Jiaze Wang

I am a year-3 PhD student at CUHK CSE under the supervision of Prof. Pheng Ann Heng and Prof. Guangyong Chen. My research is on Artificial Intelligence, particularly Multi-modal Learning and 3D Vision.

Previously, I was a research assistant of MMLAB supervised by Prof. Dahua Lin. I got my MSc Degree in the Department of Computer Science and Engineering at The Chinese University of Hong Kong in 2019. I was a visiting student at SIAT, working closely with Prof. Xiaojiang Peng and Prof. Yu Qiao in 2018. During my undergraduate study, I worked with Prof. Anfeng Liu at Central South University

Email / GitHub / Google Scholar

Research

* denotes equal contribution.

	TripletMix: Triplet Data Augmentation for 3D Understanding Jiaze Wang, Yi Wang, Ziyu Guo, Renrui Zhang, Donghao Zhou, Guangyong Chen, Anfeng Liu, Pheng-Ann Heng In Submission paper / website / We propose a deformable targets network for trajectory prediction.
	SFANet: Spatial-Frequency Attention Network for Weather Forecasting Jiaze Wang, Hao Chen, Hongcan Xu, Jinpeng Li, Bowen Wang, Kun Shao, Furui Liu, Huaxi Chen, Guangyong Chen, and Pheng-Ann Heng. In submission We present an innovative approach that seamlessly integrates advanced token mixing and attention mechanisms for weather prediction.
	SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning Hao Chen, Jiaze Wang, Ziyu Guo, Jinpeng Li, Donghao Zhou, Bian Wu, Chenyong Guan, Guangyong Chen, and Pheng-Ann Heng. In submission paper / website / We present SignVTCL, a multi-modal continuous sign language recognition framework enhanced by visual-textual contrastive learning, which leverages the full potential of multi-modal data and the generalization ability of language model.
	PointPatchMix: Point Cloud Mixing with Patch Scoring Yi Wang, Jiaze Wang, Jinpeng Li, Zixu Zhao, Guangyong Chen, Anfeng Liu and Pheng-Ann Heng. AAAI 2024 paper / code / website / A novel approach that mixes point clouds at the patch level and integrates a patch scoring module to generate content-based targets for mixed point clouds.
	Traj-MAE: Masked Autoencoders for Trajectory Prediction Hao Chen, Jiaze Wang, Kun Shao, Furui Liu, Chenyong Guan, Jianye Hao, Guangyong Chen, Pheng-Ann Heng. ICCV 2023 paper / website / An efficient masked autoencoder for trajectory prediction.
	Object-centric Multiple Object Tracking Zixu Zhao, Jiaze Wang, Max Horn, Yizhuo Ding, Tong He, Zechen Bai, Bing Shuai, Dominik Zietlow, Carl-Johann Simon-Gabriel, Zhuowen Tu, Thomas Brox, Bernt Schiele, Yanwei Fu, Tianjun Xiao, Francesco Locatello, Zheng Zhang. ICCV 2023 paper / code / We propose a video object-centric model for multiple object tracking.
	DR-Label: Label Deconstruction and Reconstruction of GNN Models for Catalysis Systems Bowen Wang, Chen Liang, Jiaze Wang, Jiezhong Qiu, Furui Liu, Shaogang Hao, Dong Li, Guangyong Chen, Xiaolong Zou, Pheng-Ann Heng. AAAI 2024 We present a novel graph neural network supervision and prediction strategy DR-Label for catalysis systems.
	Fast Non-Markovian Diffusion Model for Weakly Supervised Anomaly Detection in Brain MR Images Jinpeng Li, Hanqun CAO, Jiaze Wang, Furui Liu, Qi Dou, Guangyong Chen, Pheng-Ann Heng. MICCAI 2023 We design a novel non-Markovian diffusion process for efficient anatomical information transfer across diffusion steps to resolve gradual anatomical information loss along Markov Chain.
	Learning Robust Classifier for Imbalanced Medical Image Dataset with Noisy Labels by Minimizing Invariant Risk Jinpeng Li, Hanqun CAO, Jiaze Wang, Furui Liu, Qi Dou, Guangyong Chen, Pheng-Ann Heng. MICCAI 2023 We propose a robust classifier that trains on a multi-stage noise removal framework, which jointly rectifies the adverse effects of label noise, imbalanced distribution, and class hardness.
	Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Network Jiaze Wang, Kai Chen, and Qi Dou IROS 2021 paper / code / website / Category-Level 6D Object Pose Estimation.
	A Unified Framework for Shot Type Classification Based on Subject Centric Lens Anyi Rao, Jiaze Wang, Linning Xu, Xuekun Jiang, Qingqiu Huang, Bolei Zhou, Dahua Lin ECCV 2020 paper / website / Cinematic style analysis in videos.
	MovieNet: A Holistic Dataset for Movie Understanding Qingqiu Huang, Yu Xiong, Anyi Rao, Jiaze Wang, Dahua Lin ECCV 2020 paper / website / A holistic dataset for movie understanding.
	Cascade Multi-Head Attention Networks for Action Recognition Jiaze Wang, Xiaojiang Peng, Yu Qiao. Computer Vision and Image Understanding A cascade multi-head attention Network to construct video representations..
	Part Matching with Multi-level Attention for Person Re-Identification Jiaze Wang ICCV Workshops 2019 A Multi-level Attention Network associated with a Part Matching Distance.
	A resource allocation model based on double-sided combinational auctions for transparent computing Jiaze Wang, Anfeng Liu, Tong Yan, Zhiwen Zeng. Peer-to-Peer Networking and Applications Propose an effective resource allocation model for optimizing the performance of mobile cloud computing.
	Key parameters decision for cloud computing: Insights from a multiple game model Jiaze Wang, Anfeng Liu, Shigeng Zhang. Concurrency and Computation: Practice and Experience Propose a multiple game model to formulate the critical parameters decision process of cloud computing.
	Comprehensive Optimization of Energy Consumption and Delay Performance for Green Communication in Internet of Things Jiaze Wang, Chunhua Hu, Anfeng Liu. Mobile Information Systems Propose a novel utility-based adaptive duty cycle (UADC) routing algorithm for WSNs.