AI Paper Atlas

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

AAAI 2018 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual speech separation · 41 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use shared-weight fusion instead of visual-only encodingVideo caption model · MSR-VTTB@4: 0.363 -> 0.383Improved
Use shared-memory visual-audio fusion instead of visual-only encodingVideo caption model · MSR-VTTB@4: 0.363 -> 0.375Improved
Concatenate visual and audio features after the encoder LSTMs rather than before (ablation)Visual-audio concatenation · MSR-VTTB@4: 0.369 -> 0.374Improved
Add shared-memory fusion rather than feature concatenation (ablation)Video caption model · MSR-VTTB@4: 0.374 -> 0.375Improved
Add shared-weight fusion rather than shared-memory fusion (ablation)Video caption model · MSR-VTTB@4: 0.375 -> 0.383Improved
Use generated audio features instead of zero-filled audio features (ablation)Dynamic multimodal fusion · MSR-VTTB@4: 0.354 -> 0.379Improved
Use generated audio features instead of zero-filled audio features (ablation)Dynamic multimodal fusion · MSR-VTTB@4: 0.338 -> 0.374Improved
Use generated audio features instead of zero-filled audio features (ablation)Dynamic multimodal fusion · MSR-VTTB@4: 0.343 -> 0.372Improved
Add generated audio features with shared-weight fusionVideo caption model · MSVDB@4: 0.455 -> 0.468Improved
Pretrain the generated-audio model on MSR-VTT (ablation)V-ShaWei-GA · MSVDB@4: 0.468 -> 0.479Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy