DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns
Authors:
- Ali DibaADAli Diba
- Ali Mohammad PazandehAPAli Mohammad Pazandeh
- Hamed PirsiavashHPHamed Pirsiavash
- Luc Van GoolLGLuc Van Gool
- 1 June 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3557-3565
Abstract
The recognition of human actions and the determination of human attributes are two tasks that call for fine-grained classification. Indeed, often rather small and inconspicuous objects and features have to be detected to tell their classes apart. In order to deal with this challenge, we propose a novel convolutional neural network that mines mid-level image patches that are sufficiently dedicated to resolve the corresponding subtleties. In particular, we train a newly designed CNN (DeepPattern) that learns discriminative patch groups. There are two innovative aspects to this. On the one hand we pay attention to contextual information in an original fashion. On the other hand, we let an iteration of feature learning and patch clustering purify the set of dedicated patches that we use. We validate our method for action classification on two challenging datasets: PASCAL VOC 2012 Action and Stanford 40 Actions, and for attribute recognition we use the Berkeley Attributes of People dataset. Our discriminative mid-level mining CNN obtains state-of-the-art results on these datasets, without a need for annotations about parts and poses.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Caffe2014
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Expanded Parts Model for Human Attribute and Action Recognition in Still Images2013
- Unsupervised Discovery of Mid-Level Discriminative Patches2012
- Detecting People Using Mutually Consistent Poselet Activations2010
- Automatic Attribute Discovery and Characterization from Noisy Web Data2010
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998