English

SBAT: Video Captioning with Sparse Boundary-Aware Transformer

Computer Vision and Pattern Recognition 2020-07-24 v1 Computation and Language Machine Learning Multimedia

Abstract

In this paper, we focus on the problem of applying the transformer structure to video captioning effectively. The vanilla transformer is proposed for uni-modal language generation task such as machine translation. However, video captioning is a multimodal learning problem, and the video features have much redundancy between different time steps. Based on these concerns, we propose a novel method called sparse boundary-aware transformer (SBAT) to reduce the redundancy in video representation. SBAT employs boundary-aware pooling operation for scores from multihead attention and selects diverse features from different scenarios. Also, SBAT includes a local correlation scheme to compensate for the local information loss brought by sparse operation. Based on SBAT, we further propose an aligned cross-modal encoding scheme to boost the multimodal interaction. Experimental results on two benchmark datasets show that SBAT outperforms the state-of-the-art methods under most of the metrics.

Keywords

Cite

@article{arxiv.2007.11888,
  title  = {SBAT: Video Captioning with Sparse Boundary-Aware Transformer},
  author = {Tao Jin and Siyu Huang and Ming Chen and Yingming Li and Zhongfei Zhang},
  journal= {arXiv preprint arXiv:2007.11888},
  year   = {2020}
}

Comments

Appearing at IJCAI 2020

R2 v1 2026-06-23T17:20:30.579Z