Research map / Video / Action recognition
Anticipating Future Relations via Graph Growing for Action Prediction
Read the paperCheck 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 |
|---|---|---|---|
| reason over object relations and synthesize future relations with graph growing | action prediction model · UCF101, InceptionV4 features; observation ratio 0.3 | accuracy (%): 87.78 -> 88.97 | Helped |
| reason over object relations and synthesize future relations with graph growing | action prediction model · 20BN-something-something; observation ratio 0.5 | accuracy (%): 22.45 -> 27.68 | Helped |
| add relation reasoning and relation synthesizing (ablation) | action prediction model · UCF101, observation ratio 0.1 | accuracy (%): 70.95 -> 82.36 | Helped |
| add future relation synthesizing (ablation) | action prediction model · UCF101, observation ratio 0.1 | accuracy (%): 78.58 -> 82.36 | Helped |
| add observed-relation reasoning (ablation) | action prediction model · UCF101, observation ratio 0.1 | accuracy (%): 76.63 -> 82.36 | Helped |
| add local graph alignment loss (ablation) | action prediction model · UCF101, observation ratio 0.1 | accuracy (%): 70.90 -> 82.36 | Helped |
| add global graph alignment loss (ablation) | action prediction model · UCF101, observation ratio 0.1 | accuracy (%): 74.90 -> 82.36 | Helped |
| use S-Matrix initialization instead of I-Matrix (ablation) | relation matrix in the spatial graph · UCF101, observation ratio 0.1 | accuracy (%): 80.05 -> 82.36 | Helped |
| use S-Matrix initialization instead of I-Matrix (ablation) | relation matrix in the spatial graph · 20BN-something-something, observation ratio 0.1 | accuracy (%): 17.16 -> 21.17 | Helped |
Closest papers by meaning
- Unsupervised Learning for Physical Interaction through Video Prediction (NeurIPS 2016 · similarity 0.89)
- PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning (ICML 2025 · similarity 0.87)
- Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs (NeurIPS 2026 · similarity 0.87)
- Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation (CVPR 2024 · similarity 0.86)
- Motion Graph Unleashed: A Novel Approach to Video Prediction (NeurIPS 2024 · similarity 0.86)
- Open-Vocabulary Video Relation Extraction (AAAI 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.