ICCV 2023 accepted papers on Multi-agent systems and games
19 of the 2,156 papers accepted at ICCV 2023 (0.9%) are on Multi-agent systems and games, compared with 1.5% at ICCV 2021. They fall into 3 topics.
See ICCV 2023 in the interactive map
Submitting to ICCV? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Human-AI and goal-conditioned · 17 papers
- GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving (210 citations)
- MotionLM: Multi-Agent Motion Forecasting as Language Modeling (132 citations)
- HM-ViT: Hetero-Modal Vehicle-to-Vehicle Cooperative Perception with Vision Transformer (122 citations)
- Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception (120 citations)
- ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation (109 citations)
- HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World (104 citations)
- CORE: Cooperative Reconstruction for Multi-Agent Perception (89 citations)
- UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework (64 citations)
- March in Chat: Interactive Prompting for Remote Embodied Referring Expression (47 citations)
- Navigating to Objects Specified by Images (47 citations)
- R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement (45 citations)
- Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents (40 citations)
and 5 more in the interactive map.
