IRUS Total

Higher-order occurrence pooling for bags-of-words: visual concept detection

File Description SizeFormat 
pkpami2e-peter.pdfAccepted version1.11 MBAdobe PDFView/Open
Title: Higher-order occurrence pooling for bags-of-words: visual concept detection
Authors: Koniusz, P
Yan, F
Gosselin, P-H
Mikolajczyk, K
Item Type: Journal Article
Abstract: In object recognition, the Bag-of-Words model assumes: i) extraction of local descriptors from images, ii) embedding the descriptors by a coder to a given visual vocabulary space which results in mid-level features, iii) extracting statistics from mid-level features with a pooling operator that aggregates occurrences of visual words in images into signatures, which we refer to as First-order Occurrence Pooling. This paper investigates higher-order pooling that aggregates over co-occurrences of visual words. We derive Bag-of-Words with Higher-order Occurrence Pooling based on linearisation of Minor Polynomial Kernel, and extend this model to work with various pooling operators. This approach is then effectively used for fusion of various descriptor types. Moreover, we introduce Higher-order Occurrence Pooling performed directly on local image descriptors as well as a novel pooling operator that reduces the correlation in the image signatures. Finally, First-, Second-, and Third-order Occurrence Pooling are evaluated given various coders and pooling operators on several widely used benchmarks. The proposed methods are compared to other approaches such as Fisher Vector Encoding and demonstrate improved results.
Issue Date: 1-Feb-2017
Date of Acceptance: 1-Mar-2016
URI: http://hdl.handle.net/10044/1/39814
DOI: 10.1109/TPAMI.2016.2545667
ISSN: 0162-8828
Publisher: Institute of Electrical and Electronics Engineers
Start Page: 313
End Page: 326
Journal / Book Title: IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume: 39
Issue: 2
Copyright Statement: © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor/Funder: Engineering & Physical Science Research Council (E
Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: EP/N007743/1
Keywords: Science & Technology
Computer Science, Artificial Intelligence
Engineering, Electrical & Electronic
Computer Science
mid-level features
pooling operator
sparse coding
0801 Artificial Intelligence and Image Processing
0806 Information Systems
0906 Electrical and Electronic Engineering
Artificial Intelligence & Image Processing
Publication Status: Published
Online Publication Date: 2016-03-22
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering