Incorporating Scalability in Unsupervised Spatio-Temporal Feature Learning

2018/08/06 by Sujoy Paul, Paul, Sujoy, Sourya Roy +3
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV

paper · pdf · doi:10.48550/arxiv.1808.01727

International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2018

arxiv created 2018/08/15 · arxiv updated 2018/08/16

Abstract

Deep neural networks are efficient learning machines which leverage upon a large amount of manually labeled data for learning discriminative features. However, acquiring substantial amount of supervised data, especially for videos can be a tedious job across various computer vision tasks. This necessitates learning of visual features from videos in an unsupervised setting. In this paper, we propose a computationally simple, yet effective, framework to learn spatio-temporal feature embedding from unlabeled videos. We train a Convolutional 3D Siamese network using positive and negative pairs mined from videos under certain probabilistic assumptions. Experimental results on three datasets demonstrate that our proposed framework is able to learn weights which can be used for same as well as cross dataset and tasks.

Related

• Object-Centric Representation Learning from Unlabeled Videos
• Learning Spatiotemporal Features with 3D Convolutional Networks
• Initialization Strategies of Spatio-Temporal Convolutional Neural Networks
• Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
• A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning