Ask the dictionary: Soft-assignment location-orientation pooling for image classification

Qilong Wang; Xiaona Deng; Peihua Li; Lei Zhang

doi:10.1109/ICIP.2015.7351672

Ask the dictionary: Soft-assignment location-orientation pooling for image classification

Qilong Wang, Xiaona Deng, Peihua Li, Lei Zhang

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

2 Citations (Scopus)

Abstract

The pooling step is one of the key components of the well-known Bag-of-visual words (BoW) model widely used in image classification. In this paper, we propose a novel pooling method, which is called Soft-Assignment Location-Orientation Pooling (SALOP). Inspired by the bag of statistical sampling analysis (Bossa), SALOP also explores the effect of dictionary for pooling method, but leverages both location and orientation information between the local descriptors and the atoms of dictionary to aggregate feature codes. Moreover, different from existing pooling methods, SALOP employs a soft-assignment pooling scheme to handle ambiguity and uncertainty existing in the pooling process. The evaluation is conducted on two image benchmarks: Scene15 and PASCAL VOC 2007. The experimental results show our SALOP can achieve promising performances.

Original language	English
Title of host publication	2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
Publisher	IEEE Computer Society
Pages	4570-4574
Number of pages	5
Volume	2015-December
ISBN (Electronic)	9781479983391
DOIs	https://doi.org/10.1109/ICIP.2015.7351672
Publication status	Published - 9 Dec 2015
Event	IEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada Duration: 27 Sept 2015 → 30 Sept 2015

Conference

Conference	IEEE International Conference on Image Processing, ICIP 2015
Country/Territory	Canada
City	Quebec City
Period	27/09/15 → 30/09/15

Keywords

Bag-of-visual words
dictionary
Image classification
location-orientation pooling
soft-assignment

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

More information

10.1109/ICIP.2015.7351672

Cite this

@inproceedings{b41adfc5d4a0439093a48deda410696d,

title = "Ask the dictionary: Soft-assignment location-orientation pooling for image classification",

abstract = "The pooling step is one of the key components of the well-known Bag-of-visual words (BoW) model widely used in image classification. In this paper, we propose a novel pooling method, which is called Soft-Assignment Location-Orientation Pooling (SALOP). Inspired by the bag of statistical sampling analysis (Bossa), SALOP also explores the effect of dictionary for pooling method, but leverages both location and orientation information between the local descriptors and the atoms of dictionary to aggregate feature codes. Moreover, different from existing pooling methods, SALOP employs a soft-assignment pooling scheme to handle ambiguity and uncertainty existing in the pooling process. The evaluation is conducted on two image benchmarks: Scene15 and PASCAL VOC 2007. The experimental results show our SALOP can achieve promising performances.",

keywords = "Bag-of-visual words, dictionary, Image classification, location-orientation pooling, soft-assignment",

author = "Qilong Wang and Xiaona Deng and Peihua Li and Lei Zhang",

year = "2015",

month = dec,

day = "9",

doi = "10.1109/ICIP.2015.7351672",

language = "English",

volume = "2015-December",

pages = "4570--4574",

booktitle = "2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings",

publisher = "IEEE Computer Society",

address = "United States",

note = "IEEE International Conference on Image Processing, ICIP 2015 ; Conference date: 27-09-2015 Through 30-09-2015",

}

Wang, Q, Deng, X, Li, P & Zhang, L 2015, Ask the dictionary: Soft-assignment location-orientation pooling for image classification. in 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. vol. 2015-December, 7351672, IEEE Computer Society, pp. 4570-4574, IEEE International Conference on Image Processing, ICIP 2015, Quebec City, Canada, 27/09/15. https://doi.org/10.1109/ICIP.2015.7351672

Ask the dictionary: Soft-assignment location-orientation pooling for image classification. / Wang, Qilong; Deng, Xiaona; Li, Peihua et al.
2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. Vol. 2015-December IEEE Computer Society, 2015. p. 4570-4574 7351672.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Ask the dictionary: Soft-assignment location-orientation pooling for image classification

AU - Wang, Qilong

AU - Deng, Xiaona

AU - Li, Peihua

AU - Zhang, Lei

PY - 2015/12/9

Y1 - 2015/12/9

N2 - The pooling step is one of the key components of the well-known Bag-of-visual words (BoW) model widely used in image classification. In this paper, we propose a novel pooling method, which is called Soft-Assignment Location-Orientation Pooling (SALOP). Inspired by the bag of statistical sampling analysis (Bossa), SALOP also explores the effect of dictionary for pooling method, but leverages both location and orientation information between the local descriptors and the atoms of dictionary to aggregate feature codes. Moreover, different from existing pooling methods, SALOP employs a soft-assignment pooling scheme to handle ambiguity and uncertainty existing in the pooling process. The evaluation is conducted on two image benchmarks: Scene15 and PASCAL VOC 2007. The experimental results show our SALOP can achieve promising performances.

AB - The pooling step is one of the key components of the well-known Bag-of-visual words (BoW) model widely used in image classification. In this paper, we propose a novel pooling method, which is called Soft-Assignment Location-Orientation Pooling (SALOP). Inspired by the bag of statistical sampling analysis (Bossa), SALOP also explores the effect of dictionary for pooling method, but leverages both location and orientation information between the local descriptors and the atoms of dictionary to aggregate feature codes. Moreover, different from existing pooling methods, SALOP employs a soft-assignment pooling scheme to handle ambiguity and uncertainty existing in the pooling process. The evaluation is conducted on two image benchmarks: Scene15 and PASCAL VOC 2007. The experimental results show our SALOP can achieve promising performances.

KW - Bag-of-visual words

KW - dictionary

KW - Image classification

KW - location-orientation pooling

KW - soft-assignment

UR - http://www.scopus.com/inward/record.url?scp=84956645365&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7351672

DO - 10.1109/ICIP.2015.7351672

M3 - Conference article published in proceeding or book

VL - 2015-December

SP - 4570

EP - 4574

BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings

PB - IEEE Computer Society

T2 - IEEE International Conference on Image Processing, ICIP 2015

Y2 - 27 September 2015 through 30 September 2015

ER -

Ask the dictionary: Soft-assignment location-orientation pooling for image classification

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this