Merge branch 'master' of asdf.us:megapixels_dev

41 files changed, 28 insertions, 0 deletions

diff --git a/datasets/scholar/entries/300 Faces in-the-Wild Challenge: The first facial landmark localization Challenge.csv b/datasets/scholar/entries/300 Faces in-the-Wild Challenge: The first facial landmark localization Challenge.csv
new file mode 100644
index 00000000..38f502f9
--- /dev/null
+++ b/datasets/scholar/entries/300 Faces in-the-Wild Challenge: The first facial landmark localization Challenge.csv
@@ -0,0 +1 @@
+300 faces in-the-wild challenge: The first facial landmark localization challenge|http://openaccess.thecvf.com/content_iccv_workshops_2013/W11/papers/Sagonas_300_Faces_in-the-Wild_2013_ICCV_paper.pdf|2013|396|15|7861246476672124064|http://openaccess.thecvf.com/content_iccv_workshops_2013/W11/papers/Sagonas_300_Faces_in-the-Wild_2013_ICCV_paper.pdf|http://scholar.google.com/scholar?cites=7861246476672124064&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=7861246476672124064&hl=en&as_sdt=0,5|None|Automatic facial point detection plays arguably the most important role in face analysis. Several methods have been proposed which reported their results on databases of both constrained and unconstrained conditions. Most of these databases provide annotations with different mark-ups and in some cases the are problems related to the accuracy of the fiducial points. The aforementioned issues as well as the lack of a evaluation protocol makes it difficult to compare performance between different systems. In this paper, we present the …
diff --git a/datasets/scholar/entries/Age and Gender Estimation of Unfiltered Faces.csv b/datasets/scholar/entries/Age and Gender Estimation of Unfiltered Faces.csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/Age and Gender Estimation of Unfiltered Faces.csv
diff --git a/datasets/scholar/entries/AgeDB: the first manually collected, in-the-wild age database.csv b/datasets/scholar/entries/AgeDB: the first manually collected, in-the-wild age database.csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/AgeDB: the first manually collected, in-the-wild age database.csv
diff --git a/datasets/scholar/entries/Annotated Facial Landmarks in the Wild: A Large-scale, Real-world Database for Facial Landmark Localization.csv b/datasets/scholar/entries/Annotated Facial Landmarks in the Wild: A Large-scale, Real-world Database for Facial Landmark Localization.csv
new file mode 100644
index 00000000..035e5e0f
--- /dev/null
+++ b/datasets/scholar/entries/Annotated Facial Landmarks in the Wild: A Large-scale, Real-world Database for Facial Landmark Localization.csv
@@ -0,0 +1 @@
+Annotated facial landmarks in the wild: A large-scale, real-world database for facial landmark localization|http://scholar.google.com/https://ieeexplore.ieee.org/abstract/document/6130513/|2011|402|12|2106290919498044015|None|http://scholar.google.com/scholar?cites=2106290919498044015&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=2106290919498044015&hl=en&as_sdt=0,5|None|Face alignment is a crucial step in face recognition tasks. Especially, using landmark localization for geometric face normalization has shown to be very effective, clearly improving the recognition results. However, no adequate databases exist that provide a sufficient number of annotated facial landmarks. The databases are either limited to frontal views, provide only a small number of annotated images or have been acquired under controlled conditions. Hence, we introduce a novel database overcoming these limitations …
diff --git a/datasets/scholar/entries/Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues.csv b/datasets/scholar/entries/Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues.csv
new file mode 100644
index 00000000..0b36206c
--- /dev/null
+++ b/datasets/scholar/entries/Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues.csv
@@ -0,0 +1 @@
+Beyond frontal faces: Improving person recognition using multiple cues|http://scholar.google.com/https://www.cv-foundation.org/openaccess/content_cvpr_2015/html/Zhang_Beyond_Frontal_Faces_2015_CVPR_paper.html|2015|70|13|4032136205953773331|None|http://scholar.google.com/scholar?cites=4032136205953773331&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=4032136205953773331&hl=en&as_sdt=0,5|None|We explore the task of recognizing peoples' identities in photo albums in an unconstrained setting. To facilitate this, we introduce the new People In Photo Albums (PIPA) dataset, consisting of over 60000 instances of~ 2000 individuals collected from public Flickr photo albums. With only about half of the person images containing a frontal face, the recognition task is very challenging due to the large variations in pose, clothing, camera viewpoint, image resolution and illumination. We propose the Pose Invariant PErson Recognition …
diff --git a/datasets/scholar/entries/DEX: Deep EXpectation of apparent age from a single image.csv b/datasets/scholar/entries/DEX: Deep EXpectation of apparent age from a single image.csv
new file mode 100644
index 00000000..b3728548
--- /dev/null
+++ b/datasets/scholar/entries/DEX: Deep EXpectation of apparent age from a single image.csv
@@ -0,0 +1 @@
+Dex: Deep expectation of apparent age from a single image|http://scholar.google.com/https://www.cv-foundation.org/openaccess/content_iccv_2015_workshops/w11/html/Rothe_DEX_Deep_EXpectation_ICCV_2015_paper.html|2015|155|15|12384435539194835187|None|http://scholar.google.com/scholar?cites=12384435539194835187&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=12384435539194835187&hl=en&as_sdt=0,5|None|In this paper we tackle the estimation of apparent age in still face images with deep learning. Our convolutional neural networks (CNNs) use the VGG-16 architecture and are pretrained on ImageNet for image classification. In addition, due to the limited number of apparent age annotated images, we explore the benefit of finetuning over crawled Internet face images with available age. We crawled 0.5 million images of celebrities from IMDB and Wikipedia that we make public. This is the largest public dataset for age prediction to date. We pose the …
diff --git a/datasets/scholar/entries/Deep expectation of real and apparent age from a single image without facial landmarks.csv b/datasets/scholar/entries/Deep expectation of real and apparent age from a single image without facial landmarks.csv
new file mode 100644
index 00000000..ed47fdef
--- /dev/null
+++ b/datasets/scholar/entries/Deep expectation of real and apparent age from a single image without facial landmarks.csv
@@ -0,0 +1 @@
+Deep expectation of real and apparent age from a single image without facial landmarks|http://scholar.google.com/https://link.springer.com/article/10.1007/s11263-016-0940-3|2018|135|7|11164967779616636427|None|http://scholar.google.com/scholar?cites=11164967779616636427&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=11164967779616636427&hl=en&as_sdt=0,5|None|In this paper we propose a deep learning solution to age estimation from a single face image without the use of facial landmarks and introduce the IMDB-WIKI dataset, the largest public dataset of face images with age and gender labels. If the real age estimation research spans over decades, the study of apparent age estimation or the age as perceived by other humans from a face image is a recent endeavor. We tackle both tasks with our convolutional neural networks (CNNs) of VGG-16 architecture which are pre-trained on ImageNet for …
diff --git a/datasets/scholar/entries/Distance Estimation of an Unknown Person from a Portrait .csv b/datasets/scholar/entries/Distance Estimation of an Unknown Person from a Portrait .csv
new file mode 100644
index 00000000..5cd26552
--- /dev/null
+++ b/datasets/scholar/entries/Distance Estimation of an Unknown Person from a Portrait .csv
@@ -0,0 +1 @@
+Distance estimation of an unknown person from a portrait|http://scholar.google.com/https://link.springer.com/chapter/10.1007/978-3-319-10590-1_21|2014|7|9|11199246855168438175|None|http://scholar.google.com/scholar?cites=11199246855168438175&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=11199246855168438175&hl=en&as_sdt=0,5|None|We propose the first automated method for estimating distance from frontal pictures of unknown faces. Camera calibration is not necessary, nor is the reconstruction of a 3D representation of the shape of the head. Our method is based on estimating automatically the position of face and head landmarks in the image, and then using a regressor to estimate distance from such measurements. We collected and annotated a dataset of frontal portraits of 53 individuals spanning a number of attributes (sex, age, race, hair), each …
diff --git a/datasets/scholar/entries/Distance Estimation of an Unknown Person from a Portrait.csv b/datasets/scholar/entries/Distance Estimation of an Unknown Person from a Portrait.csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/Distance Estimation of an Unknown Person from a Portrait.csv
diff --git a/datasets/scholar/entries/FDDB: A Benchmark for Face Detection in Unconstrained Settings.csv b/datasets/scholar/entries/FDDB: A Benchmark for Face Detection in Unconstrained Settings.csv
new file mode 100644
index 00000000..eeb0adb1
--- /dev/null
+++ b/datasets/scholar/entries/FDDB: A Benchmark for Face Detection in Unconstrained Settings.csv
@@ -0,0 +1 @@
+Fddb: A benchmark for face detection in unconstrained settings|http://www.cs.umass.edu/~elm/papers/fddb.pdf|2010|525|13|17267836250801810690|http://www.cs.umass.edu/~elm/papers/fddb.pdf|http://scholar.google.com/scholar?cites=17267836250801810690&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=17267836250801810690&hl=en&as_sdt=0,5|None|Despite the maturity of face detection research, it remains difficult to compare different algorithms for face detection. This is partly due to the lack of common evaluation schemes. Also, existing data sets for evaluating face detection algorithms do not capture some aspects of face appearances that are manifested in real-world scenarios. In this work, we address both of these issues. We present a new data set of face images with more faces and more accurate annotations for face regions than in previous data sets. We also propose two …
diff --git a/datasets/scholar/entries/Face Recognition in Unconstrained Videos with Matched Background Similarity.csv b/datasets/scholar/entries/Face Recognition in Unconstrained Videos with Matched Background Similarity.csv
new file mode 100644
index 00000000..2f1e41af
--- /dev/null
+++ b/datasets/scholar/entries/Face Recognition in Unconstrained Videos with Matched Background Similarity.csv
@@ -0,0 +1,2 @@
+Face recognition in unconstrained videos with matched background similarity|http://scholar.google.com/https://ieeexplore.ieee.org/abstract/document/5995566/|2011|657|10|5401801956686441353|None|http://scholar.google.com/scholar?cites=5401801956686441353&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=5401801956686441353&hl=en&as_sdt=0,5|None|Recognizing faces in unconstrained videos is a task of mounting importance. While obviously related to face recognition in still images, it has its own unique characteristics and algorithmic requirements. Over the years several methods have been suggested for this problem, and a few benchmark data sets have been assembled to facilitate its study. However, there is a sizable gap between the actual application needs and the current state of the art. In this paper we make the following contributions.(a) We present a comprehensive …
+Face Recognition in Unconstrained Videos with Matched Background Similarity|http://www.cs.tau.ac.il/thesis/thesis/Maoz.Itay-MSc.Thesis.pdf|2012|0|0|None|http://www.cs.tau.ac.il/thesis/thesis/Maoz.Itay-MSc.Thesis.pdf|None|None|None|Recognizing faces in unconstrained videos is a task of mounting importance. While obviously related to face recognition in still images, it has its own unique characteristics and algorithmic requirements. Over the years several methods have been suggested for this problem, and a few benchmark data sets have been assembled to facilitate its study. However, there is a sizable gap between the actual application needs and the current state of the art. In this work we make the following contributions:(a) We present a comprehensive …
diff --git a/datasets/scholar/entries/Face Swapping: Automatically Replacing Faces in Photographs.csv b/datasets/scholar/entries/Face Swapping: Automatically Replacing Faces in Photographs.csv
new file mode 100644
index 00000000..de202138
--- /dev/null
+++ b/datasets/scholar/entries/Face Swapping: Automatically Replacing Faces in Photographs.csv
@@ -0,0 +1 @@
+Face swapping: automatically replacing faces in photographs|http://scholar.google.com/https://dl.acm.org/citation.cfm?id=1360638|2008|228|9|8277329192835426026|None|http://scholar.google.com/scholar?cites=8277329192835426026&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=8277329192835426026&hl=en&as_sdt=0,5|None|In this paper, we present a complete system for automatic face replacement in images. Our system uses a large library of face images created automatically by downloading images from the internet, extracting faces using face detection software, and aligning each extracted face to a common coordinate system. This library is constructed off-line, once, and can be efficiently accessed during face replacement. Our replacement algorithm has three main stages. First, given an input image, we detect all faces that are present, align them to the …
diff --git a/datasets/scholar/entries/Face detection, pose estimation and landmark localization in the wild.csv b/datasets/scholar/entries/Face detection, pose estimation and landmark localization in the wild.csv
new file mode 100644
index 00000000..43da8a92
--- /dev/null
+++ b/datasets/scholar/entries/Face detection, pose estimation and landmark localization in the wild.csv
@@ -0,0 +1 @@
+Face detection, pose estimation, and landmark localization in the wild|http://scholar.google.com/https://ieeexplore.ieee.org/abstract/document/6248014/|2012|1693|7|4876235110904982186|None|http://scholar.google.com/scholar?cites=4876235110904982186&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=4876235110904982186&hl=en&as_sdt=0,5|None|We present a unified model for face detection, pose estimation, and landmark estimation in real-world, cluttered images. Our model is based on a mixtures of trees with a shared pool of parts; we model every facial landmark as a part and use global mixtures to capture topological changes due to viewpoint. We show that tree-structured models are surprisingly effective at capturing global elastic deformation, while being easy to optimize unlike dense graph structures. We present extensive results on standard face benchmarks, as well as a …
diff --git a/datasets/scholar/entries/FaceTracer: A Search Engine for Large Collections of Images with Faces.csv b/datasets/scholar/entries/FaceTracer: A Search Engine for Large Collections of Images with Faces.csv
new file mode 100644
index 00000000..a03e78e4
--- /dev/null
+++ b/datasets/scholar/entries/FaceTracer: A Search Engine for Large Collections of Images with Faces.csv
@@ -0,0 +1 @@
+Facetracer: A search engine for large collections of images with faces|http://scholar.google.com/https://link.springer.com/10.1007/978-3-540-88693-8_25|2008|324|15|10337130688446550899|None|http://scholar.google.com/scholar?cites=10337130688446550899&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=10337130688446550899&hl=en&as_sdt=0,5|None|We have created the first image search engine based entirely on faces. Using simple text queries such as “smiling men with blond hair and mustaches,” users can search through over 3.1 million faces which have been automatically labeled on the basis of several facial attributes. Faces in our database have been extracted and aligned from images downloaded from the internet using a commercial face detector, and the number of images and attributes continues to grow daily. Our classification approach uses a novel combination of Support …
diff --git a/datasets/scholar/entries/From Facial Parts Responses to Face Detection: A Deep Learning Approach.csv b/datasets/scholar/entries/From Facial Parts Responses to Face Detection: A Deep Learning Approach.csv
new file mode 100644
index 00000000..e22f032b
--- /dev/null
+++ b/datasets/scholar/entries/From Facial Parts Responses to Face Detection: A Deep Learning Approach.csv
@@ -0,0 +1 @@
+From facial parts responses to face detection: A deep learning approach|http://scholar.google.com/https://www.cv-foundation.org/openaccess/content_iccv_2015/html/Yang_From_Facial_Parts_ICCV_2015_paper.html|2015|213|12|1818335115841631894|None|http://scholar.google.com/scholar?cites=1818335115841631894&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=1818335115841631894&hl=en&as_sdt=0,5|None|In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW. Specifically, our method achieves a high recall rate of 90.99% on the challenging FDDB benchmark, outperforming the state-of-the-art method by a large margin of 2.91%. Importantly, we consider finding faces from a new perspective through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is carefully formulated considering challenging …
diff --git a/datasets/scholar/entries/From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose.csv b/datasets/scholar/entries/From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose.csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose.csv
diff --git a/datasets/scholar/entries/Gaze Locking: Passive Eye Contact Detection for Human–Object Interaction.csv b/datasets/scholar/entries/Gaze Locking: Passive Eye Contact Detection for Human–Object Interaction.csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/Gaze Locking: Passive Eye Contact Detection for Human–Object Interaction.csv
diff --git a/datasets/scholar/entries/Hipster Wars: Discovering Elements of Fashion Styles..csv b/datasets/scholar/entries/Hipster Wars: Discovering Elements of Fashion Styles..csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/Hipster Wars: Discovering Elements of Fashion Styles..csv
diff --git a/datasets/scholar/entries/Interactive Facial Feature Localization.csv b/datasets/scholar/entries/Interactive Facial Feature Localization.csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/Interactive Facial Feature Localization.csv
diff --git a/datasets/scholar/entries/Is the Eye Region More Reliable Than the Face? A Preliminary Study of Face-based Recognition on a Transgender Dataset.csv b/datasets/scholar/entries/Is the Eye Region More Reliable Than the Face? A Preliminary Study of Face-based Recognition on a Transgender Dataset.csv
new file mode 100644
index 00000000..a47bb51d
--- /dev/null
+++ b/datasets/scholar/entries/Is the Eye Region More Reliable Than the Face? A Preliminary Study of Face-based Recognition on a Transgender Dataset.csv
@@ -0,0 +1 @@
+Is the eye region more reliable than the face? A preliminary study of face-based recognition on a transgender dataset|http://scholar.google.com/https://ieeexplore.ieee.org/abstract/document/6712710/|2013|10|4|3607022377504716214|None|http://scholar.google.com/scholar?cites=3607022377504716214&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=3607022377504716214&hl=en&as_sdt=0,5|None|In this work we investigate a truly novel and extremely unique biometric problem: face-based recognition for transgender persons. A transgender person is someone who under goes a gender transformation via hormone replacement therapy; that is, a male becomes a female by suppressing natural testosterone production and exogenously increasing estrogen. Transgender hormone replacement therapy causes physical changes in the body and face. This work provides a preliminary investigation into the effects of these changes on face …
diff --git a/datasets/scholar/entries/Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments..csv b/datasets/scholar/entries/Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments..csv
new file mode 100644
index 00000000..23c90284
--- /dev/null
+++ b/datasets/scholar/entries/Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments..csv
@@ -0,0 +1 @@
+Labeled faces in the wild: A database forstudying face recognition in unconstrained environments|http://scholar.google.com/https://hal.inria.fr/inria-00321923/|2008|3014|37|6713997626354918066|None|http://scholar.google.com/scholar?cites=6713997626354918066&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=6713997626354918066&hl=en&as_sdt=0,5|None|Most face databases have been created under controlled conditions to facilitate the study of specific parameters on the face recognition problem. These parameters include such variables as position, pose, lighting, background, camera quality, and gender. While there are many applications for face recognition technology in which one can control the parameters of image acquisition, there are also many applications in which the practitioner has little or no control over such parameters. This database, Labeled Faces in the Wild, is …
diff --git a/datasets/scholar/entries/Large Age-Gap Face Verification by Feature Injection in Deep Networks.csv b/datasets/scholar/entries/Large Age-Gap Face Verification by Feature Injection in Deep Networks.csv
new file mode 100644
index 00000000..9cd388eb
--- /dev/null
+++ b/datasets/scholar/entries/Large Age-Gap Face Verification by Feature Injection in Deep Networks.csv
@@ -0,0 +1 @@
+Large age-gap face verification by feature injection in deep networks|http://scholar.google.com/https://www.sciencedirect.com/science/article/pii/S0167865517300727|2017|12|8|6980699793307007950|None|http://scholar.google.com/scholar?cites=6980699793307007950&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=6980699793307007950&hl=en&as_sdt=0,5|None|This paper introduces a new method for face verification across large age gaps and also a dataset containing variations of age in the wild, the Large Age-Gap (LAG) dataset, with images ranging from child/young to adult/old. The proposed method exploits a deep convolutional neural network (DCNN) pre-trained for the face recognition task on a large dataset and then fine-tuned for the large age-gap face verification task. Fine-tuning is performed in a Siamese architecture using a contrastive loss function. A feature injection …
diff --git a/datasets/scholar/entries/Learning Face Representation from Scratch.csv b/datasets/scholar/entries/Learning Face Representation from Scratch.csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/Learning Face Representation from Scratch.csv
diff --git a/datasets/scholar/entries/Localizing Parts of Faces Using a Consensus of Exemplars.csv b/datasets/scholar/entries/Localizing Parts of Faces Using a Consensus of Exemplars.csv
new file mode 100644
index 00000000..0fa7a800
--- /dev/null
+++ b/datasets/scholar/entries/Localizing Parts of Faces Using a Consensus of Exemplars.csv
@@ -0,0 +1 @@
+Localizing parts of faces using a consensus of exemplars|http://scholar.google.com/https://ieeexplore.ieee.org/abstract/document/6412675/|2013|740|13|8801930631236620204|None|http://scholar.google.com/scholar?cites=8801930631236620204&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=8801930631236620204&hl=en&as_sdt=0,5|None|We present a novel approach to localizing parts in images of human faces. The approach combines the output of local detectors with a nonparametric set of global models for the part locations based on over 1,000 hand-labeled exemplar images. By assuming that the global models generate the part locations as hidden variables, we derive a Bayesian objective function. This function is optimized using a consensus of models for these hidden variables. The resulting localizer handles a much wider range of expression, pose, lighting, and …
diff --git a/datasets/scholar/entries/MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition.csv b/datasets/scholar/entries/MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition.csv
new file mode 100644
index 00000000..3af655d0
--- /dev/null
+++ b/datasets/scholar/entries/MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition.csv
@@ -0,0 +1 @@
+Ms-celeb-1m: A dataset and benchmark for large-scale face recognition|http://scholar.google.com/https://link.springer.com/chapter/10.1007/978-3-319-46487-9_6|2016|189|6|7096719334274798105|None|http://scholar.google.com/scholar?cites=7096719334274798105&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=7096719334274798105&hl=en&as_sdt=0,5|None|In this paper, we design a benchmark task and provide the associated datasets for recognizing face images and link them to corresponding entity keys in a knowledge base. More specifically, we propose a benchmark task to recognize one million celebrities from their face images, by using all the possibly collected face images of this individual on the web as training data. The rich information provided by the knowledge base helps to conduct disambiguation and improve the recognition accuracy, and contributes to various real-world …
diff --git a/datasets/scholar/entries/Names and Faces .csv b/datasets/scholar/entries/Names and Faces .csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/Names and Faces .csv
diff --git a/datasets/scholar/entries/Presentation and validation of the Radboud Faces Database.csv b/datasets/scholar/entries/Presentation and validation of the Radboud Faces Database.csv
new file mode 100644
index 00000000..89746fe9
--- /dev/null
+++ b/datasets/scholar/entries/Presentation and validation of the Radboud Faces Database.csv
@@ -0,0 +1 @@
+Presentation and validation of the Radboud Faces Database|http://scholar.google.com/https://www.tandfonline.com/doi/abs/10.1080/02699930903485076|2010|1052|10|9283473996856444608|None|http://scholar.google.com/scholar?cites=9283473996856444608&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=9283473996856444608&hl=en&as_sdt=0,5|None|Many research fields concerned with the processing of information contained in human faces would benefit from face stimulus sets in which specific facial characteristics are systematically varied while other important picture characteristics are kept constant. Specifically, a face database in which displayed expressions, gaze direction, and head orientation are parametrically varied in a complete factorial design would be highly useful in many research domains. Furthermore, these stimuli should be standardised in several …
diff --git a/datasets/scholar/entries/Pruning Training Sets for Learning of Object Categories.csv b/datasets/scholar/entries/Pruning Training Sets for Learning of Object Categories.csv
new file mode 100644
index 00000000..c5540c9a
--- /dev/null
+++ b/datasets/scholar/entries/Pruning Training Sets for Learning of Object Categories.csv
@@ -0,0 +1 @@
+Pruning training sets for learning of object categories|http://scholar.google.com/https://ieeexplore.ieee.org/abstract/document/1467308/|2005|98|19|6629732990128685315|None|http://scholar.google.com/scholar?cites=6629732990128685315&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=6629732990128685315&hl=en&as_sdt=0,5|None|Training datasets for learning of object categories are often contaminated or imperfect. We explore an approach to automatically identify examples that are noisy or troublesome for learning and exclude them from the training set. The problem is relevant to learning in semi-supervised or unsupervised setting, as well as to learning when the training data is contaminated with wrongly labeled examples or when correctly labeled, but hard to learn examples, are present. We propose a fully automatic mechanism for noise cleaning …
diff --git a/datasets/scholar/entries/Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A.csv b/datasets/scholar/entries/Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A.csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A.csv
diff --git a/datasets/scholar/entries/Robust face landmark estimation under occlusion .csv b/datasets/scholar/entries/Robust face landmark estimation under occlusion .csv
new file mode 100644
index 00000000..c1245878
--- /dev/null
+++ b/datasets/scholar/entries/Robust face landmark estimation under occlusion .csv
@@ -0,0 +1 @@
+Robust face landmark estimation under occlusion|http://scholar.google.com/https://www.cv-foundation.org/openaccess/content_iccv_2013/html/Burgos-Artizzu_Robust_Face_Landmark_2013_ICCV_paper.html|2013|441|16|6035683787196907858|None|http://scholar.google.com/scholar?cites=6035683787196907858&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=6035683787196907858&hl=en&as_sdt=0,5|None|Human faces captured in real-world conditions present large variations in shape and occlusions due to differences in pose, expression, use of accessories such as sunglasses and hats and interactions with objects (eg food). Current face landmark estimation approaches struggle under such conditions since they fail to provide a principled way of handling outliers. We propose a novel method, called Robust Cascaded Pose Regression (RCPR) which reduces exposure to outliers by detecting occlusions explicitly and using …
diff --git a/datasets/scholar/entries/Spoofing Faces Using Makeup: An Investigative Study.csv b/datasets/scholar/entries/Spoofing Faces Using Makeup: An Investigative Study.csv
new file mode 100644
index 00000000..6fa46797
--- /dev/null
+++ b/datasets/scholar/entries/Spoofing Faces Using Makeup: An Investigative Study.csv
@@ -0,0 +1 @@
+Spoofing faces using makeup: An investigative study|http://scholar.google.com/https://ieeexplore.ieee.org/abstract/document/7947686/|2017|6|8|1291042674502639294|None|http://scholar.google.com/scholar?cites=1291042674502639294&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=1291042674502639294&hl=en&as_sdt=0,5|None|Makeup can be used to alter the facial appearance of a person. Previous studies have established the potential of using makeup to obfuscate the identity of an individual with respect to an automated face matcher. In this work, we analyze the potential of using makeup for spoofing an identity, where an individual attempts to impersonate another person's facial appearance. In this regard, we first assemble a set of face images downloaded from the internet where individuals use facial cosmetics to impersonate …
diff --git a/datasets/scholar/entries/Sports Videos in the Wild (SVW): A Video Dataset for Sports Analysis.csv b/datasets/scholar/entries/Sports Videos in the Wild (SVW): A Video Dataset for Sports Analysis.csv
new file mode 100644
index 00000000..a9d02e41
--- /dev/null
+++ b/datasets/scholar/entries/Sports Videos in the Wild (SVW): A Video Dataset for Sports Analysis.csv
@@ -0,0 +1 @@
+Sports videos in the wild (SVW): A video dataset for sports analysis|http://scholar.google.com/https://ieeexplore.ieee.org/abstract/document/7163105/|2015|14|11|10001086963759053928|None|http://scholar.google.com/scholar?cites=10001086963759053928&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=10001086963759053928&hl=en&as_sdt=0,5|None|Considering the enormous creation rate of usergenerated videos on websites like YouTube, there is an immediate need for automatic categorization, recognition and analysis of videos. To develop algorithms for analyzing user-generated videos, unconstrained and representative datasets are of great significance. For this purpose, we collected a dataset of Sports Videos in the Wild (SVW), consisting of videos captured by users of the leading sports training mobile app (Coach's Eye) while practicing a sport or watching a game. The dataset …
diff --git a/datasets/scholar/entries/The CMU Pose, Illumination, and Expression Database.csv b/datasets/scholar/entries/The CMU Pose, Illumination, and Expression Database.csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/The CMU Pose, Illumination, and Expression Database.csv
diff --git a/datasets/scholar/entries/The Do's and Don'ts for CNN-based Face Verification.csv b/datasets/scholar/entries/The Do's and Don'ts for CNN-based Face Verification.csv
new file mode 100644
index 00000000..d494c943
--- /dev/null
+++ b/datasets/scholar/entries/The Do's and Don'ts for CNN-based Face Verification.csv
@@ -0,0 +1 @@
+The Do's and Don'ts for CNN-based Face Verification.|http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w37/Bansal_The_Dos_and_ICCV_2017_paper.pdf|2017|21|7|16583671830808674747|http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w37/Bansal_The_Dos_and_ICCV_2017_paper.pdf|http://scholar.google.com/scholar?cites=16583671830808674747&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=16583671830808674747&hl=en&as_sdt=0,5|None|While the research community appears to have developed a consensus on the methods of acquiring annotated data, design and training of CNNs, many questions still remain to be answered. In this paper, we explore the following questions that are critical to face recognition research:(i) Can we train on still images and expect the systems to work on videos?(ii) Are deeper datasets better than wider datasets?(iii) Does adding label noise lead to improvement in performance of deep networks?(iv) Is alignment needed for face …
diff --git a/datasets/scholar/entries/The Extended Cohn-Kanade Dataset (CK+): A complete expression dataset for action unit and emotion-specified expression.csv b/datasets/scholar/entries/The Extended Cohn-Kanade Dataset (CK+): A complete expression dataset for action unit and emotion-specified expression.csv
new file mode 100644
index 00000000..399b667f
--- /dev/null
+++ b/datasets/scholar/entries/The Extended Cohn-Kanade Dataset (CK+): A complete expression dataset for action unit and emotion-specified expression.csv
@@ -0,0 +1 @@
+The extended cohn-kanade dataset (ck+) a complete expression dataset for action unit and emotion-speified expression|None|2010|3|0|13817454793240235261|None|http://scholar.google.com/scholar?cites=13817454793240235261&as_sdt=2005&sciodt=0,5&hl=en|None|None|None
diff --git a/datasets/scholar/entries/The MUCT Landmarked Face Database.csv b/datasets/scholar/entries/The MUCT Landmarked Face Database.csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/The MUCT Landmarked Face Database.csv
diff --git a/datasets/scholar/entries/The MegaFace Benchmark: 1 Million Faces for Recognition at Scale.csv b/datasets/scholar/entries/The MegaFace Benchmark: 1 Million Faces for Recognition at Scale.csv
new file mode 100644
index 00000000..68dc8389
--- /dev/null
+++ b/datasets/scholar/entries/The MegaFace Benchmark: 1 Million Faces for Recognition at Scale.csv
@@ -0,0 +1 @@
+The megaface benchmark: 1 million faces for recognition at scale|http://scholar.google.com/https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Kemelmacher-Shlizerman_The_MegaFace_Benchmark_CVPR_2016_paper.html|2016|159|11|6051410257476935491|None|http://scholar.google.com/scholar?cites=6051410257476935491&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=6051410257476935491&hl=en&as_sdt=0,5|None|Recent face recognition experiments on a major benchmark LFW show stunning performance--a number of algorithms achieve near to perfect score, surpassing human recognition rates. In this paper, we advocate evaluations at the million scale (LFW includes only 13K photos of 5K people). To this end, we have assembled the MegaFace dataset and created the first MegaFace challenge. Our dataset includes One Million photos that capture more than 690K different individuals. The challenge evaluates performance of algorithms …
diff --git a/datasets/scholar/entries/UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild.csv b/datasets/scholar/entries/UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild.csv
new file mode 100644
index 00000000..9cbf069c
--- /dev/null
+++ b/datasets/scholar/entries/UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild.csv
@@ -0,0 +1 @@
+UCF101: A dataset of 101 human actions classes from videos in the wild|http://scholar.google.com/https://arxiv.org/abs/1212.0402|2012|1211|11|10653986877352008041|None|http://scholar.google.com/scholar?cites=10653986877352008041&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=10653986877352008041&hl=en&as_sdt=0,5|None|We introduce UCF101 which is currently the largest dataset of human actions. It consists of 101 action classes, over 13k clips and 27 hours of video data. The database consists of realistic user uploaded videos containing camera motion and cluttered background. Additionally, we provide baseline action recognition results on this new dataset using standard bag of words approach with overall performance of 44.5%. To the best of our knowledge, UCF101 is currently the most challenging dataset of actions due to its large …
diff --git a/datasets/scholar/entries/UMDFaces: An Annotated Face Dataset for Training Deep Networks.csv b/datasets/scholar/entries/UMDFaces: An Annotated Face Dataset for Training Deep Networks.csv
new file mode 100644
index 00000000..adf44ba7
--- /dev/null
+++ b/datasets/scholar/entries/UMDFaces: An Annotated Face Dataset for Training Deep Networks.csv
@@ -0,0 +1 @@
+Umdfaces: An annotated face dataset for training deep networks|http://scholar.google.com/https://ieeexplore.ieee.org/abstract/document/8272731/|2017|35|5|15417824747310072694|None|http://scholar.google.com/scholar?cites=15417824747310072694&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=15417824747310072694&hl=en&as_sdt=0,5|None|Recent progress in face detection (including keypoint detection), and recognition is mainly being driven by (i) deeper convolutional neural network architectures, and (ii) larger datasets. However, most of the large datasets are maintained by private companies and are not publicly available. The academic computer vision community needs larger and more varied datasets to make further progress. In this paper, we introduce a new face dataset, called UMDFaces, which has 367,888 annotated faces of 8,277 subjects. We also introduce …
diff --git a/datasets/scholar/entries/WIDER FACE: A Face Detection Benchmark.csv b/datasets/scholar/entries/WIDER FACE: A Face Detection Benchmark.csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/WIDER FACE: A Face Detection Benchmark.csv
diff --git a/datasets/scholar/entries/Who's in the Picture .csv b/datasets/scholar/entries/Who's in the Picture .csv
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/datasets/scholar/entries/Who's in the Picture .csv