中国科学院计算技术研究所机构知识库

浏览/检索结果: 共4条，第1-4条

帮助

已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序WOS被引频次升序WOS被引频次降序提交时间升序提交时间降序期刊影响因子升序期刊影响因子降序题名升序题名降序发表日期升序发表日期降序
	A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking 期刊论文 INTERNATIONAL JOURNAL OF COMPUTER VISION, 2024, 页码: 23 作者:  Liu, Chang;  Dong, Yinpeng;  Xiang, Wenzhao;  Yang, Xiao;  Su, Hang;  Zhu, Jun;  Chen, Yuefeng;  He, Yuan;  Xue, Hui;  Zheng, Shibao 收藏  |  浏览/下载：1/0  |  提交时间：2024/12/06 Robustness benchmark  Distribution shift  Pre-training  Adversarial training  Image classification
	A2Pt : Anti-Associative Prompt Tuning for Open Set Visual Recognition 期刊论文 IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 卷号: 26, 页码: 8419-8431 作者:  Ren, Hairui;  Tang, Fan;  Pan, Xingjia;  Cao, Juan;  Dong, Weiming;  Lin, Zhiwen;  Yan, Ke;  Xu, Changsheng 收藏  |  浏览/下载：2/0  |  提交时间：2024/12/06 Tuning  Neck  Task analysis  Image recognition  Calibration  Visualization  Training  Multi-modality Pre-trained models (PTMs)  open set recognition (OSR)  class-aware representation  anti-associative prompt tuning (A(2)Pt)
	MemBridge: Video-Language Pre-Training With Memory-Augmented Inter-Modality Bridge 期刊论文 IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 4073-4087 作者:  Yang, Jiahao;  Li, Xiangyang;  Zheng, Mao;  Wang, Zihan;  Zhu, Yongqing;  Guo, Xiaoqian;  Yuan, Yuchen;  Chai, Zifeng;  Jiang, Shuqiang 收藏  |  浏览/下载：22/0  |  提交时间：2023/12/04 Video-language pre-training  inter-modality bridge  memory module
	Focus and Align: Learning Tube Tokens for Video-Language Pre-Training 期刊论文 IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 卷号: 25, 页码: 8036-8050 作者:  Zhu, Yongqing;  Li, Xiangyang;  Zheng, Mao;  Yang, Jiahao;  Wang, Zihan;  Guo, Xiaoqian;  Chai, Zifeng;  Yuan, Yuchen;  Jiang, Shuqiang 收藏  |  浏览/下载：11/0  |  提交时间：2024/05/20 Electron tubes  Semantics  Visualization  Feature extraction  Task analysis  Transformers  Detectors  Local alignment mechanism  semantic centers  tube tokens  video-language pre-training