Beyond Caption To Narrative: Video Captioning With Multiple Sentences
This addresses the limitation of current video captioning methods that fail to fully utilize dynamic video content, offering a more detailed narrative approach for applications like video indexing and accessibility.
The paper tackled the problem of generating richer video captions by moving beyond single-sentence descriptions to create story-like narratives, achieving competitive results with state-of-the-art methods without relying on video-level features.
Recent advances in image captioning task have led to increasing interests in video captioning task. However, most works on video captioning are focused on generating single input of aggregated features, which hardly deviates from image captioning process and does not fully take advantage of dynamic contents present in videos. We attempt to generate video captions that convey richer contents by temporally segmenting the video with action localization, generating multiple captions from multiple frames, and connecting them with natural language processing techniques, in order to generate a story-like caption. We show that our proposed method can generate captions that are richer in contents and can compete with state-of-the-art method without explicitly using video-level features as input.