Guidance Module Network for Video Captioning

TL;DR

This paper introduces GMNet, a guidance module network that enhances video captioning by normalizing features and encouraging context-aware word generation, leading to improved performance on standard datasets.

Contribution

The paper proposes a novel guidance module integrated into encoder-decoder models to improve video captioning accuracy by leveraging past and future context.

Findings

GMNet outperforms baseline models on MSVD dataset

Normalization of video features improves captioning performance

Guidance module effectively incorporates contextual information

Abstract

Video captioning has been a challenging and significant task that describes the content of a video clip in a single sentence. The model of video captioning is usually an encoder-decoder. We find that the normalization of extracted video features can improve the final performance of video captioning. Encoder-decoder model is usually trained using teacher-enforced strategies to make the prediction probability of each word close to a 0-1 distribution and ignore other words. In this paper, we present a novel architecture which introduces a guidance module to encourage the encoder-decoder model to generate words related to the past and future words in a caption. Based on the normalization and guidance module, guidance module net (GMNet) is built. Experimental results on commonly used dataset MSVD show that proposed GMNet can improve the performance of the encoder-decoder model on video captioning tasks.