Adult Image and Video Recognition by a Deep Multicontext Network and Fine-to-Coarse Strategy
| Autor: | Ping Li, Han Yu, Si Liu, Fuhao Zou, Xinyu Ou, Hefei Ling |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
021110 strategic
defence & security studies Computer science Generalization business.industry Deep learning 0211 other engineering and technologies Cognitive neuroscience of visual object recognition 02 engineering and technology Machine learning computer.software_genre Theoretical Computer Science Convolution Image (mathematics) Discriminative model Artificial Intelligence 0202 electrical engineering electronic engineering information engineering Feature (machine learning) 020201 artificial intelligence & image processing Artificial intelligence Video recognition business computer |
| Zdroj: | ACM Transactions on Intelligent Systems and Technology. 8:1-25 |
| ISSN: | 2157-6912 2157-6904 |
| DOI: | 10.1145/3057733 |
| Popis: | Adult image and video recognition is an important and challenging problem in the real world. Low-level feature cues do not produce good enough information, especially when the dataset is very large and has various data distributions. This issue raises a serious problem for conventional approaches. In this article, we tackle this problem by proposing a deep multicontext network with fine-to-coarse strategy for adult image and video recognition. We employ a deep convolution networks to model fusion features of sensitive objects in images. Global contexts and local contexts are both taken into consideration and are jointly modeled in a unified multicontext deep learning framework. To make the model more discriminative for diverse target objects, we investigate a novel hierarchical method, and a task-specific fine-to-coarse strategy is designed to make the multicontext modeling more suitable for adult object recognition. Furthermore, some recently proposed deep models are investigated. Our approach is extensively evaluated on four different datasets. One dataset is used for ablation experiments, whereas others are used for generalization experiments. Results show significant and consistent improvements over the state-of-the-art methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|