Weixin Li

Dr. Weixin Li is an Associate Professor at the School of Computer Science and Engineering, Beihang Univeristy. Her research interests include include computer vision, image processing, and big data analytics. She received the Ph.D. degree in computer science from the University of California, Los Angeles (UCLA), Los Angeles, CA, USA, in 2017, under the supervision of Professor Song-Chun Zhu. She is currently a faculty member at the Laboratory of Intelligent Recognition and Image Processing (IRIP).

Current Research Projects

I am currently working on the projects of Social Media Analysis (supported by National Natural Science Foundation of China No. 62276018), Multi-level Autonomous Adaptation of Models and Tasks for Visual Perception (supported by National Key Research and Development Plan of China 2022ZD0161901), High-Speed Deep Leaning Inference Models (supported by National Key Research and Development Plan of China 2021ZD0110503).

Social Media Analysis
Multimodal Topic Detection and Tracking
Visual Perception
Multimodal Topic And-Or Graph (MT-AOG)

Multi-level Autonomous Adaptation of Models and Tasks for Visual Perception
Relation Modeling of Models and Tasks
Parameter-Efficient Transfer Learning (PETL)
Multi-Task Joint Learning

High-Speed Deep Leaning Inference Models
Neural Architecture Search (NAS)
High-Speed Inference Model
Deep Learning Models for Multimodal Tasks

Publications

• Leveraging Predicate and Triplet Learning for Scene Graph Generation
  -- Jiankai Li, Yunhong Wang, and Weixin Li
  -- IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 (accepted).
• MHRN: A Multimodal Hierarchical Reasoning Network for Topic Detection
  -- Jiankai Li, Yunhong Wang, and Weixin Li
  -- IEEE Transactions on Multimedia (TMM), 2024 (accepted).
• Read, Spell and Repeat: Scene Text Recognition with Vision-Language Circular Refinement
  -- Taiwei Zhang, Zhenghui Hu, Weixin Li, Qingjie Liu, and Yunhong Wang
  -- IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024 (accepted).
• Multi-Modal and Multi-Scale Temporal Fusion Architecture Search for Audio-Visual Video Parsing
  -- Jiayi Zhang, and Weixin Li
  -- Proceedings of the 31st ACM International Conference on Multimedia (MM), 2023.
• Human Emotion Recognition With Relational Region-Level Analysis
  -- Weixin Li, Xuan Dong, and Yunhong Wang
  -- IEEE Transactions on Affective Computing, 2023.
• Facial Expression Animation by Landmark Guided Residual Module
  -- Xueping Wang, Yunhong Wang, Weixin Li, Zhengyin Du, and Di Huang
  -- IEEE Transactions on Affective Computing, 2023.
• Causal Intervention and Counterfactual Reasoning for Multi-modal Fake News Detection
  -- Ziwei Chen, Linmei Hu, Weixin Li, Yingxia Shao, and Liqiang Nie
  -- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), 2023.
• Zero-shot Scene Graph Generation via Triplet Calibration and Reduction
  -- Jiankai Li, Yunhong Wang, and Weixin Li
  -- ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2023.
• Dual-Lens HDR using Guided 3D Exposure CNN and Guided Denoising Transformer
  -- Weixin Li, Tiantian Cao, Chang Liu, Xue Tian, Ya Li, Xiaojie Wang, and Xuan Dong
  -- ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2023.
• CUR Transformer: A Convolutional Unbiased Regional Transformer for Image Denoising
  -- Kang Xu, Weixin Li, Xia Wang, Xiaoyan Hu, Ke Yan, Xiaojie Wang, and Xuan Dong
  -- ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2023.
• Spatially Consistent Transformer for Colorization in Monochrome-Color Dual-Lens System
  -- Xuan Dong, Chang Liu, Xiaoyan Hu, Kang Xu, and Weixin Li
  -- IEEE Transations on Image Processing (TIP), 2022.
• A Colorization Framework for Monochrome-Color Dual-Lens Systems Using a Deep Convolutional Network
  -- Xuan Dong, Weixin Li, Xiaoyan Hu, Xiaojie Wang, and Yunhong Wang
  -- IEEE Transations on Visualization and Computer Graphics (TVCG), 2022.
• Self-Supervised Colorization Towards Monochrome-Color Camera Systems Using Cycle CNN
  -- Xuan Dong, Chang Liu, Weixin Li, Xiaoyan Hu, Xiaojie Wang, and Yunhong Wang
  -- IEEE Transations on Image Processing (TIP), 2021.
• MIEHDR CNN: Main Image Enhancement based Ghost-Free High Dynamic Range Imaging using Dual-Lens Systems
  -- Xuan Dong, Xiaoyan Hu, Weixin Li, Xiaojie Wang, and Yunhong Wang
  -- The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021.
• Spatio-Temporal Encoder-Decoder Fully Convolutional Network for Video-Based Dimensional Emotion Recognition
  -- Zhengyin Du, Suowei Wu, Di Huang, Weixin Li, and Yunhong Wang
  -- IEEE Transactions on Affective Computing, 2021.
• Expression-Latent-Space-guided GAN for Facial Expression Animation based on Discrete Labels
  -- Xueping Wang, Weixin Li, and Di Huang
  -- IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2021.
• Entity Relation Fusion for Real-Time One-Stage Referring Expression Comprehension
  -- Hang Yu, Weixin Li, Jiankai Li, and Ye Du
  -- ACM Multimedia Asia, 2021.
• Cycle-CNN for Colorization towards Real Monochrome-Color Camera Systems
  -- Xuan Dong, Weixin Li, Xiaojie Wang, and Yunhong Wang
  -- The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2020.
• 3D Face Mask Anti-spoofing via Deep Fusion of Dynamic Texture and Shape Clues
  -- Song Chen, Weixin Li, Hongyu Yang, Di Huang, and Yunhong Wang
  -- IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2020.
• Learning a Deep Convolutional Network for Colorization in Monochrome-Color Dual-Lens System
  -- Xuan Dong, Weixin Li, Xiaojie Wang, and Yunhong Wang
  -- The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2019.
• Encoding Visual Behaviors with Attentive Temporal Convolution for Depression Prediction
  -- Zhengyin Du, Weixin Li, Di Huang, and Yunhong Wang
  -- IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2019.
• Discriminative Attention-based Convolutional Neural Network for 3D Facial Expression Recognition
  -- Kangkang Zhu, Zhengyin Du, Weixin Li, Di Huang, Yunhong Wang, and Liming Chen
  -- IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2019.
• Continuous Emotion Recognition in Videos by Fusing Facial Expression, Head Pose and Eye Gaze
  -- Suowei Wu, Zhengyin Du, Weixin Li, Di Huang, and Yunhong Wang
  -- ACM International Conference on Multimodal Interaction (ICMI), 2019.
• Ground-Truth Data Set and Baseline Evaluations for Base-Detail Separation Algorithms at the Part Level
  -- Xuan Dong, Boyan I. Bonev, Weixin Li, Weichao Qiu, Xianjie Chen, and Alan L. Yuille
  -- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2018.
• Bipolar Disorder Recognition via Multi-scale Discriminative Audio Temporal Representation
  -- Zhengyin Du, Weixin Li, Di Huang, and Yunhong Wang
  -- Proceedings of the 2018 on Audio/Visual Emotion Challenge and Workshop (AVEC), 2018.
• Joint Image-Text News Topic Detection and Tracking by Multimodal Topic And-Or Graph
  -- Weixin Li, Jungseock Joo, Hang Qi, and Song-Chun Zhu
  -- IEEE Transactions on Multimedia (TMM), 2017.
• Visual Persuasion: Inferring Communicative Intents of Images
  -- Jungseock Joo, Weixin Li, Francis F. Steen, and Song-Chun Zhu
  -- IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
• Combining Tensor Space Analysis and Active Appearance Models for Aging Effect Simulation on Face Images
  -- Yunhong Wang, Zhaoxiang Zhang, Weixin Li, and Fangyuan Jiang -- IEEE Transactions on Systems, Man, and Cybernetics - Part B: Cybernetics, 2012.

Teaching

• Introduction to Pattern Recognition
• Human-Computer Interaction
• Methodology of Computer Science