Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization
This work addresses the problem of generating descriptive captions for untrimmed videos, which is incremental as it builds on existing captioning methods with a novel summarization approach.
The paper tackles dense video captioning by proposing a division-and-summarization framework that partitions videos into event proposals, generates sentences for segments, and summarizes them into a single descriptive sentence using a two-stage LSTM with hierarchical attention, achieving effectiveness on the ActivityNet Captions dataset.
In this work, we propose a division-and-summarization (DaS) framework for dense video captioning. After partitioning each untrimmed long video as multiple event proposals, where each event proposal consists of a set of short video segments, we extract visual feature (e.g., C3D feature) from each segment and use the existing image/video captioning approach to generate one sentence description for this segment. Considering that the generated sentences contain rich semantic descriptions about the whole event proposal, we formulate the dense video captioning task as a visual cue aided sentence summarization problem and propose a new two stage Long Short Term Memory (LSTM) approach equipped with a new hierarchical attention mechanism to summarize all generated sentences as one descriptive sentence with the aid of visual features. Specifically, the first-stage LSTM network takes all semantic words from the generated sentences and the visual features from all segments within one event proposal as the input, and acts as the encoder to effectively summarize both semantic and visual information related to this event proposal. The second-stage LSTM network takes the output from the first-stage LSTM network and the visual features from all video segments within one event proposal as the input, and acts as the decoder to generate one descriptive sentence for this event proposal. Our comprehensive experiments on the ActivityNet Captions dataset demonstrate the effectiveness of our newly proposed DaS framework for dense video captioning.