Guidance Module Network for Video Captioning
This work provides an incremental improvement for video captioning models, which benefits researchers and developers working on automatic video content description.
This paper addresses video captioning by proposing the Guidance Module Network (GMNet), which incorporates feature normalization and a guidance module to encourage the generation of contextually relevant words. On the MSVD dataset, GMNet improves the performance of the encoder-decoder model for video captioning.
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.