Towards Diverse Paragraph Captioning for Untrimmed Videos
This addresses the challenge of video paragraph captioning for untrimmed videos, offering a more efficient and accurate approach without needing event boundary annotations, though it is incremental as it builds on existing captioning methods.
The paper tackles the problem of generating descriptive paragraphs for untrimmed videos by proposing a model that directly generates paragraphs without relying on event detection, achieving state-of-the-art performance on accuracy and diversity metrics on ActivityNet and Charades datasets.
Video paragraph captioning aims to describe multiple events in untrimmed videos with descriptive paragraphs. Existing approaches mainly solve the problem in two steps: event detection and then event captioning. Such two-step manner makes the quality of generated paragraphs highly dependent on the accuracy of event proposal detection which is already a challenging task. In this paper, we propose a paragraph captioning model which eschews the problematic event detection stage and directly generates paragraphs for untrimmed videos. To describe coherent and diverse events, we propose to enhance the conventional temporal attention with dynamic video memories, which progressively exposes new video features and suppresses over-accessed video contents to control visual focuses of the model. In addition, a diversity-driven training strategy is proposed to improve diversity of paragraph on the language perspective. Considering that untrimmed videos generally contain massive but redundant frames, we further augment the video encoder with keyframe awareness to improve efficiency. Experimental results on the ActivityNet and Charades datasets show that our proposed model significantly outperforms the state-of-the-art performance on both accuracy and diversity metrics without using any event boundary annotations. Code will be released at https://github.com/syuqings/video-paragraph.