Learning from Videos with Deep Convolutional LSTM Networks

Abstract

This paper explores the use of convolution LSTMs to simultaneously learn spatial- and temporal-information in videos. A deep network of convolutional LSTMs allows the model to access the entire range of temporal information at all spatial scales of the data. We describe our experiments involving convolution LSTMs for lipreading that demonstrate the model is capable of selectively choosing which spatiotemporal scales are most relevant for a particular dataset. The proposed deep architecture also holds promise in other applications where spatiotemporal features play a vital role without having to specifically cater the design of the network for the particular spatiotemporal features existent within the problem. For the Lip Reading in the Wild (LRW) dataset, our model slightly outperforms the previous state of the art (83.4% vs. 83.0%) and sets the new state of the art at 85.2% when the model is pretrained on the Lip Reading Sentences (LRS2) dataset.

References in corpus (27)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Distributed Representations of Words and Phrases and their Compositionality
• Sequence to Sequence Learning with Neural Networks
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• YOLOv3: An Incremental Improvement
• Two-Stream Convolutional Networks for Action Recognition in Videos
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Language Models are Few-Shot Learners
• The Kinetics Human Action Video Dataset
• VoxCeleb2: Deep Speaker Recognition
• Recurrent Neural Network Regularization
• Unsupervised Learning of Video Representations using LSTMs
• Activation Functions: Comparison of trends in Practice and Research for Deep Learning
• YouTube-8M: A Large-Scale Video Classification Benchmark
• Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
• Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
• Deep Audio-Visual Speech Recognition
• A Short Note on the Kinetics-700-2020 Human Action Dataset
• LRS3-TED: a large-scale dataset for visual speech recognition
• Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
• Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification
• Learn to cycle: Time-consistent feature discovery for action recognition
• Omni-sourced Webly-supervised Learning for Video Recognition
• On Training Recurrent Networks with Truncated Backpropagation Through Time in Speech Recognition