858 citations
- University of Chinese Academy of SciencesCN27 papers
- Chinese Academy of SciencesCN23 papers
- Institute of AutomationCN19 papers
- Tsinghua UniversityCN19 papers
- Shanghai Artificial Intelligence LaboratoryCN10 papers
- Peking UniversityCN9 papers
- Shandong Institute of AutomationCN9 papers
- Beihang UniversityCN8 papers
- Center for Excellence in Brain Science and Intelligence TechnologyCN7 papers
- South China University of TechnologyCN5 papers
- Center for Life SciencesCN4 papers
- Chinese University of Hong KongHK4 papers
80 papers
Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning
Chenjia Bai, Lingxiao Wang, Jianye Hao +4
Offline Reinforcement Learning (RL) has shown promising results in learning a task-specific policy from a fixed dataset. However, successful offline RL often relies heavily on the…
S4TP: Social-Suitable and Safety-Sensitive Trajectory Planning for Autonomous Vehicles
Xiao Wang, Ke Tang, Xingyuan Dai +5
In public roads, autonomous vehicles (AVs) face the challenge of frequent interactions with human-driven vehicles (HDVs), which render uncertain driving behavior due to varying soc…
Calibration & Reconstruction: Deep Integrated Language for Referring Image Segmentation
Yichen Yan, Xingjian He, Sihan Chen +1
Referring image segmentation aims to segment an object referred to by natural language expression from an image. The primary challenge lies in the efficient propagation of fine-gra…
Unified Multi-modal Diagnostic Framework with Reconstruction Pre-training and Heterogeneity-combat Tuning
Yupei Zhang, Li Pan, Qiushi Yang +2
Medical multi-modal pre-training has revealed promise in computer-aided diagnosis by leveraging large-scale unlabeled datasets. However, existing methods based on masked autoencode…
Hypergraph-based Multi-View Action Recognition using Event Cameras
Yue Gao, Jiaxuan Lu, Siqi Li +2
Action recognition from video data forms a cornerstone with wide-ranging applications. Single-view action recognition faces limitations due to its reliance on a single viewpoint. I…
MS-Net: A Multi-Path Sparse Model for Motion Prediction in Multi-Scenes
Xiaqiang Tang, Weigao Sun, Siyuan Hu +2
The multi-modality and stochastic characteristics of human behavior make motion prediction a highly challenging task, which is critical for autonomous driving. While deep learning…