Image retrieval with geometry-preserving visual phrases

Zhang, Yimeng; Jia, Zhaoyin; Chen, Tsuhan

doi:10.1109/cvpr.2011.5995528

Cited by 269 publications

(197 citation statements)

References 17 publications

Supporting

Mentioning

195

Contrasting

Unclassified

Order By: Relevance

“…In fact, compared with the GVP method, phraselet achieves a noticeable gain in accuracy on all datasets, especially on the 1 M dataset, so the limited efficiency loss is worthwhile. Moreover, [5] reports a runtime of 0.248 s on Oxford 5 K+Flickr 1 M dataset, so the efficiency of visual phraselet based approach is also demonstrated.…”

Section: Scalability and Efficiencymentioning

confidence: 99%

“…Since GVP of length-2 was shown to outperform other lengths in [5], in what follows, we always refer to GVP of length-2 if not specified. Same with the common weakness of visual phrase mining algorithms, GVP method again neglects the spatial information among visual phrases.…”

Section: Visual Phraseletmentioning

confidence: 99%

“…where is the IDF weight table as derived in [5], denotes the 9 bins with highest responses, and encodes the GVP length (equals 2).…”

Section: Visual Phraseletmentioning

confidence: 99%

“…To tackle this, we propose a novel visual element, called Visual Phraselet, to describe spatially consistent sets of visual phrases. We extend the previous work [5] on mining geometry-preserving visual phrases (GVPs) and propose a simple yet effective approach to efficiently discover visual phraselets. We show that visual phraselet encodes more strict spatial information and achieves significant improvement over the baseline approach.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Visual Phraselet: Refining Spatial Constraints for Large Scale Image Search

Zheng¹,

Wang²

2013

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Abstract-The Bag-of-Words (BoW) model is prone to the deficiency of spatial constraints among visual words. The state of the art methods encode spatial information via visual phrases. However, these methods discard the spatial context among visual phrases instead. To address the problem, this letter introduces a novel visual concept, the Visual Phraselet, as a kind of similarity measurement between images. The visual phraselet refers to the spatial consistent group of visual phrases. In a simple yet effective manner, visual phraselet filters out false visual phrase matches, and is much more discriminative than both visual word and visual phrase. To boost the discovery of visual phraselets, we apply the soft quantization scheme. Our method is evaluated through extensive experiments on three benchmark datasets (Oxford 5 K, Paris 6 K and Flickr 1 M). We report significant improvements as large as 54.6% over the baseline approach, thus validating the concept of visual phraselet.Index Terms-Image search, spatial constraint, visual phrase, visual phraselet.

show abstract

Section: Scalability and Efficiencymentioning

confidence: 99%

Section: Visual Phraseletmentioning

confidence: 99%

“…where is the IDF weight table as derived in [5], denotes the 9 bins with highest responses, and encodes the GVP length (equals 2).…”

Section: Visual Phraseletmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Visual Phraselet: Refining Spatial Constraints for Large Scale Image Search

Zheng¹,

Wang²

2013

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

show abstract

“…In [36], Zhang et al present a visual phrases approach to image retrieval. It is supported by imposing geometric constraints over the different visual words in a given scene.…”

Section: Ultra-wide Baseline Matchingmentioning

confidence: 99%

Ultra-wide Baseline Aerial Imagery Matching in Urban Environments

Altwaijry

Belongie

2013

Procedings of the British Machine Vision Conference 2013

View full text Add to dashboard Cite

Correspondence matching is a core problem in computer vision. Under narrow baseline viewing conditions, this problem has been successfully addressed using SIFT-like approaches. However, under wide baseline viewing conditions these methods often fail. In this paper we propose a method for correspondence estimation that addresses this challenge for aerial scenes in urban environments. Our method creates synthetic views and leverages self-similarity cues to recover correspondences using a RANSAC-based approach aided by self-similarity graph-based sampling. We evaluate our method on 30 challenging image pairs and demonstrate improved performance to alternative methods in the literature.

show abstract

A new algorithm for product image search based on salient edge characterization

Luo

et al. 2014

Asso for Info Science & Tech

View full text Add to dashboard Cite

Visually assisted product image search has gained increasing popularity because of its capability to greatly improve end users' e‐commerce shopping experiences. Different from general‐purpose content‐based image retrieval (CBIR) applications, the specific goal of product image search is to retrieve and rank relevant products from a large‐scale product database to visually assist a user's online shopping experience. In this paper, we explore the problem of product image search through salient edge characterization and analysis, for which we propose a novel image search method coupled with an interactive user region‐of‐interest indication function. Given a product image, the proposed approach first extracts an edge map, based on which contour curves are further extracted. We then segment the extracted contours into fragments according to the detected contour corners. After that, a set of salient edge elements is extracted from each product image. Based on salient edge elements matching and similarity evaluation, the method derives a new pairwise image similarity estimate. Using the new image similarity, we can then retrieve product images. To evaluate the performance of our algorithm, we conducted 120 sessions of querying experiments on a data set comprised of around 13k product images collected from multiple, real‐world e‐commerce websites. We compared the performance of the proposed method with that of a bag‐of‐words method (Philbin, Chum, Isard, Sivic, & Zisserman, 2008) and a Pyramid Histogram of Orientated Gradients (PHOG) method (Bosch, Zisserman, & Munoz, 2007). Experimental results demonstrate that the proposed method improves the performance of example‐based product image retrieval.

show abstract

Image retrieval with geometry-preserving visual phrases

Cited by 269 publications

References 17 publications

Visual Phraselet: Refining Spatial Constraints for Large Scale Image Search

Visual Phraselet: Refining Spatial Constraints for Large Scale Image Search

Ultra-wide Baseline Aerial Imagery Matching in Urban Environments

A new algorithm for product image search based on salient edge characterization

Contact Info

Product

Resources

About