Face tracking and recognition with visual constraints in real-world videos

By Minyoung Kim, Sanjiv Kumar, Vladimir I. Pavlovic, Henry A. Rowley. 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008

517 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fa2f1ae7e37e7a98b83242b125280f080bc53dde

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

Manifold Discriminant Analysis (2009, methodology): “For face recognition task, three datasets are considered: Honda/UCSD [16], CMU MoBo [10], and YouTube Celebrities [14], to ensure extensive evaluations of different methods.”
Incremental Face Alignment in the Wild (2014, methodology): “For this experiment, we use the extremely challenging Youtube Celebrities database [16] which contains videos of celebrities captured in the wild.”
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors (2018, background): “Following [13], we report the results for the 49 inner points on subset A and C. YouTube Celebrities [14].”
Unconstrained Face Recognition: Identifying a Person of Interest From a Media Collection (2014, unknown): “[16]”
Projection Metric Learning on Grassmann Manifold with Application to Video based Face Recognition (2015, methodology): “We used YouTube Celebrities (YTC) [26] for video based face identification, YouTube Face (YTF) [40] and Point-and-Shoot Face Recognition Challenge (PaSC) [3] for video based face verification task.”
A Comprehensive Look at Coding Techniques on Riemannian Manifolds (2018, methodology): “RECOGNITION ACCURACIES IN % FOR THE MARYLAND [30], DYNTEX++ [12], AND YTC [23] DATA SETS”
Learning Where to Attend with Deep Architectures for Image Tracking (2011, methodology): “In our second experiment we use the Youtube celebrity dataset from Kim et al. (2008).”
Deep Face Recognition: A Survey (2018, unknown): “r and 3D pose YTF [171] 2011 3,425 1,595 48/181.3/6,070 1:1: Acc 97.30% Acc [115]; 96.52% Acc [124] video (IV-B) PaSC [11] 2013 2,802 265 – 1:1: VR vs. FAR (ROC) 95.67%@10−2FAR [124] video (IV-B) YTC [82] 2008 1,910 47 – 1:N: Rank-N (CMC) 97.82% Rank-1 [124]; 97.32% Rank-1 [123] video (IV-B) CALFW [”
Deep Reconstruction Models for Image Set Classification (2015, background): “Index Terms—Image set classification, deep learning, auto-encoders, video based face recognition, object recognition Ç”
The First Facial Landmark Tracking in-the-Wild Challenge: Benchmark and Results (2015, background): “Rigid and non-rigid tracking of faces and facial features has been a very popular topic of research over the past twenty years [21, 29, 20, 17, 25, 37, 43, 23, 61, 19, 49, 14, 31, 34, 62, 63, 64, 10, 32, 40, 51, 39, 50, 35, 24, 26, 53, 56, 57, 54].”
3D Face Pose Tracking using Low Quality Depth Cameras (2013, background): “3D face pose tracking is becoming an important task for many research domains in computer vision like Human-Computer Interaction and face analysis (Weise et al., 2011; Cai et al., 2010; Maurel et al., 2008) and recognition (Kim et al., 2008).”
Supervised Descent Method and Its Applications to Face Alignment (2013, methodology): “We show how SDM improves state-of-the-art performance for facial feature detection in two “face in the wild” databases [26, 4] and demonstrate extremely good performance tracking faces in the YouTube celebrity database [20].”
Attention-Aware Deep Reinforcement Learning for Video Face Recognition (2017, methodology): “We used the the YouTube Celebrities (YTC) dataset to evaluate the performance of our methods on the video face classification task.”
Zero-effort payments: design, deployment, and lessons (2014, background): “One project evaluated the accuracy of recognizing a set of 35 celebrities in videos stored on YouTube; it reported a 60–70% accuracy rate depending on the algorithm used [12].”
Multi-manifold deep metric learning for image set classification (2015, methodology): “The YTC dataset [15] contains 1910 face video sequences of 47 different persons, who are celebrities such as actors, actresses and politicians.”
Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set Classification (2015, methodology): “To more clearly understand the resulting SPD feature, we take the YTC dataset for example.”
Covariance discriminative learning: A natural and efficient approach to image set classification (2012, methodology): “Among previous work, there is a category of video-based classification methods [11], [14], which focus on utilizing the temporal dynamic information between consecutive video frames.”
MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization (2014, methodology): “Some other methods address the drift problem by incorporating the original template in the updates [20], or by leveraging additional knowledge about the target [15,9].”
S^3FD: Single Shot Scale-Invariant Face Detector (2017, background): “Face detection is the key step of many subsequent face-related applications, such as face alignment [50, 61], face recognition [32, 40, 62], face veriﬁcation [44, 46] and face tracking [17], etc.”