中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共9条，第1-9条 帮助

限定条件        
已选(0)清除 条数/页：   排序方式：
Exploring Explicitly Disentangled Features for Domain Generalization 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 11, 页码: 6360-6373
作者:  Li, Jingwei;  Li, Yuan;  Wang, Huanjie;  Liu, Chengbao;  Tan, Jie
收藏  |  浏览/下载：64/0  |  提交时间：2023/12/21
Domain generalization  feature disentanglement  Fourier transform  data augmentation  
Semantic-Context Graph Network for Point-Based 3D Object Detection 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 11, 页码: 6474-6486
作者:  Dong, Shuwei;  Kong, Xiaoyu;  Pan, Xingjia;  Tang, Fan;  Li, Wei;  Chang, Yi;  Dong, Weiming
收藏  |  浏览/下载：95/0  |  提交时间：2023/12/21
3D object detection  graph neural networks  information entanglement  
Dual Transformer With Multi-Grained Assembly for Fine-Grained Visual Classification 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 9, 页码: 5009-5021
作者:  Ji, Ruyi;  Li, Jiaying;  Zhang, Libo;  Liu, Jing;  Wu, Yanjun
收藏  |  浏览/下载：98/0  |  提交时间：2023/11/16
Transformer  multi-grained assembly  fine-grained visual classification  
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：96/12  |  提交时间：2023/11/16
Vision-language model  prompt tuning  over-fitting  subspace learning  gradient projection  
Debiased Video-Text Retrieval via Soft Positive Sample Calibration 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 9, 页码: 5257-5270
作者:  Zhang, Huaiwen;  Yang, Yang;  Qi, Fan;  Qian, Shengsheng;  Xu, Changsheng
收藏  |  浏览/下载：59/0  |  提交时间：2023/11/16
debias  soft positive samples  
Jointing Recurrent Across-Channel and Spatial Attention for Multi-Object Tracking With Block-Erasing Data Augmentation 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 8, 页码: 4054-4069
作者:  Deng, Keyu;  Zhang, Congxuan;  Chen, Zhen;  Hu, Weiming;  Li, Bing;  Lu, Feng
收藏  |  浏览/下载：83/0  |  提交时间：2023/11/17
Multi-object tracking  one shot  multiattention feature learning  block erasing strategy  object occlusions  
Beyond Single Reference for Training: Underwater Image Enhancement via Comparative Learning 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 6, 页码: 2561-2576
作者:  Li, Kunqian;  Wu, Li;  Qi, Qi;  Liu, Wenjie;  Gao, Xiang;  Zhou, Liqin;  Song, Dalei
收藏  |  浏览/下载：76/0  |  提交时间：2023/11/17
Training  Image enhancement  Visualization  Task analysis  Generators  Deep learning  Oceans  Underwater image enhancement  deep learning  convolutional neural network  comparative learning  blind image quality assessment  
SiamON: Siamese Occlusion-Aware Network for Visual Tracking 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 1, 页码: 186-199
作者:  Fan, Chao;  Yu, Hongyuan;  Huang, Yan;  Shan, Caifeng;  Wang, Liang;  Li, Chenglong
收藏  |  浏览/下载：89/0  |  提交时间：2023/03/20
Visual tracking  occlusion aware  attention  siamese network  
MoEP-AE: Autoencoding Mixtures of Exponential Power Distributions for Open-Set Recognition 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 1, 页码: 312-325
作者:  Sun, Jiayin;  Wang, Hong;  Dong, Qiulei
收藏  |  浏览/下载：73/0  |  提交时间：2023/03/20
Feature extraction  Task analysis  Training  Power distribution  Sun  Decoding  Gaussian distribution  Open-set recognition  autoencoder  scale mixture distribution  exponential power distribution