Scene-Domain Active Part Models for Object Representation

Abstract : In this paper, we are interested in enhancing the expressivity and robustness of part-based models for object representation, in the common scenario where the training data are based on 2D images. To this end, we propose scene-domain active part models (SDAPM), which reconstruct and characterize the 3D geometric statistics between object's parts in 3D scene-domain by using 2D training data in the image-domain alone. And on top of this, we explicitly model and handle occlusions in SDAPM. Together with the developed learning and inference algorithms, such a model provides rich object descriptions, including 2D object and parts localization, 3D landmark shape and camera viewpoint, which offers an effective representation to various image understanding tasks, such as object and parts detection, 3D landmark shape and viewpoint estimation from images. Experiments on the above tasks show that SDAPM outperforms previous part-based models, and thus demonstrates the potential of the proposed technique.
Document type :
Conference papers
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download

https://hal-upec-upem.archives-ouvertes.fr/hal-01578411
Contributor : Chaohui Wang <>
Submitted on : Tuesday, August 29, 2017 - 10:53:06 AM
Last modification on : Wednesday, August 7, 2019 - 12:14:40 PM

File

SceneDomainActivePartModels_IC...
Files produced by the author(s)

Identifiers

Citation

Zhou Ren, Chaohui Wang, Alan Yuille. Scene-Domain Active Part Models for Object Representation. IEEE International Conference on Computer Vision (ICCV), Dec 2015, Santiago, Chile. pp.2497 - 2505, ⟨10.1109/ICCV.2015.287⟩. ⟨hal-01578411⟩

Share

Metrics

Record views

444

Files downloads

107