Research map / Vision-language and multimodal / Cross-modal learning
Integrating Both Visual and Audio Cues for Enhanced Video Caption
Wangli Hao, Zhaoxiang Zhang, He Guan
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 |
|---|---|---|---|
| Use shared-weight fusion instead of visual-only encoding | Video caption model · MSR-VTT | B@4: 0.363 -> 0.383 | Improved |
| Use shared-memory visual-audio fusion instead of visual-only encoding | Video caption model · MSR-VTT | B@4: 0.363 -> 0.375 | Improved |
| Concatenate visual and audio features after the encoder LSTMs rather than before (ablation) | Visual-audio concatenation · MSR-VTT | B@4: 0.369 -> 0.374 | Improved |
| Add shared-memory fusion rather than feature concatenation (ablation) | Video caption model · MSR-VTT | B@4: 0.374 -> 0.375 | Improved |
| Add shared-weight fusion rather than shared-memory fusion (ablation) | Video caption model · MSR-VTT | B@4: 0.375 -> 0.383 | Improved |
| Use generated audio features instead of zero-filled audio features (ablation) | Dynamic multimodal fusion · MSR-VTT | B@4: 0.354 -> 0.379 | Improved |
| Use generated audio features instead of zero-filled audio features (ablation) | Dynamic multimodal fusion · MSR-VTT | B@4: 0.338 -> 0.374 | Improved |
| Use generated audio features instead of zero-filled audio features (ablation) | Dynamic multimodal fusion · MSR-VTT | B@4: 0.343 -> 0.372 | Improved |
| Add generated audio features with shared-weight fusion | Video caption model · MSVD | B@4: 0.455 -> 0.468 | Improved |
| Pretrain the generated-audio model on MSR-VTT (ablation) | V-ShaWei-GA · MSVD | B@4: 0.468 -> 0.479 | Improved |
Closest papers by meaning
- OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning (NeurIPS 2026 · similarity 0.89)
- Aligned Better, Listen Better for Audio-Visual Large Language Models (ICLR 2025 · similarity 0.88)
- JointAVBench: A Benchmark for Joint Audio-Visual Reasoning Evaluation (ICLR 2026 · similarity 0.87)
- An eye for an ear: zero-shot audio description leveraging an image captioner with audio-visual token distribution matching (NeurIPS 2024 · similarity 0.87)
- LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos (CVPR 2025 · similarity 0.87)
- Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities (CVPR 2024 · similarity 0.87)
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.
