中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共13条，第1-10条 帮助

限定条件                    
已选(0)清除 条数/页：   排序方式：
Reparameterizing and dynamically quantizing image features for image generation 期刊论文
PATTERN RECOGNITION, 2024, 卷号: 146, 页码: 11
作者:  Sun, Mingzhen;  Wang, Weining;  Zhu, Xinxin;  Liu, Jing
Adobe PDF(3612Kb)  |  收藏  |  浏览/下载：113/12  |  提交时间：2023/12/21
Vector quantization  Variational auto-encoder  Unconditional image generation  Text-to-image generation  Autoregressive generation  
An Efficient Sampling-Based Attention Network for Semantic Segmentation 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 2850-2863
作者:  He, Xingjian;  Liu, Jing;  Wang, Weining;  Lu, Hanqing
Adobe PDF(3252Kb)  |  收藏  |  浏览/下载：361/77  |  提交时间：2022/06/10
Stochastic processes  Sampling methods  Semantics  Image segmentation  Computational complexity  Pattern recognition  Convolution  Semantic segmentation  stochastic sampling-based attention  deterministic sampling-based attention  
Multi-Granularity Mutual Learning Network for Object Re-Identification 期刊论文
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 页码: 12
作者:  Tu, Mingfei;  Zhu, Kuan;  Guo, Haiyun;  Miao, Qinghai;  Zhao, Chaoyang;  Zhu, Guibo;  Qiao, Honglin;  Huang, Gaopan;  Tang, Ming;  Wang, Jinqiao
Adobe PDF(4360Kb)  |  收藏  |  浏览/下载：368/72  |  提交时间：2022/06/10
Feature extraction  Visualization  Task analysis  Intelligent transportation systems  Image reconstruction  Semantics  Licenses  Object re-identification  mutual learning  feature reconstruction  solving jigsaw puzzle  
Enhanced Bounding Box Estimation with Distribution Calibration for Visual Tracking 期刊论文
SENSORS, 2021, 卷号: 21, 期号: 23, 页码: 14
作者:  Yu, Bin;  Tang, Ming;  Zhu, Guibo;  Wang, Jinqiao;  Lu, Hanqing
Adobe PDF(10825Kb)  |  收藏  |  浏览/下载：386/67  |  提交时间：2022/02/16
visual tracking  bounding box estimation  overlap maximization  distribution calibration  
Question-Guided Erasing-Based Spatiotemporal Attention Learning for Video Question Answering 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 0
作者:  Liu, Fei;  Liu, Jing;  Hong, Richang;  Lu, Hanqing
Adobe PDF(3550Kb)  |  收藏  |  浏览/下载：318/78  |  提交时间：2022/01/27
video question answering  attention mechanism  metric learning  
Visual Question Answering With Dense Inter- and Intra-Modality Interactions 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 3518-3529
作者:  Liu, Fei;  Liu, Jing;  Fang, Zhiwei;  Hong, Richang;  Lu, Hanqing
Adobe PDF(2891Kb)  |  收藏  |  浏览/下载：285/60  |  提交时间：2021/12/28
Visualization  Knowledge discovery  Connectors  Encoding  Task analysis  Image coding  Stacking  Visual question answering  attention  dense interactions  
Antidecay LSTM for Siamese Tracking With Adversarial Learning 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 卷号: 32, 期号: 10, 页码: 4475-4489
作者:  Zhao, Fei;  Zhang, Ting;  Wu, Yi;  Tang, Ming;  Wang, Jinqiao
收藏  |  浏览/下载：232/0  |  提交时间：2021/12/28
Target tracking  Feature extraction  Computer architecture  Visualization  Training  Task analysis  Adversarial learning  deep learning  long short-term memory (LSTM)  visual tracking  
Macro-micro mutual learning inside compositional model for human pose estimation 期刊论文
Neurocomputing, 2021, 卷号: 449, 期号: 449, 页码: 176-188
作者:  Zhou Lu;  Chen Yingying;  Cao Congqi;  Chu Yakui;  Wang Jinqiao;  Lu Hanqing
Adobe PDF(3325Kb)  |  收藏  |  浏览/下载：218/48  |  提交时间：2021/06/21
Mutual learning  Macro-micro  BMMSE  Human pose estimation  
Show, Tell, and Polish: Ruminant Decoding for Image Captioning 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 卷号: 22, 期号: 8, 页码: 2149-2162
作者:  Guo, Longteng;  Liu, Jing;  Lu, Shichen;  Lu, Hanqing
Adobe PDF(4378Kb)  |  收藏  |  浏览/下载：204/31  |  提交时间：2020/08/31
Image captioning  Multi-pass decoding  Rumination  
Semantic-spatial fusion network for human parsing 期刊论文
NEUROCOMPUTING, 2020, 卷号: 91, 期号: 402, 页码: 375-383
作者:  Zhang, Xiaomei;  Chen, Yingying;  Zhu, Bingke;  Wang, Jinqiao;  Tang, Ming
Adobe PDF(2060Kb)  |  收藏  |  浏览/下载：301/42  |  提交时间：2020/07/20
SSFNet  Semantic modulation model  Resolution-aware model  Human parsing