Research map / Vision-language and multimodal / Human and embodied modeling
Deep Temporal Sets with Evidential Reinforced Attentions for Unique Behavioral Pattern Discovery
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 |
|---|---|---|---|
| add evidential reinforced attention (ERA) to DTS (ablation) | DTS · Maze-Mixed | accuracy: 92.7 to 95.0 | Helped |
| add evidential reinforced attention (ERA) to DTS (ablation) | DTS · Maze-2D | accuracy: 93.1 to 94.0 | Helped |
| replace RL-based ERA with standard ANP attention on DTS (ablation) | DTS · Maze-Mixed | accuracy: 95.0 to 91.8 | Hurt |
| use only ERA-selected attentive embedding without concatenating full DTS embedding (ablation) | DTS-ERA · Maze-Mixed | accuracy: 95.0 to 92.4 | Hurt |
| use DTS set-based encoder instead of LSTM recurrent encoder | LSTM baseline · Maze-Mixed | accuracy: 68.8 to 92.7 | Helped |
| add evidential reinforced attention on top of DTS (DTS-ERA) vs baselines | DTS-ERA · Coloring | accuracy: 91.0 vs 88.0 (best baseline GRU-FCN) | Helped |
Closest papers by meaning
- AXON: Action Characterization Through Cross-Modal Knowledge Distillation for Neurodiverse Individuals (AAAI 2026 · similarity 0.85)
- Understanding Unique Behavioral Patterns through Multimodal Analysis of Eye-Hand Coordination in Autistic Children (Student Abstract) (AAAI 2025 · similarity 0.85)
- Human Behavior Atlas: Benchmarking Unified Psychological And Social Behavior Understanding (ICLR 2026 · similarity 0.85)
- Sparse Maximum Margin Learning from Multimodal Human Behavioral Patterns (AAAI 2023 · similarity 0.85)
- Causal Explanation of Quality of Parent-Child Interactions with Multimodal Behavioral Features (Student Abstract) (AAAI 2025 · similarity 0.82)
- MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series (NeurIPS 2025 · similarity 0.82)
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.