Joint Cascade Face Detection and Alignment

By Dong Chen, Shaoqing Ren, Yichen Wei, Xudong Cao. 2014

410 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

FaceNet: A unified embedding for face recognition and clustering (2015, methodology): “A proprietary face detector (similar to Picasa [3]) is run on the provided LFW thumbnails.”
Face X-Ray for More General Face Forgery Detection (2019, methodology): “We use the face landmarks (extracted by [9]) as the matching criteria to search from a random subset of the rest training videos according to the Euclidean distance between landmarks.”
Image based Static Facial Expression Recognition with Multiple Deep Network Learning (2015, background): “In particular, Tang [34] reported a deep CNN jointly learned with a linear support vector machine (SVM) output.”
MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation (2017, methodology): “Following prior work on face [62], [67] and gaze [41], [68] analysis, we use a grey-scale single channel image as input with a resolution of 60 36 pixels.”
An All-In-One Convolutional Neural Network for Face Analysis (2016, methodology): “It has been shown recently that jointly learning correlated tasks can boost the performance of individual tasks [59], [36], [5].”
HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition (2019, methodology): “Some of the recent published methods compared in our evaluations include DP2MFD [42], Faceness [60], HeadHunter [39], JointCascade [6], CCF [59], SquaresChnFtrs-”
Convolutional Channel Features (2015, methodology): “JointCascade uses facial landmark annotations and adopts an additional post classifier to largely eliminate false positives, which are both orthogonal to our work.”
Neural Aggregation Network for Video Face Recognition (2016, methodology): “The faces are detected using the JDA method[2], and aligned with the LBR method [22].”
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).”
Multi-scale Fully Convolutional Network for Face Detection in the Wild (2017, methodology): “[35], ACF-multiscale [39], HeadHunter [23], Joint Cascade [4], SURF-multiview [19] and Zhu et al.”
Face Detection using Deep Learning: An Improved Faster RCNN Approach (2017, background): “Along with the popularity of deep learning in computer vision, a surge of research attention has been emerging to explore deep learning for resolving face detection tasks.”
A survey on face detection in the wild: Past, present and future (2015, methodology): “Other notable parts-based methods include [49] [50] [51].”
Video-Based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms (2021, methodology): “First, compared with the other two methods, JCFDA [113] provides the best recognition rate of 38.”
FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping (2019, methodology): “Implementation Detail : For each face image, we ﬁrst align and crop the face using ﬁve point landmarks extracted with [11], the cropped image is of size 256 × 256 covering the whole face, as well as some background regions.”
Face Detection with the Faster R-CNN (2016, background): “[3] demonstrate better face detection performance with a joint cascade for face detection and alignment, where shape-index features are used.”
Deep Facial Expression Recognition: A Survey (2018, neutral): “[44] concatenate three detectors (JDA detector [45], DCNN detector [46] and MoT detector [36]) to complement each other.”
CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training (2017, methodology): “For the FaceScrub dataset, we first detect the facial region with the JDA face detector [3], and then locate five facial landmarks (two eyes, nose tip and two mouth corners) with SDM [45].”
FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single Image (2019, background): “Recent work [7, 31, 49] demonstrates that learning related tasks jointly achieves better results than performing individual tasks independently.”