Stel component analysis: Modeling spatial correlations in image class structure

Jojić, Nebojša; Perina, Alessandro; Cristani, Marco; Murino, Vittorio; Frey, Bronwyn

doi:10.1109/cvprw.2009.5206581

Cited by 33 publications

(24 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Object segmentation Fully supervised segmentation techniques aim at separating instances of an object class from their background (e.g. horses, faces, cars [11,33,9]). They are supervised in that the training set shows images of other instances of the class along with their binary segmentations.…”

Section: Related Workmentioning

confidence: 99%

ImageNet Auto-Annotation with Segmentation Propagation

2014

View full text Add to dashboard Cite

ImageNet is a large-scale hierarchical database of object classes with millions of images. We propose to automatically populate it with pixelwise object-background segmentations, by leveraging existing manual annotations in the form of class labels and bounding-boxes. The key idea is to recursively exploit images segmented so far to guide the segmentation of new images. At each stage this propagation process expands into the images which are easiest to segment at that point in time, e.g. by moving to the semantically most related classes to those segmented so far. The propagation of segmentation occurs both (a) at the image level, by transferring existing segmentations to estimate the probability of a pixel to be foreground, and (b) at the class level, by jointly segmenting images of the same class and by importing the appearance models of classes that are already segmented. Through experiments on 577 classes and 500k images we show that our technique (i) annotates a wide range of classes with accurate segmentations; (ii) effectively exploits the hierarchical structure of ImageNet; (iii) scales efficiently, especially when implemented on superpixels; (iv) outperforms a baseline GrabCut [52] initialized on the image center, as well as segmentation transfer from a fixed source pool and run independently on each target image [37]. Moreover, our method also delivers state-of-the-art results on the recent iCoseg dataset for co-segmentation.

show abstract

Section: Related Workmentioning

confidence: 99%

ImageNet Auto-Annotation with Segmentation Propagation

2014

View full text Add to dashboard Cite

show abstract

“…Meanwhile, MSDALF is an extension of SDALF, which is a well‐known image feature for person re‐identification. While the traditional SDALF utilizes person image mask generated by Stel component analysis to calculate image features, the MSDALF estimates the person image mask by using Mask R‐CNN . These masked images of the viewpoint invariant pedestrian recognition (VIPeR) dataset are illustrated in Fig.…”

Section: Person Re‐identification Via the Smamentioning

confidence: 99%

Simultaneous image matching for person re‐identification via the stable marriage algorithm

Hashim

Kawanishi

Deguchi

et al. 2020

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Recently, multiperson tracking across non-overlapping camera views is gaining increasing attention in the video surveillance field due to its importance for public security. Most existing methods find a correspondence of person images individually across each pair of adjacent two cameras. However, in such a naive approach, redundant matching where one of the person images is selected for the matching pair for several times, often occurs. It leads to tracking failure. To overcome this problem, in this paper, by considering the matching problem as an instance of the "marriage problem" that is well known in Economics, we propose a simultaneous image matching method for multiple persons based on the stable marriage algorithm. We confirmed that the proposed method outperforms some of the existing state-of-the-art methods on several well-known public datasets.

show abstract

“…Image Segmentation. In this phase each frame is subject to a pre-processing step, which includes background subtraction ( (Stauffer and Grimson, 1999), (Zivkovic, 2004), (Jojic et al, 2009), (Renò et al, 2014), (Spagnolo et al, 2004)), human detection ( (Dalal and Triggs, 2005), (Corvee et al, 2012)) and shadow suppression ( (Lu and Zhang, 2007)), in order to discard noisy information reguarding background and shadows. Descriptor Extraction.…”

Section: Mathematical Formulation Of the Prid Task 21 Prid Taskmentioning

confidence: 99%

Exploiting Ambiguities in the Analysis of Cumulative Matching Curves for Person Re-identification

Renò

Cardellicchio

Politi

et al. 2016

Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

In this paper, a method to find, exploit and classify ambiguities in the results of a person re-identification (PRID) algorithm is presented. We start from the assumption that ambiguity is implicit in the classical formulation of the re-identification problem, as a specific individual may resemble one or more subjects by the color of dresses or the shape of the body. Therefore, we propose the introduction of the AMbiguity rAte in REidentification (AMARE) approach, which relates the results of a classical PRID pipeline on a specific dataset with their effectiveness in re-identification terms, exploiting the ambiguity rate (AR). As a consequence, the cumulative matching curves (CMC) used to show the results of a PRID algorithm will be filtered according to the AR. The proposed method gives a different interpretation of the output of PRID algorithms, because the CMC curves are processed, split and studied separately. Real experiments demonstrate that the separation of the results is really helpful in order to better understand the capabilities of a PRID algorithm.

show abstract

Stel component analysis: Modeling spatial correlations in image class structure

Abstract: As a useful concept in the study of the low level image class structure, we introduce the notion of a structure element -'stel. '

Cited by 33 publications

References 7 publications

ImageNet Auto-Annotation with Segmentation Propagation

ImageNet Auto-Annotation with Segmentation Propagation

Simultaneous image matching for person re‐identification via the stable marriage algorithm

Exploiting Ambiguities in the Analysis of Cumulative Matching Curves for Person Re-identification

Contact Info

Product

Resources

About