Enriching Video Captions With Contextual Text
This addresses the challenge of producing specific video captions for applications like news analysis, though it is incremental as it builds on prior captioning methods with contextual text integration.
The paper tackles the problem of generating video captions with context by infusing extracted information from relevant text data, resulting in competitive performance on the News Video Dataset and validated efficacy through ablation studies.
Understanding video content and generating caption with context is an important and challenging task. Unlike prior methods that typically attempt to generate generic video captions without context, our architecture contextualizes captioning by infusing extracted information from relevant text data. We propose an end-to-end sequence-to-sequence model which generates video captions based on visual input, and mines relevant knowledge such as names and locations from contextual text. In contrast to previous approaches, we do not preprocess the text further, and let the model directly learn to attend over it. Guided by the visual input, the model is able to copy words from the contextual text via a pointer-generator network, allowing to produce more specific video captions. We show competitive performance on the News Video Dataset and, through ablation studies, validate the efficacy of contextual video captioning as well as individual design choices in our model architecture.