Attention is all you need for Videos: Self-attention based Video Summarization using Universal Transformers

Abstract

Video Captioning and Summarization have become very popular in the recent years due to advancements in Sequence Modelling, with the resurgence of Long-Short Term Memory networks (LSTMs) and introduction of Gated Recurrent Units (GRUs). Existing architectures extract spatio-temporal features using CNNs and utilize either GRUs or LSTMs to model dependencies with soft attention layers. These attention layers do help in attending to the most prominent features and improve upon the recurrent units, however, these models suffer from the inherent drawbacks of the recurrent units themselves. The introduction of the Transformer model has driven the Sequence Modelling field into a new direction. In this project, we implement a Transformer-based model for Video captioning, utilizing 3D CNN architectures like C3D and Two-stream I3D for video extraction. We also apply certain dimensionality reduction techniques so as to keep the overall size of the model within limits. We finally present our results on the MSVD and ActivityNet datasets for Single and Dense video captioning tasks respectively.

arXiv comment15 pages, 10 figures

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• The Kinetics Human Action Video Dataset
• Universal Transformers
• Adaptive Computation Time for Recurrent Neural Networks
• Towards Automatic Learning of Procedures from Web Instructional Videos
• Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks

Cited by in corpus (4)

• A Survey on Visual Transformer
• Reconstructive Sequence-Graph Network for Video Summarization
• Why an Android App is Classified as Malware? Towards Malware Classification Interpretation
• A Comprehensive Review on Recent Methods and Challenges of Video Description