Controllable Video Captioning with POS Sequence Guidance Based on Gated Fusion Network

TL;DR

This paper introduces a novel gated fusion network that incorporates POS sequence guidance to control and improve the quality and diversity of video captioning, demonstrated on benchmark datasets.

Contribution

The paper presents a new gated fusion network with cross-gating blocks and a POS sequence generator to guide caption syntax, enhancing performance and controllability.

Findings

Improved captioning accuracy on MSR-VTT and MSVD datasets.

Enhanced syntactic control and diversity in generated captions.

Effective fusion of motion and content features through cross-gating.

Abstract

In this paper, we propose to guide the video caption generation with Part-of-Speech (POS) information, based on a gated fusion of multiple representations of input videos. We construct a novel gated fusion network, with one particularly designed cross-gating (CG) block, to effectively encode and fuse different types of representations, e.g., the motion and content features of an input video. One POS sequence generator relies on this fused representation to predict the global syntactic structure, which is thereafter leveraged to guide the video captioning generation and control the syntax of the generated sentence. Specifically, a gating strategy is proposed to dynamically and adaptively incorporate the global syntactic POS information into the decoder for generating each word. Experimental results on two benchmark datasets, namely MSR-VTT and MSVD, demonstrate that the proposed model can well exploit complementary information from multiple representations, resulting in improved performances. Moreover, the generated global POS information can well capture the global syntactic structure of the sentence, and thus be exploited to control the syntactic structure of the description. Such POS information not only boosts the video captioning performance but also improves the diversity of the generated captions. Our code is at: https://github.com/vsislab/Controllable_XGating.