Towards Diverse Paragraph Captioning for Untrimmed Videos

Abstract

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.

arXiv commentAccepted by CVPR 2021

References in corpus (21)

• Deep Residual Learning for Image Recognition
• Image Captioning with Semantic Attention
• Neural Text Generation with Unlikelihood Training
• Sequence to Sequence -- Video to Text
• Describing Videos by Exploiting Temporal Structure
• Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs
• Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
• CIDEr: Consensus-based Image Description Evaluation
• Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning
• Reconstruction Network for Video Captioning
• Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning
• VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research
• Jointly Localizing and Describing Events for Dense Video Captioning
• Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training
• Spatio-Temporal Attention Models for Grounded Video Captioning
• Video Captioning via Hierarchical Reinforcement Learning
• End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering
• A Hierarchical Approach for Generating Descriptive Image Paragraphs
• Move Forward and Tell: A Progressive Generator of Video Descriptions
• Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation
• Grounded Video Description