SELECTED PUBLICATIONS
Full paper list can be found at DBLP and Google Scholar.
PREPRINTS
Vision Language Navigation with Multi-granularity Observation and Auxiliary Reasoning Tasks
- we propose Multi-granularity Auxiliary Reason- ing Navigation (MG-AuxRN) to facilitate navigation learning. MG-AuxRN perceives multi-granularity input which combining dense object features and global image features.
Fengda Zhu, Yi Zhu, Yanxin Long, Xiaojun Chang, and Xiaodan Liang
Submitted to IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI), 2020
pdf
|
code
ZeroNAS:Differentiable Generative Adversarial Networks Search for Zero-Shot Learning
- Considering the varieties in datasets and tasks, we make the first attempt to bring NAS techniques into the realm of ZSL, and thus propose ZeroNAS to formulate the GAN architecture design for ZSL as a NAS problem.
Caixia Yan, Xiaojun Chang, Zhihui Li, Zongyuan Ge, Weili Guan, Lei Zhu and Qinghua Zheng
Submitted to IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI), 2020
pdf
A Comprehensive Survey of Neural Architecture Search:Challenges and Solutions
- we provide a new perspective, beginning with an overview of the characteristics of the earliest NAS algorithms, summarizing the problems in these early NAS algorithms, and then providing solutions for subsequent related research work
Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Xiaojiang Chen and Xin Wang
Accepted by ACM Computing Surveys, 2021
pdf
CONFERENCE PAPERS
UPDeT:Universal Multi-agent RL via Policy Decoupling with Transformers
- propose a universal policy decoupling transformer model that extends MARL to a much broader scenario
Siyi Hu, Fengda Zhu, Xiaojun Chang and Xiaodan Liang
ICLR 2021
paper
Mining Inter-Video Proposal Relations for Video Object Detection
- design a novel Inter-Video Proposal Relation method, which can effectively leverage inter-video proposal relation to learn discriminative representations for video object detection
Mingfei Han, Yali Wang, Xiaojun Chang and Yu Qiao
ECCV 2020
paper
|
code
Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting
- investigate how to utilize visual content for disambiguation and latent space alignment in unsupervised MMT
Po-Yao Huang, Junjie Hu, Xiaojun Chang and Alexander Hauptmann
ACL 2020
paper
Vision-language Navigation with Self-Supervised Auxiliary Reasoning Tasks
- Introducing Auxiliary Reasoning Navigation (AuxRN), a framework with four self-supervised auxiliary reasoning tasks to take advantage of the additional training signals derived from the semantic information
Fengda Zhu, Yi Zhu, Xiaojun Chang, Xiaodan Liang
CVPR 2020
paper
|
DEMO
|
CODE
ZSTAD:Zero-Shot Temporal Activity Detection
- Proposing a novel problem setting for temporal activity detection in which activities that are not seen during the training stage can be recognized and localized simultaneously
Lingling Zhang, Xiaojun Chang, Jun Liu, Sen Wang, Zongyuan Ge, Minnan Luo, Alexander Hauptmann
CVPR 2020
paper
Unity Style Transfer for Person Re-Identification
- smooth the style disparities within the same camera and across different cameras
Chong Liu, Xiaojun Chang, Yi-Dong Shen
CVPR 2020
paper
Neural Architecture Search by Block-wisely Distilling Architecture Knowledge
- modularize the large search space of NAS into blocks to ensure that the potential candidate architectures are fully trained
Changlin Li, Jiefeng Peng, Liuchun Yuan, Guangrun Wang, Xiaodan Liang, Liang Lin, Xiaojun Chang
CVPR 2020
paper
|
code
Vision Dialogue Navigation by Exploring Cross-modal Memory
- learning an agent endowed with the capability of constant conversation for help with natural language and navigating according to human responses
- propose a Cross-modal Memory Network (CMN) for remembering and understanding the rich information relevant to historical navigation actions
Yi Zhu, Fengda Zhu, Zhao huan Zhan, Bingqian Lin, Jianbin Jiao, Xiaojun Chang, Xiaodan Liang
CVPR 2020
paper
|
code
Overcoming Multi-Model Forgetting in One-Shot NAS with Diversity Maximization
- formulate the supernet training in the One-Shot NAS as a constrained optimization problem of continual learning that the learning of current architecture should not degrade the performance of previous architectures during the supernet training
Miao Zhang, Huiqi Li, Shirui Pan, Xiaojun Chang, Steven Su
CVPR 2020
paper
|
code
Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement
- enhance the intelligent exploration of differentiable Neural Architecture Search in the latent space
Miao Zhang, Huiqi Li, Shirui Pan, Xiaojun Chang, Zongyuan Ge and Steven Su
NeurIPS 2020
paper
|
code
Hierarchical Neural Architecture Search for Deep Stereo Matching
- leverage the volumetric stereo matching pipeline and allow the network to automat70 ically select the optimal structures for both the Feature Net and the Matching Net
Xuelian Cheng, Yiran Zhong, Mehrtash Harandi, Yuchao Dai, Xiaojun Chang, Hongdong Li, Tom Drummond, and Zongyuan Ge
NeurIPS 2020
paper
|
code
Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations
- leveraging visual object detection and propose a model with diverse multi-head attention to learn grounded multilingual multimodal representations
Po-Yao Huang, Xiaojun Chang, Alexander G. Hauptmann
EMNLP 2019
paper
Annotation Efficient Cross-Modal Retrieval with Adversarial Attentive Alignment
- propose a novel framework to leverage automatically extracted regional semantics from un-annotated images as additional weak supervision to learn visual-semantic embeddings
Po-Yao Huang, Guoliang Kang, Wenhe Liu, Xiaojun Chang, Alexander G. Hauptmann
ACM MM 2019
paper
RCAA:Relational Context-Aware Agents for Person Search
- made the earliest attempt to address the person search problem and built the first deep reinforcement learning based person search framework
Xiaojun Chang, Po-Yao Huang, Yi-Dong Shen, Xiaodan Liang, Yi Yang and Alexander G. Hauptmann
ECCV 2018
paper
Reinforcement Cutting-Agent Learning for Video Object Segmentation
- make a pioneer effort to formulate the video object segmentation problem as a Markov Decision Process and propose a novel reinforcement cutting-agent learning framework to tackle this problem
Junwei Han, Le Yang, Dingwen Zhang, Xiaojun Chang, Xiaodan Liang
CVPR 2018
paper
Complex Event Detection by Identifying Reliable Shots from Untrimmed Videos
- simultaneously learns a linear SVM classifier and infers a binary indicator for each instance in order to select reliable training instances from each positive or negative bag
Hehe Fan, Xiaojun Chang, De Cheng, Yi Yang, Dong Xu, Alexander G. Hauptmann
ICCV 2017
paper
They are Not Equally Reliable:Semantic Event Search Using Differentiated Concept Classifiers
- combine the concept classifiers based on a principled estimate of their accuracy on the unlabeled test videos
Xiaojun Chang, Yao-Liang Yu, Yi Yang, Eric P. Xing
CVPR 2016
paper
Complex Event Detection using Semantic Saliency and Nearly-Isotonic SVM
- define a novel notion of semantic saliency that assesses the relevance of each shot with the event of interest
Xiaojun Chang, Yi Yang, Eric P. Xing, Yao-Liang Yu
ICML 2015
paper
|
code
Searching Persuasively:Joint Event Detection and Evidence Recounting with Limited Supervision
- propose a joint framework that simultaneously detects high-level events and localizes the indicative concepts of the events
Xiaojun Chang, Yao-Liang Yu, Yi Yang, Alexander G. Hauptmann
ACM MM 2015
paper
JOURNAL PAPERS
One-Shot Neural Architecture Search:Maximising Diversity to Overcome Catastrophic Forgetting
- To improve transferability, we further devised a variant of NSAS, called NSAS-C, which searches for deeper architectures in the convolutional cell search.
Miao Zhang, Huiqi Li, Shirui Pan, Xiaojun Chang, Chuan Zhou, Zongyuan Ge, and Steven Su
IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI), 2020
pdf
|
code
Semantic Pooling for Complex Event Analysis in Untrimmed Videos
- design the informed nearly-isotonic SVM classifier (NI-SVM) that is able to exploit the carefully constructed ordering information
Xiaojun Chang, Yaoliang Yu, Yi Yang, Eric P. Xing
IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI) 39(8) 1617-1632 (2017)
pdf
|
code
Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization
- propose a semi-supervised batch mode multi-class active learning algorithm for visual concept recognition
Yi Yang, Zhigang Ma, Feiping Nie, Xiaojun Chang, Alexander G. Hauptmann
International Journal of Computer Vision (IJCV) 113(2) 113-127 (2015)
pdf
Semantics Preserving Graph Propagation for Zero-Shot Object Detection
- propose a semantics preserving graph propagation model based on GCN for the challenging ZSD task, which leverages both the semantic description and structural knowledge in prior category graphs to facilitate the semantic coherency of region graph.
Caixia Yan, Qinghua Zheng, Xiaojun Chang, Minnan Luo, ChungHsing Yeh and Alexander G. Hauptmann
IEEE Transactions on Image Processing 29:8163-8176 (2020)
pdf
Self-supervised Deep Correlation Tracking
- formulate a multi-cycle consistency loss based selfsupervised learning manner to pre-training the deep feature extraction network, which can take advantage of extensive unlabeled video samples rather than limited manually annotated samples
Di Yuan, Xiaojun Chang, Po-Yao Huang, Qiao Liu, and Zhenyu He
IEEE Transactions on Image Processing 30:976-985 (2021)
pdf