Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Zheng-Jun Zha

Multi-Modulation Network for Audio-Visual Event Localization

Aug 30, 2021
Hao Wang, Zheng-Jun Zha, Liang Li, Xuejin Chen, Jiebo Luo

  Access Paper or Ask Questions

A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP

Aug 30, 2021
Yucheng Zhao, Guangting Wang, Chuanxin Tang, Chong Luo, Wenjun Zeng, Zheng-Jun Zha

  Access Paper or Ask Questions

Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification

Aug 23, 2021
Kecheng Zheng, Cuiling Lan, Wenjun Zeng, Jiawei Liu, Zhizheng Zhang, Zheng-Jun Zha

* ACM MM 2021 

  Access Paper or Ask Questions

Self-Supervised Visual Representations Learning by Contrastive Mask Prediction

Aug 18, 2021
Yucheng Zhao, Guangting Wang, Chong Luo, Wenjun Zeng, Zheng-Jun Zha

* Accepted to ICCV 2021 

  Access Paper or Ask Questions

Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment

Aug 18, 2021
Heliang Zheng, Huan Yang, Jianlong Fu, Zheng-Jun Zha, Jiebo Luo

  Access Paper or Ask Questions

Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers

Aug 05, 2021
Wen Wang, Yang Cao, Jing Zhang, Fengxiang He, Zheng-Jun Zha, Yonggang Wen, Dacheng Tao

* Accepted by ACM MM2021. Source code is available at: Update acknowledgment 

  Access Paper or Ask Questions

Disentangle Your Dense Object Detector

Jul 27, 2021
Zehui Chen, Chenhongyi Yang, Qiaofei Li, Feng Zhao, Zheng-Jun Zha, Feng Wu

* ACM MM2021 

  Access Paper or Ask Questions

Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning

Jul 19, 2021
Kai Zhu, Yang Cao, Wei Zhai, Jie Cheng, Zheng-Jun Zha

* Accepted by CVPR 2021 

  Access Paper or Ask Questions

Adaptive Domain-Specific Normalization for Generalizable Person Re-Identification

May 11, 2021
Jiawei Liu, Zhipeng Huang, Kecheng Zheng, Dong Liu, Xiaoyan Sun, Zheng-Jun Zha

* Withdraw this paper for internal review. Since we were not familiar with the use of arXiv, our initial manuscript was uploaded by mistake and we found many inappropriate and unmodified parts of it (such as the experimental results in Table 2,3, the Equation 13). I am sorry to say that this work still needs to be further completed and we do not intend to use it for publication 

  Access Paper or Ask Questions

Rethinking Graph Neural Network Search from Message-passing

Apr 18, 2021
Shaofei Cai, Liang Li, Jincan Deng, Beichen Zhang, Zheng-Jun Zha, Li Su, Qingming Huang

* This paper has been accepted by CVPR2021 

  Access Paper or Ask Questions

Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos

Apr 15, 2021
Jiawei Liu, Zheng-Jun Zha, Wei Wu, Kecheng Zheng, Qibin Sun

  Access Paper or Ask Questions

Memory Enhanced Embedding Learning for Cross-Modal Video-Text Retrieval

Mar 29, 2021
Rui Zhao, Kecheng Zheng, Zheng-Jun Zha, Hongtao Xie, Jiebo Luo

* Technical Report 

  Access Paper or Ask Questions

Group-aware Label Transfer for Domain Adaptive Person Re-identification

Mar 23, 2021
Kecheng Zheng, Wu Liu, Lingxiao He, Tao Mei, Jiebo Luo, Zheng-Jun Zha

* Accepted by CVPR 2021 

  Access Paper or Ask Questions

Synergy Between Semantic Segmentation and Image Denoising via Alternate Boosting

Feb 24, 2021
Shunxin Xu, Ke Sun, Dong Liu, Zhiwei Xiong, Zheng-Jun Zha

  Access Paper or Ask Questions

General-Purpose Speech Representation Learning through a Self-Supervised Multi-Granularity Framework

Feb 03, 2021
Yucheng Zhao, Dacheng Yin, Chong Luo, Zhiyuan Zhao, Chuanxin Tang, Wenjun Zeng, Zheng-Jun Zha

  Access Paper or Ask Questions

VAE^2: Preventing Posterior Collapse of Variational Video Predictions in the Wild

Jan 28, 2021
Yizhou Zhou, Chong Luo, Xiaoyan Sun, Zheng-Jun Zha, Wenjun Zeng

* 17 pages, 26 figures 

  Access Paper or Ask Questions

Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification

Dec 17, 2020
Kecheng Zheng, Cuiling Lan, Wenjun Zeng, Zhizheng Zhang, Zheng-Jun Zha

* 9 pages. Accepted to 35th AAAI Conference on Artificial Intelligence (AAAI 2021) 

  Access Paper or Ask Questions

Temporal Attribute-Appearance Learning Network for Video-based Person Re-Identification

Sep 09, 2020
Jiawei Liu, Xierong Zhu, Zheng-Jun Zha

  Access Paper or Ask Questions

Nighttime Dehazing with a Synthetic Benchmark

Sep 09, 2020
Jing Zhang, Yang Cao, Zheng-Jun Zha, Dacheng Tao

* ACM MM 2020. Both the dataset and source code will be available at \url{

  Access Paper or Ask Questions

DeepFacePencil: Creating Face Images from Freehand Sketches

Aug 31, 2020
Yuhang Li, Xuejin Chen, Binxin Yang, Zihan Chen, Zhihua Cheng, Zheng-Jun Zha

* ACM MM 2020 (oral) 

  Access Paper or Ask Questions

Learning to Discretely Compose Reasoning Module Networks for Video Captioning

Jul 17, 2020
Ganchao Tan, Daqing Liu, Meng Wang, Zheng-Jun Zha

* IJCAI 2020, Pages 745-752 
* Accepted at IJCAI 2020 Main Track. Sole copyright holder is IJCAI. Code is available at 

  Access Paper or Ask Questions

Co-Saliency Spatio-Temporal Interaction Network for Person Re-Identification in Videos

May 11, 2020
Jiawei Liu, Zheng-Jun Zha, Xierong Zhu, Na Jiang

  Access Paper or Ask Questions

Self-Supervised Tuning for Few-Shot Segmentation

Apr 12, 2020
Kai Zhu, Wei Zhai, Zheng-Jun Zha, Yang Cao

* under review 

  Access Paper or Ask Questions

Spatiotemporal Fusion in 3D CNNs: A Probabilistic View

Apr 10, 2020
Yizhou Zhou, Xiaoyan Sun, Chong Luo, Zheng-Jun Zha, Wenjun Zeng

* To be published in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 

  Access Paper or Ask Questions