Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection

By X. Wang, Liang Lin, Lichao Huang, Shuicheng Yan. 2013

20 citations recorded by the source corpus.

This paper proposes a reconfigurable model to recognize and detect multiclass (or multiview) objects with large variation in appearance. Compared with well acknowledged hierarchical models, we study two advanced capabilities in hierarchy for object modeling: (i)``switch'' variables(i.e. or-nodes) for specifying alternative compositions, and (ii) making local classifiers (i.e. leaf-nodes) shared among different classes. These capabilities enable us to account well for structural variabilities while preserving the model compact. Our model, in the form of an And-Or Graph, comprises four layers: a batch of leaf-nodes with collaborative edges in bottom for localizing object parts, the or-nodes over bottom to activate their children leaf-nodes, the and-nodes to classify objects as a whole, one root-node on the top for switching multiclass classification, which is also an or-node. For model training, we present an EM-type algorithm, namely dynamical structural optimization (DSO), to iteratively determine the structural configuration, (e.g., leaf-node generation associated with their parent or-nodes and shared across other classes), along with optimizing multi-layer parameters. The proposed method is valid on challenging databases, e.g., PASCAL VOC 2007 and UIUC-People, and it achieves state-of-the-arts performance.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Wangmeng Zuo
2. Luc Van Gool
3. Liang Lin
4. Ming-Hsuan Yang
5. Dacheng Tao
6. Lei Zhang
7. X. Wang
8. Xiaogang Wang

In Media Technology

1. Wangmeng Zuo
2. Liang Lin
3. X. Wang
4. M. Wang
5. Kai Zhang
6. Radu Timofte
7. Lei Zhang
8. Luc Van Gool

Citations in the corpus

• 3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks (2014, methodology): “In this work, we develop an expressive configurable human activity model to address the above mentioned issues, absorbing the powers of two promising techniques of broad interests: deep learning [13, 7, 11, 8, 34, 18, 32] and reconfigurable part-based models [41, 1, 22, 16].”