中文版 | English

在结果中检索

CASIA OpenIR
（本次检索基于用户作品认领结果）

浏览/检索结果: 共15条，第1-10条 帮助

限定条件        
已选(0)清除 条数/页：   排序方式：
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：94/12  |  提交时间：2023/11/16
Vision-language model  prompt tuning  over-fitting  subspace learning  gradient projection  
TENET: Beyond Pseudo-Labeling for Semi-supervised Few-shot Learning 期刊论文
Machine Intelligence Research, 2023, 页码: 0
作者:  Ma CC(马成丞);  Dong WM(董未名);  Xu CS(徐常胜)
Adobe PDF(741Kb)  |  收藏  |  浏览/下载：96/22  |  提交时间：2024/01/29
Semi-supervised few-shot learning  few-shot learning  pseudo-labeling  linear regression  low-rank reconstruction  
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：305/61  |  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  
Unsupervised Video Summarization via Relation-Aware Assignment Learning 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 3203-3214
作者:  Gao, Junyu;  Yang, Xiaoshan;  Zhang, Yingying;  Xu, Changsheng
Adobe PDF(3649Kb)  |  收藏  |  浏览/下载：292/60  |  提交时间：2021/11/03
Feature extraction  Training  Optimization  Semantics  Recurrent neural networks  Task analysis  Graph neural network  unsupervised learning  video summarization  
Knowledge-driven Egocentric Multimodal Activity Recognition 期刊论文
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2020, 卷号: 16, 期号: 4, 页码: 21
作者:  Huang, Yi;  Yang, Xiaoshan;  Gao, Junyu;  Sang, Jitao;  Xu, Changsheng
Adobe PDF(1875Kb)  |  收藏  |  浏览/下载：336/46  |  提交时间：2021/03/08
Egocentric videos  wearable sensors  graph neural networks  
Part-based Structured Representation Learning for Person Re-identification 期刊论文
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2020, 卷号: 16, 期号: 4, 页码: 22
作者:  Li, Yaoyu;  Yao, Hantao;  Zhang, Tianzhu;  Xu, Changsheng
Adobe PDF(19052Kb)  |  收藏  |  浏览/下载：263/35  |  提交时间：2021/03/08
Person re-identification  representation learning  graph convolutional network  
Self-Supervised Feature Augmentation for Large Image Object Detection 期刊论文
IEEE Transactions on Image Processing, 2020, 卷号: 29, 期号: 0, 页码: 6745-6758
作者:  Pan, Xingjia;  Tang, Fan;  Dong, Weiming;  Gu, Yang;  Song, Zhichao;  Meng, Yiping;  Xu, Pengfei;  Oliver, Deussen;  Xu, Changsheng
浏览  |  Adobe PDF(5411Kb)  |  收藏  |  浏览/下载：278/61  |  提交时间：2020/12/21
object detection  large image  self-supervise  feature augmentation  
A2CMHNE: Attention-Aware Collaborative Multimodal Heterogeneous Network Embedding 期刊论文
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2019, 卷号: 15, 期号: 2, 页码: 1-17
作者:  Jun Hu;  Shengsheng Qian;  Quan Fang;  Xueliang Liu;  Changsheng Xu
浏览  |  Adobe PDF(4471Kb)  |  收藏  |  浏览/下载：250/76  |  提交时间：2019/09/26
Network Embedding  Multimodal  Heterogeneous Network  
Deep Structured Event Modeling for User-Generated Photos 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 卷号: 20, 期号: 8, 页码: 2100-2113
作者:  Yang, Xiaoshan;  Zhang, Tianzhu;  Xu, Changsheng
浏览  |  Adobe PDF(1164Kb)  |  收藏  |  浏览/下载：363/82  |  提交时间：2018/01/03
Event Analysis  Unusual Event Detection  Deep Learning  
Cross-media analysis and reasoning: advances and directions 期刊论文
FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING, 2017, 卷号: 18, 期号: 1, 页码: 44-57
作者:  Peng, Yu-xin;  Zhu, Wen-wu;  Zhao, Yao;  Xu, Chang-sheng;  Huang, Qing-ming;  Lu, Han-qing;  Zheng, Qing-hua;  Huang, Tie-jun;  Gao, Wen
Adobe PDF(981Kb)  |  收藏  |  浏览/下载：387/101  |  提交时间：2017/05/05
Cross-media Analysis  Cross-media Reasoning  Cross-media Applications