Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition
| Autor: | Peng Dai, Juwei Lu, Li Wei, Niamul Quader |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Scheme (programming language)
Computer science business.industry Feature extraction 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Gesture recognition 0202 electrical engineering electronic engineering information engineering Key (cryptography) Feature (machine learning) Decomposition (computer science) 020201 artificial intelligence & image processing Artificial intelligence Focus (optics) business computer 0105 earth and related environmental sciences computer.programming_language |
| Zdroj: | Computer Vision – ECCV 2020 ISBN: 9783030585761 ECCV (30) |
| DOI: | 10.1007/978-3-030-58577-8_3 |
| Popis: | State-of-the-art approaches to video-based action and gesture recognition often employ two key concepts: First, they employ multistream processing; second, they use an ensemble of convolutional networks. We improve and extend both aspects. First, we systematically yield enhanced receptive fields for complementary feature extraction via coarse-to-fine decomposition of input imagery along the spatial and temporal dimensions, and adaptively focus on training important feature pathways using a reparameterized fully connected layer. Second, we develop a ‘use when needed’ scheme with a ‘coarse-exit’ strategy that allows selective use of expensive high-resolution processing in a data-dependent fashion to retain accuracy while reducing computation cost. Our C2F learning approach builds ensemble networks that outperform most competing methods in terms of both reduced computation cost and improved accuracy on the Something-Something V1, V2, and Jester datasets, while also remaining competitive on the Kinetics-400 dataset. Uniquely, our C2F ensemble networks can operate at varying computation budget constraints. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|