Video Captioning via Hierarchical Reinforcement Learning

Xin Wang, Wenhu Chen, Jiawei Wu, Yuan-Fang Wang, William Yang Wang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4213-4222


Video captioning is the task of automatically generating a textual description of the actions in a video. Although previous work (e.g. sequence-to-sequence model) has shown promising results in abstracting a coarse description of a short video, it is still very challenging to caption a video containing multiple fine-grained actions with a detailed description. This paper aims to address the challenge by proposing a novel hierarchical reinforcement learning framework for video captioning, where a high-level Manager module learns to design sub-goals and a low-level Worker module recognizes the primitive actions to fulfill the sub-goal. With this compositional framework to reinforce video captioning at different levels, our approach significantly outperforms all the baseline methods on a newly introduced large-scale dataset for fine-grained video captioning. Furthermore, our non-ensemble model has already achieved the state-of-the-art results on the widely-used MSR-VTT dataset.

Related Material

[pdf] [Supp] [arXiv]
author = {Wang, Xin and Chen, Wenhu and Wu, Jiawei and Wang, Yuan-Fang and Yang Wang, William},
title = {Video Captioning via Hierarchical Reinforcement Learning},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}