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.

arXiv commentNAACL 2018

References in corpus (8)

• ADADELTA: An Adaptive Learning Rate Method
• Microsoft COCO Captions: Data Collection and Evaluation Server
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• A Deep Reinforced Model for Abstractive Summarization
• Sequence to Sequence -- Video to Text
• Describing Videos by Exploiting Temporal Structure
• Weakly Supervised Dense Video Captioning
• Deep Multimodal Representation Learning from Temporal Data

Cited by in corpus (7)

• An Attempt towards Interpretable Audio-Visual Video Captioning
• Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing
• Multi-modal Feature Fusion with Feature Attention for VATEX Captioning Challenge 2020
• Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation
• Repetitive Activity Counting by Sight and Sound
• Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning
• Attending Category Disentangled Global Context for Image Classification