Visual concepts and compositional voting
It is very attractive to formulate vision in terms of pattern theory [26], where patterns are defined hierarchically by compositions of elementary building blocks. But applying pattern theory to real world images is very challenging and is currently less successful than discriminative methods such a...
Main Authors: | Wang, Jianyu, Zhang, Zhishuai, Xie, Cihang, Zhou, Yuyin, Premachandran, Vittal, Zhu, Jun, Xie, Lingxi, Yuille, Alan L. |
---|---|
Format: | Technical Report |
Language: | en_US |
Published: |
Center for Brains, Minds and Machines (CBMM)
2018
|
Online Access: | http://hdl.handle.net/1721.1/115182 |
Similar Items
-
DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection under Partial Occlusion
by: Zhang, Zhishuai, et al.
Published: (2018) -
Detecting Semantic Parts on Partially Occluded Objects
by: Wang, Jianyu, et al.
Published: (2018) -
Single-Shot Object Detection with Enriched Semantics
by: Zhang, Zhishuai, et al.
Published: (2018) -
Semantic Part Segmentation using Compositional Model combining Shape and Appearance
by: Wang, Jianyu, et al.
Published: (2015) -
Exploiting shape properties for improved retrieval, discrimination and recognition
by: Vittal Premachandran
Published: (2014)