Diverse Video Captioning by Adaptive Spatio-temporal Attention

TL;DR

This paper presents a novel end-to-end video captioning framework using adaptive spatio-temporal attention with transformers, achieving state-of-the-art results and diverse captions on multiple benchmarks.

Contribution

It introduces an adaptive frame selection scheme and a combined transformer architecture for improved video understanding and caption generation.

Findings

Achieves state-of-the-art results on MSVD, MSR-VTT, and VATEX datasets.

Demonstrates improved diversity and expressiveness in generated captions.

Reduces computational load with adaptive frame selection.

Abstract

To generate proper captions for videos, the inference needs to identify relevant concepts and pay attention to the spatial relationships between them as well as to the temporal development in the clip. Our end-to-end encoder-decoder video captioning framework incorporates two transformer-based architectures, an adapted transformer for a single joint spatio-temporal video analysis as well as a self-attention-based decoder for advanced text generation. Furthermore, we introduce an adaptive frame selection scheme to reduce the number of required incoming frames while maintaining the relevant content when training both transformers. Additionally, we estimate semantic concepts relevant for video captioning by aggregating all ground truth captions of each sample. Our approach achieves state-of-the-art results on the MSVD, as well as on the large-scale MSR-VTT and the VATEX benchmark datasets considering multiple Natural Language Generation (NLG) metrics. Additional evaluations on diversity scores highlight the expressiveness and diversity in the structure of our generated captions.