skeleton-Based Action Recognition 期刊论文
IEEE Transactions on Circuits and Systems for Video Technology, 2023, 页码: 1-12
Authors:  Haowei Liu;  Yongcheng Liu;  Yuxin Chen;  Chunfeng Yuan;  Bing Li;  Weiming Hu
Adobe PDF(1276Kb)  |  Favorite  |  View/Download:209/75  |  Submit date:2023/04/28
Learning Video-Text Aligned Representations for Video Captioning 期刊论文
ACM Trans. Multimedia Comput. Commun. Appl., 2023, 页码: 1-21
Authors:  Yaya Shi;  Haiyang Xu;  Chunfeng Yuan;  Bing Li;  Weiming Hu,;  Zhengjun Zha
Adobe PDF(3574Kb)  |  Favorite  |  View/Download:191/70  |  Submit date:2023/04/28
Learning to Explore Distillability and Sparsability: A Joint Framework for Model Compression 期刊论文
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2022, 卷号: 45, 期号: 3, 页码: 3378-3395
Authors:  Yufan Liu;  Jiajiong Cao;  Bing Li;  Weiming Hu;  Stephen Maybank
Adobe PDF(3314Kb)  |  Favorite  |  View/Download:139/38  |  Submit date:2023/04/24