中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共20条，第1-10条 帮助

限定条件                    
已选(0)清除 条数/页：   排序方式：
DARTScore: DuAl-Reconstruction Transformer for Video Captioning Evaluation 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 卷号: 34, 期号: 4, 页码: 2041-2055
作者:  Chen, Yuxin;  Zhang, Ziqi;  Qi, Zhongang;  Yuan, Chunfeng;  Wang, Jie;  Shan, Ying;  Li, Bing;  Hu, Weiming;  Qie, Xiaohu;  Wu, Jianping
Adobe PDF(13765Kb)  |  收藏  |  浏览/下载：25/0  |  提交时间：2024/05/30
Chinese video captioning evaluation  dual-reconstruction transformer  
General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds With One Stone 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 6155-6167
作者:  Bao, Zenghao;  Tan, Zichang;  Li, Jun;  Wan, Jun;  Ma, Xibo;  Lei, Zhen
Adobe PDF(1634Kb)  |  收藏  |  浏览/下载：46/1  |  提交时间：2024/02/22
General age estimation  long-tailed age estimation  class-wise mean absolute error  
Zero-Shot Predicate Prediction for Scene Graph Parsing 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 卷号: 25, 页码: 3140-3153
作者:  Li, Yiming;  Yang, Xiaoshan;  Huang, Xuhui;  Ma, Zhe;  Xu, Changsheng
收藏  |  浏览/下载：155/0  |  提交时间：2023/11/17
Deep learning  zero-shot  scene graph  
Multi-Source Knowledge Reasoning Graph Network for Multi-Modal Commonsense Inference 期刊论文
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2023, 卷号: 19, 期号: 4, 页码: 17
作者:  Ma, Xuan;  Yang, Xiaoshan;  Xu, Changsheng
收藏  |  浏览/下载：96/0  |  提交时间：2023/11/17
Knowledge reasoning  multi-modal commonsense inference  graph neural network  
Dual Instance-Consistent Network for Cross-Domain Object Detection 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 6, 页码: 7338-7352
作者:  Jiao, Yifan;  Yao, Hantao;  Xu, Changsheng
收藏  |  浏览/下载：48/0  |  提交时间：2023/11/17
Feature extraction  Object detection  Detectors  Visualization  Proposals  Head  Task analysis  Cross-domain object detection  domain-specific description  dual instance-consistent network  
Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 9, 页码: 4616-4629
作者:  Ma, Chengcheng;  Liu, Yang;  Deng, Jiankang;  Xie, Lingxi;  Dong, Weiming;  Xu, Changsheng
Adobe PDF(1644Kb)  |  收藏  |  浏览/下载：143/18  |  提交时间：2023/11/16
Vision-language model  prompt tuning  over-fitting  subspace learning  gradient projection  
Model Predictive Trajectory Tracking Control of an Underactuated Bionic Underwater Vehicle 期刊论文
IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2023, 页码: 12
作者:  Wang, Kaihui;  Zou, Wei;  Ma, Ruichen;  Wang, Yu;  Su, Hu
Adobe PDF(4065Kb)  |  收藏  |  浏览/下载：117/11  |  提交时间：2023/11/16
Bionic underwater vehicle (BUV)  model predictive control (MPC)  trajectory tracking  undulatory propulsion  
Weakly-Supervised Video Object Grounding Via Learning Uni-Modal Associations 期刊论文
IEEE Transactions on Multimedia, 2022, 卷号: 25, 页码: 1-12
作者:  Wang, Wei;  Gao, Junyu;  Xu, Changsheng
Adobe PDF(5406Kb)  |  收藏  |  浏览/下载：127/38  |  提交时间：2023/04/25
Visualization  Grounding  Task analysis  Prototypes  Annotations  Uncertainty  Proposals  Cross-modal retrieval  weakly-supervised learning  video object grounding  uni-modal association  
Cross-Architecture Knowledge Distillation 会议论文
INTERNATIONAL JOURNAL OF COMPUTER VISION, Macau SAR, China, 2022.12.4-2022.12.8
作者:  Yufan Liu;  Jiajiong Cao;  Bing Li;  Weiming Hu;  Jingting Ding;  Liang Li
Adobe PDF(1020Kb)  |  收藏  |  浏览/下载：159/46  |  提交时间：2023/04/23
Knowledge distillation  Cross architecture  Model compression  Deep learning  
Holographic Feature Learning of Egocentric-Exocentric Videos for Multi-Domain Action Recognition 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 卷号: 24, 页码: 2273-2286
作者:  Huang, Yi;  Yang, Xiaoshan;  Gao, Junyun;  Xu, Changsheng
Adobe PDF(2409Kb)  |  收藏  |  浏览/下载：364/73  |  提交时间：2022/07/25
Videos  Feature extraction  Visualization  Task analysis  Computational modeling  Target recognition  Prototypes  Egocentric videos  exocentric videos  holographic feature  multi-domain  action recognition