---
title: "Modeling Inter- and Intra-Part Deformations for Object Structure Parsing"
authors:
  - "Ling Cai"
  - "Rongrong Ji"
  - "Wei Liu"
  - "Gang Hua"
doi: ""
url: "https://ijcai.org/proceedings/2015/304"
pdf: "https://ijcai.org/proceedings/2015/0304.pdf"
venue: "Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence"
year: 2015
pages: "2148-2153"
track: "Main Track"
keywords:
---

# Modeling Inter- and Intra-Part Deformations for Object Structure Parsing

Ling Cai, Rongrong Ji, Wei Liu, Gang Hua

*Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence*, pages 2148-2153.

## Abstract

Part deformation has been a longstanding challenge for object parsing, of which the primary difficulty lies in modeling the highly diverse object structures. To this end, we propose a novel structure parsing model to capture deformable object structures. The proposed model consists of two de-formable layers: the top layer is an undirected graph that incorporates inter-part deformations to infer object structures; the base layer is consisted of various independent nodes to characterize local intra-part deformations. To learn this two-layer model, we design a layer-wise learning algorithm,which employs matching pursuit and belief propagation for a low computational complexity inference. Specifically, active basis sparse coding is leveraged to build the nodes at the base layer, while the edge weights are estimated by a structural support vector machine. Experimental results on two benchmark datasets (i.e., faces and horses) demonstrate that the proposed model yields superior parsing performance over state-of-the-art models.