Reconstruction Network for Video Captioning
This addresses the problem of generating natural language descriptions from videos for applications like accessibility or video search, but it is incremental as it builds on existing encoder-decoder models.
The paper tackles video captioning by proposing a reconstruction network (RecNet) with an encoder-decoder-reconstructor architecture that uses both forward (video to sentence) and backward (sentence to video) flows, resulting in significant gains in caption accuracy on benchmark datasets.
In this paper, the problem of describing visual contents of a video sequence with natural language is addressed. Unlike previous video captioning work mainly exploiting the cues of video contents to make a language description, we propose a reconstruction network (RecNet) with a novel encoder-decoder-reconstructor architecture, which leverages both the forward (video to sentence) and backward (sentence to video) flows for video captioning. Specifically, the encoder-decoder makes use of the forward flow to produce the sentence description based on the encoded video semantic features. Two types of reconstructors are customized to employ the backward flow and reproduce the video features based on the hidden state sequence generated by the decoder. The generation loss yielded by the encoder-decoder and the reconstruction loss introduced by the reconstructor are jointly drawn into training the proposed RecNet in an end-to-end fashion. Experimental results on benchmark datasets demonstrate that the proposed reconstructor can boost the encoder-decoder models and leads to significant gains in video caption accuracy.