High-Performance Rotation Invariant Multiview Face Detection

By Chang Huang, Haizhou Ai, Yuan Li, Shihong Lao. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007

389 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7f0198ae468cb50eadbdbf7e9f45f7f74464434e

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

Face Detection using Deep Learning: An Improved Faster RCNN Approach (2017, background): “One simple strategy was to combine multiple detectors that had been trained separately for different views or poses[20][21][22].”
Feature representation for statistical-learning-based object detection: A review (2015, background): “Sparse granule features: Sparse granule features [40] are defined as the linear combination of shiftable square regions (Figure 10(a)).”
SSDMNV2: A real time DNN-based face mask detection system using single shot multibox detector and MobileNetV2 (2020, neutral): “They are used to facilitate self-focusing (Huang, Ai, Li, & Lao, 2007), the interaction be-tween humans and computers (Jun, Choi, & Kim, 2012), and managing image database (Ge, Li, Ye, & Luo, 2017).”
From Facial Parts Responses to Face Detection: A Deep Learning Approach (2015, methodology): “In the last decades, cascade based [3, 9, 20, 34] and deformable part models (DPM) detectors dominate the face detection approaches.”
Multi-view Face Detection Using Deep Convolutional Neural Networks (2015, methodology): “This method is further improved by [13, 12] where, instead of one detector cascade, several detectors are used after the initial classiﬁer.”
RepPoints: Point Set Representation for Object Detection (2019, background): “These include an elliptic representation for pedestrian detection [22] and a rotated bounding box to better handle rotational variations [16, 48].”
On-line Boosting and Vision (2006, methodology): “, introducing FloatBoost (weak classifiers can be also removed from the strong classifier) [71], a vector boosting [52], or by using sequential decision making theory [120].”
WIDER FACE: A Face Detection Benchmark (2015, neutral): “Modern face detection algorithms can be categorized into four categories: cascade based methods [2, 10, 15, 16, 21], part based methods [19, 23, 30], channel feature based methods [25, 24], and neural network based methods [6, 14, 25, 28].”
FDDB: A benchmark for face detection in unconstrained settings (2010, background): “• multi-view: out-of-plane rotations are binned into a pre-determined set of views [7, 9, 12];”
Detecting Masked Faces in the Wild with LLE-CNNs (2017, background): “Due to the great success of these face detectors, some of them have been integrated into applications so as to facilitate auto-focusing [10], human computer interaction [12] and image database management [27].”
Dense Label Encoding for Boundary Discontinuity Free Rotation Detection (2020, methodology): “Many rotation detectors (including those for aerial image [46, 15, 47, 2, 6, 51, 45, 30, 48, 49, 50], scene text [56, 23, 14, 26, 19, 18] and face [34, 13, 33]) are derived based on the vanilla detection algorithms [10, 32, 31, 5, 20, 21].”
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, background): “It is worthwhile to note that although objects in scene text detection [83] and face detection [60]”
Grouplet: A structured image representation for recognizing human and object interactions (2010, methodology): “We first run a face detector [14] on all PPMI images.”
Large-scale privacy protection in Google Street View (2009, methodology): “For example, if the box is from camera zero and there are eight cameras, then the entries for the camera index are { 10000000 } . impressive performance, such as the Tsinghua University detector[5].”
Joint Cascade Face Detection and Alignment (2014, background): “Many works are on multi-view face detection [10,17,27,7].”