Submodular Attribute Selection for Visual Recognition

In real-world visual recognition problems, low-level features cannot adequately characterize the semantic content in images, or the spatio-temporal structure in videos. In this work, we encode objects or actions based on attributes that describe them as high-level concepts. We consider two types of...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on pattern analysis and machine intelligence Ročník 39; číslo 11; s. 2242 - 2255
Hlavní autoři: Zheng, Jingjing, Jiang, Zhuolin, Chellappa, Rama
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.11.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Animals
Attribute selection
Databases, Factual
Dictionaries
entropy rate
Feature recognition
Greedy algorithms
Human Activities - classification
Humans
Image Processing, Computer-Assisted - methods
Learning systems
maximum coverage function
Object recognition
Optimization
Pattern Recognition, Automated - methods
Representations
Semantics
Sports - classification
submodular optimization
Training
Videos
Visualization
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In real-world visual recognition problems, low-level features cannot adequately characterize the semantic content in images, or the spatio-temporal structure in videos. In this work, we encode objects or actions based on attributes that describe them as high-level concepts. We consider two types of attributes. One type of attributes is generated by humans, while the second type is data-driven attributes extracted from data using dictionary learning methods. Attribute-based representation may exhibit variations due to noisy and redundant attributes. We propose a discriminative and compact attribute-based representation by selecting a subset of discriminative attributes from a large attribute set. Three attribute selection criteria are proposed and formulated as a submodular optimization problem. A greedy optimization algorithm is presented and its solution is guaranteed to be at least (1-1/e)-approximation to the optimum. Experimental results on four public datasets demonstrate that the proposed attribute-based representation significantly boosts the performance of visual recognition and outperforms most recently proposed recognition approaches.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2016.2636827