Research map / Video / Video-language understanding
A Proposal-Based Approach for Activity Image-to-Video 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 |
|---|---|---|---|
| add triplet loss (ablation) | APIVR · THUMOS'14 | mAP@10: 0.3228 -> 0.3812 | Helped |
| add adversarial loss (ablation) | APIVR · THUMOS'14 | mAP@10: 0.3278 -> 0.3812 | Helped |
| add classification loss (ablation) | APIVR · THUMOS'14 | mAP@10: 0.2438 -> 0.3812 | Helped |
| use geometry-aware point-to-subspace distance instead of weighted-average feature distance (ablation) | APIVR · THUMOS'14 | mAP@10: 0.3531 -> 0.3812 | Helped |
| learn proposal weights with GMIL instead of assigning uniform weights (ablation) | APIVR · THUMOS'14 | mAP@10: 0.3428 -> 0.3812 | Helped |
| add graph convolution to MIL (ablation) | APIVR · THUMOS'14 | mAP@10: 0.3618 -> 0.3812 | Helped |
| truncate the proposal bag to the top 50 GMIL-weighted proposals rather than using the intact bag or too few proposals (ablation) | APIVR geometry-aware triplet loss · THUMOS'14 | mAP | Mixed |
Closest papers by meaning
- MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence (NeurIPS 2025 · similarity 0.84)
- From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos (NeurIPS 2025 · similarity 0.83)
- CoVR: Learning Composed Video Retrieval from Web Video Captions (AAAI 2024 · similarity 0.82)
- Learning to Predict Activity Progress by Self-Supervised Video Alignment (CVPR 2024 · similarity 0.82)
- AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding (NeurIPS 2025 · similarity 0.82)
- VVS: Video-to-Video Retrieval with Irrelevant Frame Suppression (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.