End-to-End Dense Video Captioning with Masked Transformer
arXiv:1804.00819
Abstract
Dense video captioning aims to generate text descriptions for all events in an untrimmed video. This involves both detecting and describing events. Therefore, all previous methods on dense video captioning tackle this problem by building two models, i.e. an event proposal and a captioning model, for these two sub-problems. The models are either trained separately or in alternation. This prevents direct influence of the language description to the event proposal, which is important for generating accurate descriptions. To address this problem, we propose an end-to-end transformer model for dense video captioning. The encoder encodes the video into appropriate representations. The proposal decoder decodes from the encoding with different anchors to form video event proposals. The captioning decoder employs a masking network to restrict its attention to the proposal event over the encoding feature. This masking network converts the event proposal to a differentiable mask, which ensures the consistency between the proposal and captioning during training. In addition, our model employs a self-attention mechanism, which enables the use of efficient non-recurrent structure during encoding and leads to performance improvements. We demonstrate the effectiveness of this end-to-end model on ActivityNet Captions and YouCookII datasets, where we achieved 10.12 and 6.58 METEOR score, respectively.
arXiv commentTo appear at CVPR18
References in corpus (20)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Deep Residual Learning for Image Recognition
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- A Deep Reinforced Model for Abstractive Summarization
- A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
- Image Captioning with Semantic Attention
- Towards Automatic Learning of Procedures from Web Instructional Videos
- Sequence to Sequence -- Video to Text
- Describing Videos by Exploiting Temporal Structure
- Show and Tell: A Neural Image Caption Generator
- Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs
- CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016
- Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
- Video Summarization with Long Short-term Memory
- TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
- ActivityNet Challenge 2017 Summary
- Boosting Image Captioning with Attributes
- Watch What You Just Said: Image Captioning with Text-Conditional Attention
- Video Captioning with Transferred Semantic Attributes
Cited by in corpus (14)
- Transformers in Vision: A Survey
- VideoBERT: A Joint Model for Video and Language Representation Learning
- Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interaction
- CLIP-It! Language-Guided Video Summarization
- Streamlined Dense Video Captioning
- Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning
- How to Make a BLT Sandwich? Learning to Reason towards Understanding Web Instructional Videos
- Detection and Description of Change in Visual Streams
- Video Question Generation via Cross-Modal Self-Attention Networks Learning
- Armour: Generalizable Compact Self-Attention for Vision Transformers
- 15 Keypoints Is All You Need
- Data-efficient Alignment of Multimodal Sequences by Aligning Gradient Updates and Internal Feature Distributions
- Saying the Unseen: Video Descriptions via Dialog Agents
- Multi-modal Dense Video Captioning