Research map / Learning theory and algorithms / Matrix and tensor methods
Recognizing Emotions From Abstract Paintings Using Non-Linear Matrix Completion
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 nonlinear matrix completion instead of linear matrix completion | Emotion recognition · MART | average emotion recognition accuracy (%): 71.8 -> 72.8 | Helped |
| Use nonlinear matrix completion instead of linear matrix completion | Emotion recognition · devArt | average emotion recognition accuracy (%): 72.5 -> 76.1 | Helped |
| Use nonlinear matrix completion instead of label set propagation | Joint emotion and painting technique recognition · MART (rebalanced) | average emotion recognition accuracy: 67.19 -> 69.38 | Helped |
| Use nonlinear matrix completion instead of linear matrix completion | Joint emotion and painting technique recognition · MART (rebalanced) | average painting technique recognition accuracy: 34.69 -> 41.87 | Helped |
| Use nonlinear matrix completion instead of linear matrix completion | One-shot emotion recognition · MART | average emotion recognition accuracy: 60.27 -> 64.51 | Helped |
| Use nonlinear matrix completion instead of label set propagation | One-shot emotion recognition · MART | average emotion recognition accuracy: 53.13 -> 64.51 | Helped |
| Use nonlinear matrix completion instead of linear matrix completion | One-shot painting technique recognition · MART | average painting technique recognition accuracy: 32.81 -> 33.48 | Helped |
| Use color-combination features instead of LAB visual words or CNN features | SVM emotion recognition · MART and devArt | average emotion recognition accuracy | Helped |
Closest papers by meaning
- Retrieving and Classifying Affective Images via Deep Metric Learning (AAAI 2018 · similarity 0.83)
- APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments (NeurIPS 2024 · similarity 0.82)
- CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition (AAAI 2024 · similarity 0.82)
- Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment (AAAI 2026 · similarity 0.81)
- FindingEmo: An Image Dataset for Emotion Recognition in the Wild (NeurIPS 2024 · similarity 0.81)
- AACP: Aesthetics Assessment of Children’s Paintings Based on Self-Supervised Learning (AAAI 2024 · similarity 0.81)
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.