FaceTracer: A Search Engine for Large Collections of Images with Faces

By Neeraj Kumar, Peter N. Belhumeur, Shree K. Nayar. European Conference on Computer Vision, 2008

419 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d363d3343cb70ad757d472d80622e1a7c5982fd9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Feature Consistent Variational Autoencoder (2016, background): “The average of prediction accuracies of FaceTracer [14], PANDA-w [34], PANDA-l [34], and LNets+ANet [19] are 81.13, 79.85, 85.43 and 87.30 percent respectively.”
Hierarchical semantic indexing for large scale image retrieval (2011, background): “This is related to recent research in explicitly estimating high level semantic attributes for recognition [21, 22, 11, 23, 31].”
Describing Clothing by Semantic Attributes (2012, background): “One example is the FaceTracer search engine [1], which allows the user to perform face queries with a variety of descriptive facial attributes.”
From Facial Expression Recognition to Interpersonal Relation Prediction (2016, neutral): “FaceTracer [38] 89 87 82 80 93 90 94 85 90 89 91 91 PANDA-w [91] 89 82 79 77 86 87 90 82 88 92 83 93 PANDA-l [91] 92 93 84 84 93 93 93 88 94 96 93 97 Liu et al.”
The Chicago face database: A free stimulus set of faces and norming data (2015, background): “A different category of face databases has been assembled by researchers who are interested in developing facial recognition technology (e.g., Berg et al., 2004; Kumar, Belhumeur, & Nayar, 2008; Rowley, Baluja, & Kanade, 1998).”
Attribute and simile classifiers for face verification (2009, methodology): “We note that although a few are lower than [21], the images used in our system are not limited to only frontal poses (as in theirs).”
Attribute relation learning for zero-shot classification (2014, background): “search and retrieval [15–18] has been developed with promising results.”
Understanding Objects in Detail with Fine-Grained Attributes (2014, methodology): “The method of[23] uses simile attributes to characterise face instances (e.g. " a nose like Harrison Ford's " ) and [34] extend this to relative properties (e.g. " more masculine than Clive Owen " , " less natural than a forest " ).”
Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach (2017, methodology): “[26] Grayscale and color pixel values, edge magnitude, and gradient direction; One SVM classifier per attribute CelebA (public) (180K, 20K) LFW(1) (public) (n/a; 13,143) CelebA: 81% (Avg.”
Attention Branch Network: Learning of Attention Mechanism for Visual Explanation (2018, methodology): “We evaluate the accuracy rate using FaceTracer [16], PANDAl [40], LNet+ANet [42], mixed objective optimization net- work (MOON) [28], and ResNet101.”
Learning Decision Trees Recurrently Through Communication (2021, methodology): “Attributes have been used for image description [14, 6], caption generation [47], face recognition [7], image retrieval [33, 54], action recognition [67, 63], novelty detection [57] and object classification [35, 53, 42, 52, 8].”
Multi-attribute spaces: Calibration for attribute fusion and similarity search (2012, methodology): “[9] on a large data set of almost 2 million faces, highlighting the greater relevance of our matches.”
What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics (2016, background): “It has been argued (see for example the work by Loth and Iscan [59]) that there is no single skeletal feature that definitely reveals the evidence of sexual dimorphism, and that there is in fact a cross-gender metric overlap of up to 85%, which can be attributed to environmental influences and…”
A Deep Sum-Product Architecture for Robust Facial Attributes Analysis (2013, methodology): “The previous works [11, 12] evaluated their methods on the subsets of FaceTracer and PubFig, but did not release the subsets selected.”
Image ranking and retrieval based on multi-attribute queries (2011, methodology): “We next evaluate our approach on the FaceTracer Dataset [15].”
Learning Deep Representation for Face Alignment with Auxiliary Attributes (2014, methodology): “Specifically, we jointly optimize landmark detection together with the recognition of heterogeneous but subtly correlated facial attributes, such as gender, expression, and appearance attributes.”
Look at Boundary: A Boundary-Aware Face Alignment Algorithm (2018, methodology): “In the literature of face alignment, besides classic meth-ods (ASMs [34, 23], AAMs [13, 41, 33, 25], CLMs [29, 42] and Cascaded Regression Models [7, 5, 58, 8, 72, 73, 18]), recently, state-of-the-art performance has been achieved with Deep Convolutional Neural Networks (DC-NNs).”
Describable Visual Attributes for Face Verification and Image Search (2011, positive): “In contrast, we use low-level image features to first learn intermediate representations [30], [31], in which images are labeled with an extensive list of descriptive visual attributes.”
Automatic Attribute Discovery and Characterization from Noisy Web Data (2010, background): “There has been related work on using hand labeled training data to learn models for a predetermined list (either formed by hand or produced from an available application specific ontology) of attributes [2–4, 1].”