Research map / Large language models / Language, safety and interpretability
Dialog-based Interactive Image Retrieval
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 natural-language feedback instead of predefined relative attributes | Dialog-based image retrieval · Shoes, simulated users | average ranking percentile | Helped |
| use the model-based policy improvement step instead of RL-SCST (ablation) | Dialog manager · Shoes, simulated users, across dialog turns | average ranking percentile | Helped |
| train with reinforcement learning rather than triplet-loss supervised learning alone (ablation) | Dialog manager · Shoes, simulated users | average ranking percentile | Helped |
| use dialog-based natural-language retrieval rather than attribute-based WhittleSearch | Interactive footwear retrieval · Shoes, real-user five-turn dialogs | average ranking percentile: 70.3% -> 89.9% | Helped |
Closest papers by meaning
- GenIR: Generative Visual Feedback for Mental Image Retrieval (NeurIPS 2025 · similarity 0.86)
- Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms (NeurIPS 2024 · similarity 0.85)
- INQUIRE: A Natural World Text-to-Image Retrieval Benchmark (NeurIPS 2024 · similarity 0.85)
- Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval (CVPR 2025 · similarity 0.84)
- Chat-based Person Retrieval via Dialogue-Refined Cross-Modal Alignment (CVPR 2025 · similarity 0.84)
- QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval (ICML 2025 · similarity 0.84)
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.