Congratulations! The Information Hub has had 14 papers accepted by the prestigious computer vision conference, CVPR 2024!
Recently, the acceptance results of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), one of the top international academic conferences, were announced. According to incomplete statistics, a total of 14 research papers from the faculty and students of the Information Hub at The Hong Kong University of Science and Technology (Guangzhou) have been accepted. These papers cover various fields of research, including computer vision, deep learning, and machine learning. Topics include cross-modal adaptive object recognition, panoramic segmentation under domain adaptation, action recognition, real-time SLAM, representation learning enhanced by large language models, low-light image enhancement, depth estimation, text-driven 3D generation for industrial thin film removal, radio interference data reconstruction, digital human reconstruction, efficient hyperparameter optimization, and 3D expression gesture generation. These topics aim to advance the development of computer vision and machine learning technologies to address complex real-world problems.
Assistant Professor of Thrust of Artificial Intelligence and Thrust of Computational Media and Arts, Prof. Lin WANG's team has achieved remarkable success with eight papers accepted. Assistant Professor Yingcong CHEN's team, Professor Qiong LUO's team, Assistant Professor Mingming FAN's team, Assistant Professor Zeyu WANG's team, and Assistant Professor Zeyi WEN's team have also had papers accepted.
Congratulations to the faculty and students for their fruitful achievements at the conference! May all the faculty and students who continuously dedicate themselves to research maintain their original aspirations and forge ahead on the path of scientific exploration!
Below are the research papers and achievements of our faculty and students (in no particular order):
1 EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition
Xu Zheng, Lin Wang
2 Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentation
Xu Zheng, Pengyuan Zhou, Athanasios V. Vasilakos, Lin Wang
3 GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation
Weiming Zhang, Yexin Liu, Xu Zheng, Lin Wang
4 ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More
Jiazhou Zhou, Xu Zheng, Yuanhuiyi Lyu, Lin Wang
5 Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM
Tongyan Hua, Lin Wang
6 UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All
Yuanhuiyi Lyu, Xu Zheng, Jiazhou Zhou, Lin Wang
7 Towars Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach
Guoqiang Liang, Kanghao Chen, Hangyu Li, Yunfan Lu, Lin Wang
8 Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion
Hao Ai, Lin Wang
9 Learning to Remove Wrinkled Transparent Film with Polarized Prior
Jiaqi Tang, Ruizheng Wu, Xiaogang Xu, Sixing Hu, Ying-Cong Chen
Link: https://arxiv.org/abs/2403.04368
10 LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching
Yixun Liang*, Xin Yang*, Jiantao Lin, Haodong Li, Xiaogang Xu, Yingcong Chen
Link: https://arxiv.org/abs/2311.11284
11 PolarRec: Improving Radio Interferometric Data Reconstruction Using Polar Coordinates
Ruoqi Wang, Zhuoyang Chen, Jiayi Zhu, Qiong Luo
12 SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting
Zhijing Shao, Zhaolong Wang, Zhuang Li, Duotun Wang, Xiangru Lin, Yu Zhang, Mingming Fan, Zeyu Wang
Link: https://arxiv.org/abs/2403.05087
13 Efficient Hyperparameter Optimization with Adaptive Fidelity Identification.
Jiantong Jiang*, Zeyi Wen, Atif Mansoor, Ajmal Saeed Mian
Link: https://zeyiwen.github.io/papers/fastbo_cvpr24.pdf
14 DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic3D Expression and Gesture Generation
Junming Chen, Yunfei Liu, Jianan Wang, Ailing Zeng, Yu Li, Qifeng Chen
Link: https://arxiv.org/abs/2401.04747