ICCV 2021 accepted papers on Multi-agent systems and games
24 of the 1,612 papers accepted at ICCV 2021 (1.5%) are on Multi-agent systems and games, compared with 0.9% at ICCV 2019. They fall into 3 topics.
See ICCV 2021 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 · 22 papers
- AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting (720 citations)
- Large Scale Interactive Motion Forecasting for Autonomous Driving: The Waymo Open Motion Dataset (666 citations)
- From Goals, Waypoints & Paths to Long Term Human Trajectory Forecasting (347 citations)
- Auxiliary Tasks and Exploration Enable ObjectGoal Navigation (164 citations)
- Where2Act: From Pixels to Actions for Articulated 3D Objects (156 citations)
- LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving (134 citations)
- Social NCE: Contrastive Learning of Socially-Aware Motion Representations (123 citations)
- Hierarchical Object-to-Zone Graph for Object Navigation (100 citations)
- LOKI: Long Term and Key Intentions for Trajectory Prediction (93 citations)
- Pathdreamer: A World Model for Indoor Navigation (84 citations)
- Visual Graph Memory With Unsupervised Representation for Visual Navigation (82 citations)
- THDA: Treasure Hunt Data Augmentation for Semantic Navigation (74 citations)
and 10 more in the interactive map.
LLM agents · 1 paper
- GridToPix: Training Embodied Agents With Minimal Supervision (14 citations)
Cooperative multi-agent RL · 1 paper
- Adversarial Attacks on Multi-Agent Communication (71 citations)
