Research map / Vision-language and multimodal / Cross-modal learning
Audio-Visual Mismatch-Aware Video Retrieval via Association and Adjustment
Sangmin Lee, Sungjune Park, Yong Man Ro
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 audio association (associated audio features) (ablation) | MA-Transformer · MSR-VTT-Miech | R@1: 26.5 -> 27.8 | Improved |
| add audio association (ablation) | MA-Transformer · MSR-VTT-Miech | mAP: 40.3 -> 41.2 | Improved |
| add mismatch-aware adjustment (ablation) | MA-Transformer · MSR-VTT-Miech | R@1: 25.0 -> 27.8 | Improved |
| add mismatch-aware adjustment (ablation) | MA-Transformer · MSR-VTT-Miech | mAP: 39.1 -> 41.2 | Improved |
| add AVA-Memory associative learning using MSR-VTT (ablation) | MA-Transformer · TGIF | R@1: 10.8 -> 11.5 | Improved |
| add AVA-Memory associative learning using MSR-VTT (ablation) | MA-Transformer · TGIF | mAP: 18.5 -> 19.2 | Improved |
| MA-Transformer vs strongest prior T2VLAD | text-to-video retrieval · MSR-VTT-Original | R@1: 12.7 -> 14.7 | Improved |
| MA-Transformer vs strongest prior T2VLAD | text-to-video retrieval · MSR-VTT-Miech | R@1: 26.1 -> 27.8 | Improved |
| MA-Transformer vs HSL | text-to-video retrieval · VATEX | R@1: 36.8 -> 39.0 | Improved |
| MA-Transformer vs SEA (BERT+biGRU) on audio-free videos | text-to-video retrieval · TGIF | R@1: 11.1 -> 11.5 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- T2VLAD — T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval (CVPR 2021) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression (NeurIPS 2026 · similarity 0.88)
- Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval (CVPR 2025 · similarity 0.88)
- Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning (AAAI 2025 · similarity 0.88)
- JointAVBench: A Benchmark for Joint Audio-Visual Reasoning Evaluation (ICLR 2026 · similarity 0.87)
- From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation (ICML 2024 · similarity 0.87)
- Aligned Better, Listen Better for Audio-Visual Large Language Models (ICLR 2025 · similarity 0.86)
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.
