Research map / 3D vision / 3D generation
Introvert: Human Trajectory Prediction via Conditional 3D Attention
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use conditional 3D visual attention over the video, conditioned on the target trajectory, instead of relying only on trajectory interactions | Introvert · All five datasets, 12 future steps | FDE: 0.41 -> 0.34 | Helped |
| Use conditional 3D visual attention over the video, conditioned on the target trajectory, instead of relying only on trajectory interactions | Introvert · All five datasets, 12 future steps | ADE: 0.21; 0.21 | No clear effect |
| Use conditional 3D visual attention over the video, conditioned on the target trajectory, instead of relying only on trajectory interactions | Introvert · Five datasets, 12 future steps | FDE | Mixed |
| Use Introvert rather than Social GAN or Social Ways | Trajectory prediction inference · UCY/ETH datasets | inference time: 0.82 sec. -> 0.12 second; 0.42 sec. -> 0.12 second | Helped |
| Vary the number of spatial attention maps across n ∈ {2, 4, 8, 16} (ablation) | Introvert conditional attention · Figure 5 evaluation | ADE | No clear effect |
| Add trajectory smoothness regularization with λ in {0.5, 0.75} rather than omitting it (ablation) | Introvert · Figure 5 evaluation | ADE | Helped |
| Increase the trajectory smoothness regularization parameter to larger values (ablation) | Introvert · Figure 5 evaluation | ADE | Hurt |
Closest papers by meaning
- Social-Transmotion: Promptable Human Trajectory Prediction (ICLR 2024 · similarity 0.89)
- Motion Diversification Networks (CVPR 2024 · similarity 0.86)
- SimpliHuMoN: Simplifying Human Motion Prediction (NeurIPS 2026 · similarity 0.86)
- SocialCVAE: Predicting Pedestrian Trajectory via Interaction Conditioned Latents (AAAI 2024 · similarity 0.86)
- EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed Dynamics (AAAI 2025 · similarity 0.86)
- Harmonizing Stochasticity and Determinism: Scene-responsive Diverse Human Motion Prediction (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.