Watch, Listen, And Describe: Globally And Locally Aligned Cross-modal Attentions For Video Captioning

Abstract

A major challenge for video captioning is to combine audio and visual cues. Existing multi-modal fusion methods have shown encouraging results in video understanding. However, the temporal structures of multiple modalities at different granularities are rarely explored, and how to selectively fuse the multi-modal representations at different levels of details remains uncharted. In this paper, we propose a novel hierarchically aligned cross-modal attention (HACA) framework to learn and selectively fuse both global and local temporal dynamics of different modalities. Furthermore, for the first time, we validate the superior performance of the deep audio features on the video captioning task. Finally, our HACA model significantly outperforms the previous best systems and achieves new state-of-the-art results on the widely used MSR-VTT dataset.

Stats

• citations51
• S2 citations—
• github stars0
• HF likes0
• heat score12.87
• arxiv keywang2018watch

Related papers

• Improving Audio-text Retrieval Via Hierarchical Cross-modal Interaction And Auxiliary Captions (2023)0.00
• Taming Text-to-sounding Video Generation Via Advanced Modality Condition And Interaction (2025)0.00
• Automated Audio Captioning Via Fusion Of Low- And High- Dimensional Features (2022)0.00
• Query-centric Audio-visual Cognition Network For Moment Retrieval, Segmentation And Step-captioning (2024)3.58
• Multi-modal Dense Video Captioning (2020)15.80
• Attentive Fusion Enhanced Audio-visual Encoding For Transformer Based Robust Speech Recognition (2020)0.00
• Classifier-guided Captioning Across Modalities (2025)0.00
• MM-HSD: Multi-modal Hate Speech Detection In Videos (2025)6.21