Research map / Vision-language and multimodal / Human and embodied modeling
A Task-Oriented Approach for Cost-Sensitive Recognition
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 cost-sensitive feature selection rather than GREEDY MISER | Known SHUT recognition · Known SHUTs (average) | area under AP-cost curve: 15.34 -> 18.06 | Helped |
| Use cost-sensitive feature selection rather than cost-agnostic Group Lasso (ablation) | Known SHUT recognition · Known SHUTs (average) | area under AP-cost curve: 14.63 -> 18.06 | Helped |
| Combine linguistic and visual similarities to assign unseen SHUTs to clusters | ZERO SHOT · Unseen SHUTs (average) | area under AP-cost curve: 6.60 -> 7.46; 6.37 -> 7.46 | Helped |
| Ignore linguistic similarity when clustering SHUTs (ablation) | ZERO SHOT · Unseen SHUTs (average) | area under AP-cost curve: 7.46 -> 6.37 | Hurt |
| Ignore visual similarity when clustering SHUTs (ablation) | ZERO SHOT · Unseen SHUTs (average) | area under AP-cost curve: 7.46 -> 6.60 | Hurt |
| Choose a task-specific number of clusters instead of a fixed 20 clusters (ablation) | ZERO SHOT · Sitting SHUT | area under AP-cost curve | Helped |
| Transfer features from a linguistically and visually similar SHUT cluster to an unseen SHUT | ZERO SHOT · Unseen SHUTs (average) | area under AP-cost curve: 4.50 -> 7.46 | Helped |
Closest papers by meaning
- Visual Recognition by Request (CVPR 2023 · similarity 0.87)
- DesCo: Learning Object Recognition with Rich Language Descriptions (NeurIPS 2023 · similarity 0.85)
- Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization (ICML 2025 · similarity 0.83)
- Jack of All Tasks Master of Many: Designing General-Purpose Coarse-to-Fine Vision-Language Model (CVPR 2024 · similarity 0.83)
- Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation (ICLR 2026 · similarity 0.83)
- Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence (ICLR 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.