Research map / Video / Video-language understanding
Motion Question Answering via Modular Motion Programs
Mark Endo, Joy Hsu, Jiaman Li, Jiajun Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 modular neuro-symbolic motion programs instead of end-to-end or text-only prediction | NS-Pose on BABEL-QA · BABEL-QA test | accuracy: 0.578; improvement over CLIP by 0.161, over MotionCLIP-MLP by 0.148, and over MotionCLIP-RNN by 0.158 | Improved |
| Add overlap between motion segments (ablation) | NS-Pose · BABEL-QA test | accuracy: 0.540 -> 0.578; 0.038 | Improved |
| Use weakly supervised segment grounding instead of ground-truth action boundaries (ablation) | NS-Pose · BABEL-QA test | accuracy: 0.553 -> 0.578; 0.025 | Improved |
| Replace dilated Conv1D temporal relation operators with a linear layer (ablation) | NS-Pose · BABEL-QA test | accuracy: 0.578 vs 0.540 | No clear effect |
Closest papers by meaning
- IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A (ICCV 2025 · similarity 0.88)
- STAIR: Spatial-Temporal Reasoning with Auditable Intermediate Results for Video Question Answering (AAAI 2024 · similarity 0.86)
- Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level (CVPR 2025 · similarity 0.85)
- ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks (NeurIPS 2025 · similarity 0.84)
- ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos (NeurIPS 2024 · similarity 0.84)
- Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering (ICLR 2025 · similarity 0.84)
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.
