Unsupervised learning from videos using temporal coherency deep networks
نویسندگان
چکیده
منابع مشابه
Unsupervised learning from videos using temporal coherency deep networks
In this work we address the challenging problem of unsupervised learning from videos. Existing methods utilize the spatio-temporal continuity in contiguous video frames as regularization for the learning process. Typically, this temporal coherence of close frames is used as a free form of annotation, encouraging the learned representations to exhibit small differences between these frames. But ...
متن کاملUnsupervised Learning of Visual Representations using Videos
This is a review of unsupervised learning applied to videos with the aim of learning visual representations. We look at different realizations of the notion of temporal coherence across various models. We try to understand the challenges being faced, the strengths and weaknesses of different approaches and identify directions for future work. Unsupervised Learning of Visual Representations usin...
متن کاملRecognizing facial expressions from videos using Deep Belief Networks
Deep learning techniques have been shown to perform well for problems such as image classification and handwriting analysis. In this project we aim to apply these deep learning techniques to recognize facial expressions from videos. We employ sparse feature selection to improve the efficiency and accuracy of the classification [5]. We begin by considering images, and extend the algorithms to cl...
متن کاملDetecting Overlapping Communities in Social Networks using Deep Learning
In network analysis, a community is typically considered of as a group of nodes with a great density of edges among themselves and a low density of edges relative to other network parts. Detecting a community structure is important in any network analysis task, especially for revealing patterns between specified nodes. There is a variety of approaches presented in the literature for overlapping...
متن کاملUnsupervised Learning in Networks of Spiking Neurons Using Temporal Coding
We propose a mechanism for unsupervised learning in networks of spiking neurons which is based on the timing of single ring events. Our results show that a topology preserving behaviour quite similar to that of Kohonen's self-organizing map can be achieved using temporal coding. In contrast to previous approaches, which use rate coding, the winner among competing neurons can be determined fast ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computer Vision and Image Understanding
سال: 2019
ISSN: 1077-3142
DOI: 10.1016/j.cviu.2018.08.003