Attribute and simile classifiers for face verification

Kumar, Neeraj; Berg, Alexander C.; Belhumeur, Peter N.; Nayar, Shree K.

doi:10.1109/iccv.2009.5459250

Cited by 1,215 publications

(1,077 citation statements)

References 23 publications

Supporting

Mentioning

1,066

Contrasting

Unclassified

Order By: Relevance

“…Datasets We evaluate on three datasets: UT-Zap50K, as defined above, with concatenated GIST and color histogram features; the Outdoor Scene Recognition dataset [27] (OSR); and a subset of the Public Figures faces dataset [22] (PubFig). OSR contains 2,688 images (GIST features) with 6 attributes, while PubFig contains 772 images (GIST + Color features) with 11 attributes.…”

Section: Methodsmentioning

confidence: 99%

Fine-Grained Visual Comparisons with Local Learning

Grauman

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

391

297

View full text Add to dashboard Cite

Given two images, we want to predict which exhibits a particular visual attribute more than the other-even when the two images are quite similar. Existing relative attribute methods rely on global ranking functions; yet rarely will the visual cues relevant to a comparison be constant for all data, nor will humans' perception of the attribute necessarily permit a global ordering. To address these issues, we propose a local learning approach for fine-grained visual comparisons. Given a novel pair of images, we learn a local ranking model on the fly, using only analogous training comparisons. We show how to identify these analogous pairs using learned metrics. With results on three challenging datasets-including a large newly curated dataset for fine-grained comparisons-our method outperforms stateof-the-art methods for relative attribute prediction.

show abstract

Section: Methodsmentioning

confidence: 99%

Fine-Grained Visual Comparisons with Local Learning

Grauman

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

391

297

View full text Add to dashboard Cite

show abstract

“…There have been many works on classifying attributes directly from images, for facial verification [12], demography from face [10], gender estimation from face and body [18], describing faces and scenes [20], describing clothing [11] and describing texture [17]. A large portion of related research is also dedicated to recognising attributes from pedestrians and surveillance footage [29,1,21,13].…”

Section: Related Workmentioning

confidence: 99%

Soft biometric retrieval to describe and identify surveillance images

Martinho-Corbishley

Nixon

Carter

2016

2016 IEEE International Conference on Identity, Security and Behavior Analysis (ISBA)

View full text Add to dashboard Cite

Soft biometrics are human describable, distinguishing human characteristics. We present a baseline solution to the problem of identifying individuals solely from human descriptions, by automatically retrieving soft biometric labels from images. Probe images are then identified from a gallery of known soft biometric signatures, using their predicted labels. We investigate four labelling techniques and a number of challenging re-identification scenarios with this method. We also present a novel dataset, SoBiR, consisting of 8 camera viewpoints, 100 subjects and 4 forms of comprehensive human annotation to facilitate soft biometric retrieval. We report the increased retrieval accuracy of binary labels, the generalising capability of continuous measurements and the overall performance improvement of comparative annotations over categorical annotations.

show abstract

“…Some studies evaluated human performance in the task of visual concept classification. Kumar et al [12] as well as Lin et al [14] measured the human inter-coder agreement and compared experts against crowdsourcing annotators. Other papers reported the performance of humans and machine systems on some benchmark datasets.…”

Section: Human and Machine Performance In Visual And Auditory Recognimentioning

confidence: 99%

“…In the field of multimedia analysis and retrieval, human performance in recognition tasks was reported from time to time [2,9,12,13,15,16,[20][21][22][23]], but has not been evaluated in a consistent manner. As a consequence, the quality of human performance is not exactly known and estimates exist only for few recognition tasks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

“Are Machines Better Than Humans in Image Tagging?” - A User Study Adds to the Puzzle

Ewerth

Springstein

Phan-Vogtmann

et al. 2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. "Do machines perform better than humans in visual recognition tasks?" Not so long ago, this question would have been considered even somewhat provoking and the answer would have been clear: "No". In this paper, we present a comparison of human and machine performance with respect to annotation for multimedia retrieval tasks. Going beyond recent crowdsourcing studies in this respect, we also report results of two extensive user studies. In total, 23 participants were asked to annotate more than 1000 images of a benchmark dataset, which is the most comprehensive study in the field so far. Krippendorff's α is used to measure inter-coder agreement among several coders and the results are compared with the best machine results. The study is preceded by a summary of studies which compared human and machine performance in different visual and auditory recognition tasks. We discuss the results and derive a methodology in order to compare machine performance in multimedia annotation tasks at human level. This allows us to formally answer the question whether a recognition problem can be considered as solved. Finally, we are going to answer the initial question.

show abstract

Attribute and simile classifiers for face verification

Cited by 1,215 publications

References 23 publications

Fine-Grained Visual Comparisons with Local Learning

Fine-Grained Visual Comparisons with Local Learning

Soft biometric retrieval to describe and identify surveillance images

“Are Machines Better Than Humans in Image Tagging?” - A User Study Adds to the Puzzle

Contact Info

Product

Resources

About