Query-adaptive late fusion for image search and person re-identification

Abstract-In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT-based and CNN-based methods, are presented. For the former, according to the codebook size, we organize the literature into using large/medium-sized/small codebooks. For the latter, we discuss three lines of methods, i.e., using pre-trained or fine-tuned CNN models, and hybrid methods. The first two perform a single-pass of an image to the network, while the last category employs a patch-based feature extraction scheme. This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. After analyzing and comparing retrieval performance of different categories on several datasets, we discuss promising directions towards generic and specialized instance retrieval.

show abstract

“…It is also shown in [31], [86] that using AKM [12] for clustering also yields very competitive retrieval accuracy.…”

Section: Codebook Generation and Quantizationmentioning

confidence: 95%

SIFT Meets CNN: A Decade Survey of Instance Retrieval

Zheng

Yang

Tian

2018

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

611

309

View full text Add to dashboard Cite

show abstract

“…The authors used Gabor and Schmid filters on the luminance channel for texture features. In [33], the authors used local features and proposed an unsupervised method for determining feature weight for fusion. Local descriptors of pixels are transferred into Fisher Vectors to represent images in [22].…”

Section: Related Workmentioning

confidence: 99%

“…In order to verify the effectiveness of the proposed re-ranking method, we select 4 state-of-the-art person reidentification methods: SDALF [6], MidFilter [32], Query Adaptive late Fusion (QAF) [33], and SDC knn [30] for experiments. Given initially ranked lists returned by those methods, we then apply the proposed re-ranking method to the lists.…”

Section: Experimental Settingsmentioning

confidence: 99%

“…Salient patches are then used to learn a human salient descriptor for images in an unsupervised manner. QAF [33] The authors focus on estimating weights for different features adaptively with each query or probe image. More specifically, based on the shape of the score list of each feature type when querying, the method can estimate the effect of the feature, determining its weight for fusion.…”

Section: Experimental Settingsmentioning

confidence: 99%

“…In [23], only one person re-identification method, SDALF [6], is evaluated on VIPeR [10]. In this work, we extensively consider four state-of-the-art person re-identification methods including SDALF [6], QAF [33], Mid-level filter [32], and SDC knn [30]. These methods were evaluated on three different benchmark datasets: VIPeR [10], ETHZ [5,26], and CUHK01 [15].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Person re-identification with mutual re-ranking

Nguyen

Ngo

et al. 2017

Vietnam J Comput Sci

View full text Add to dashboard Cite

Person re-identification is the problem of identifying people moving across cameras. Traditional approaches deal with this problem by pair-wise matching images recorded from two different cameras. A person in the second camera is identified by comparing his image with images in the first camera, independently of other persons in the second camera. In reality, there are many situations in which multiple persons appear concurrently in the second camera. In this paper, we propose a method for postprocessing re-identification results. The idea is to utilize information of co-occurrence persons for comparing and re-arranging given ranked lists. Experiments conducted on different datasets with several state-of-the-art methods have shown the effectiveness of our post-processing method in improving re-identification accuracy.

show abstract