Alert button
Picture for Xiaojun Chang

Xiaojun Chang

Alert button

MatchNAS: Optimizing Edge AI in Sparse-Label Data Contexts via Automating Deep Neural Network Porting for Mobile Deployment

Feb 21, 2024
Hongtao Huang, Xiaojun Chang, Wen Hu, Lina Yao

Viaarxiv icon

Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation

Dec 27, 2023
Zhuohang Dang, Minnan Luo, Chengyou Jia, Guang Dai, Xiaojun Chang, Jingdong Wang

Viaarxiv icon

Video Recognition in Portrait Mode

Dec 21, 2023
Mingfei Han, Linjie Yang, Xiaojie Jin, Jiashi Feng, Xiaojun Chang, Heng Wang

Viaarxiv icon

Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos

Dec 19, 2023
Mingfei Han, Linjie Yang, Xiaojun Chang, Heng Wang

Viaarxiv icon

Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition

Dec 04, 2023
Chengyou Jia, Minnan Luo, Xiaojun Chang, Zhuohang Dang, Mingfei Han, Mengmeng Wang, Guang Dai, Sizhe Dang, Jingdong Wang

Viaarxiv icon

Disentangled Representation Learning with Transmitted Information Bottleneck

Nov 03, 2023
Zhuohang Dang, Minnan Luo, Chengyou Jia, Guang Dai, Jihong Wang, Xiaojun Chang, Jingdong Wang, Qinghua Zheng

Figure 1 for Disentangled Representation Learning with Transmitted Information Bottleneck
Figure 2 for Disentangled Representation Learning with Transmitted Information Bottleneck
Figure 3 for Disentangled Representation Learning with Transmitted Information Bottleneck
Figure 4 for Disentangled Representation Learning with Transmitted Information Bottleneck
Viaarxiv icon

Mask Propagation for Efficient Video Semantic Segmentation

Oct 29, 2023
Yuetian Weng, Mingfei Han, Haoyu He, Mingjie Li, Lina Yao, Xiaojun Chang, Bohan Zhuang

Figure 1 for Mask Propagation for Efficient Video Semantic Segmentation
Figure 2 for Mask Propagation for Efficient Video Semantic Segmentation
Figure 3 for Mask Propagation for Efficient Video Semantic Segmentation
Figure 4 for Mask Propagation for Efficient Video Semantic Segmentation
Viaarxiv icon

No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling

Oct 09, 2023
Xuwei Xu, Changlin Li, Yudong Chen, Xiaojun Chang, Jiajun Liu, Sen Wang

Figure 1 for No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling
Figure 2 for No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling
Figure 3 for No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling
Figure 4 for No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling
Viaarxiv icon

PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement

Sep 20, 2023
Chengyou Jia, Minnan Luo, Zhuohang Dang, Guang Dai, Xiaojun Chang, Jingdong Wang, Qinghua Zheng

Figure 1 for PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement
Figure 2 for PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement
Figure 3 for PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement
Figure 4 for PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement
Viaarxiv icon

ProAgent: Building Proactive Cooperative AI with Large Language Models

Aug 28, 2023
Ceyao Zhang, Kaijie Yang, Siyi Hu, Zihao Wang, Guanghe Li, Yihang Sun, Cheng Zhang, Zhaowei Zhang, Anji Liu, Song-Chun Zhu, Xiaojun Chang, Junge Zhang, Feng Yin, Yitao Liang, Yaodong Yang

Figure 1 for ProAgent: Building Proactive Cooperative AI with Large Language Models
Figure 2 for ProAgent: Building Proactive Cooperative AI with Large Language Models
Figure 3 for ProAgent: Building Proactive Cooperative AI with Large Language Models
Figure 4 for ProAgent: Building Proactive Cooperative AI with Large Language Models
Viaarxiv icon