Dual many-to-one-encoder-based transfer learning for cross-dataset human action recognition
| Autor: | Tiantian Xu, Edward K. Wong, Yi Fang, Fan Zhu |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Computer science
Property (programming) business.industry Feature vector Feature extraction 02 engineering and technology Machine learning computer.software_genre ComputingMethodologies_PATTERNRECOGNITION Action (philosophy) 020204 information systems Signal Processing 0202 electrical engineering electronic engineering information engineering Benchmark (computing) Feature (machine learning) 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence Transfer of learning business Encoder computer |
| Zdroj: | Image and Vision Computing. 55:127-137 |
| ISSN: | 0262-8856 |
| DOI: | 10.1016/j.imavis.2016.01.001 |
| Popis: | The emergence of large-scale human action datasets poses a challenge to efficient action labeling. Hand labeling large-scale datasets is tedious and time consuming; thus a more efficient labeling method would be beneficial. One possible solution is to make use of the knowledge of a known dataset to aid the labeling of a new dataset. To this end, we propose a new transfer learning method for cross-dataset human action recognition. Our method aims at learning generalized feature representation for effective cross-dataset classification. We propose a novel dual many-to-one encoder architecture to extract generalized features by mapping raw features from source and target datasets to the same feature space. Benefiting from the favorable property of the proposed many-to-one encoder, cross-dataset action data are encouraged to possess identical encoded features if the actions share the same class labels. Experiments on pairs of benchmark human action datasets achieved state-of-the-art accuracy, proving the efficacy of the proposed method. Display Omitted Proposed a new transfer-learning method for cross-dataset action recognition.A new dual many-to-one encoder method for feature extraction across action datasets.Achieved over 10% increase in recognition accuracy over recent work. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect