From Actions to Events: A Transfer Learning Approach Using Improved Deep Belief Networks
Preprint
Abstract
In the last decade, exponential data growth supplied machine learning-based algorithms' capacity and enabled their usage in daily-life activities. Additionally, such an improvement is partially explained due to the advent of deep learning techniques, i.e., stacks of simple architectures that end up in more complex models. Although both factors produce outstanding results, they also pose drawbacks regarding the learning process as training complex models over large datasets are expensive and time-consuming. Such a problem is even more evident when dealing with video analysis. Some works have considered transfer learning or domain adaptation, i.e., approaches that map the knowledge from one domain to another, to ease the training burden, yet most of them operate over individual or small blocks of frames. This paper proposes a novel approach to map the knowledge from action recognition to event recognition using an energy-based model, denoted as Spectral Deep Belief Network. Such a model can process all frames simultaneously, carrying spatial and temporal information through the learning process. The experimental results conducted over two public video dataset, the HMDB-51 and the UCF-101, depict the effectiveness of the proposed model and its reduced computational burden when compared to traditional energy-based models, such as Restricted Boltzmann Machines and Deep Belief Networks.Keywords
All Related Versions
- Version 1, 2022-11-30, ArXiv
- Published version: , 01.
This publication has 11 references indexed in Scilit:
- Human Action Recognition and Prediction: A SurveyInternational Journal of Computer Vision, 2022
- Deep Image-to-Video Adaptation and Fusion Networks for Action RecognitionIEEE Transactions on Image Processing, 2019
- Deep-Learning Systems for Domain Adaptation in Computer Vision: Learning Transferable Feature RepresentationsIEEE Signal Processing Magazine, 2017
- Speaker recognition with hybrid features from a deep belief networkNeural Computing and Applications, 2016
- A survey of multi-source domain adaptationInformation Fusion, 2015
- High-level event recognition in unconstrained videosInternational Journal of Multimedia Information Retrieval, 2012
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002
- The recognition of human movement using temporal templatesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Task-specific gesture analysis in real-time using interpolated viewsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996