Research map / Vision-language and multimodal / Cross-modal learning
Sparse Maximum Margin Learning from Multimodal Human Behavioral Patterns
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 |
|---|---|---|---|
| Use a two-tier probabilistic mixture instead of a single-level mixture (ablation) | SM2-MRS · Dataset I | accuracy: 81.6 ± 3.2 -> 85.5 ± 2.8 | Helped |
| Use a two-tier probabilistic mixture instead of a single-level mixture (ablation) | SM2-MRS · Dataset II | accuracy: 71.9 ± 4.5 -> 74.2 ± 4.3 | Helped |
| Use a nested GRU instead of a first-order Markov structure (ablation) | SM2-MRS · Dataset I | accuracy: 82.5 ± 3.1 -> 85.5 ± 2.8 | Helped |
| Use a nested GRU instead of a first-order Markov structure (ablation) | SM2-MRS · Dataset II | accuracy: 70.1 ± 4.5 -> 74.2 ± 4.3 | Helped |
| Use maximum-margin classification instead of multinomial regression (ablation) | SM2-MRS · Dataset I | accuracy: 79.8 ± 3.5 -> 85.5 ± 2.8 | Helped |
| Use maximum-margin classification instead of multinomial regression (ablation) | SM2-MRS · Dataset II | accuracy: 68.1 ± 4.3 -> 74.2 ± 4.3 | Helped |
| Add sparsity regularization (ablation) | SM2-MRS · Dataset I | accuracy: 82.1 ± 2.9 -> 85.5 ± 2.8 | Helped |
| Add sparsity regularization (ablation) | SM2-MRS · Dataset II | accuracy: 72.0 ± 4.1 -> 74.2 ± 4.3 | Helped |
| Use group-wise sparse regularization instead of vanilla L1 regularization (ablation) | SM2-MRS · Dataset I | accuracy: 82.7 ± 2.5 -> 85.5 ± 2.8 | Helped |
| Use group-wise sparse regularization instead of vanilla L1 regularization (ablation) | SM2-MRS · Dataset II | accuracy: 72.5 ± 3.9 -> 74.2 ± 4.3 | Helped |
Closest papers by meaning
- Deep Temporal Sets with Evidential Reinforced Attentions for Unique Behavioral Pattern Discovery (ICML 2023 · similarity 0.85)
- Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process (NeurIPS 2025 · similarity 0.84)
- Causal Representation Learning from Multimodal Biomedical Observations (ICLR 2025 · similarity 0.84)
- PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits (ICLR 2026 · similarity 0.83)
- Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning (ICLR 2024 · similarity 0.83)
- Distribution Matching for Multi-Task Learning of Classification Tasks: A Large-Scale Study on Faces & Beyond (AAAI 2024 · similarity 0.83)
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.