Face Detection without Bells and Whistles

By Markus Mathias, Rodrigo Benenson, Marco Pedersoli, Luc Van Gool. 2014

584 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

End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019, methodology): “To obtain tracks of faces in the video, we run the multi-view face detector [25] based on the DPM model [12].”
Deep Learning Face Attributes in the Wild (2014, methodology): “We also investigate how these methods perform with respect to overlap ratio (IoU ), following [35, 21].”
I-Pic: A Platform for Privacy-Compliant Image Capture (2016, methodology): “These components leverage our prior work in face detection [6] and facial feature extraction [7], as detailed in Section 4.”
Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure (2019, background): “Even the seemingly simple task of facial recognition [4, 23, 32] has been shown to be subject to extreme amounts of algorithmic bias among select demographics.”
The MegaFace Benchmark: 1 Million Faces for Recognition at Scale (2015, background): “[21], which reported state of the art results in face detection, and is especially robust to a wide range of head poses including profiles.”
MOT16: A Benchmark for Multi-Object Tracking (2016, methodology): “For all these cases where the class is very similar to our target class (see Figure 5), we adopt a similar strategy as in [32].”
Person Recognition in Personal Photo Collections (2015, methodology): “The face region f is defined by a state of the art face detector [31] (see §3.”
Detecting Masked Faces in the Wild with LLE-CNNs (2017, methodology): “[22] trained a DPM-based face detector with about 26, 000 faces from AFLW, which achieved an average precision of 97.”
From Facial Parts Responses to Face Detection: A Deep Learning Approach (2015, methodology): “A recent study [23] demonstrates state-of-the-art performance with just a vanilla DPM, achieving better results than more sophisticated DPM variants [36, 40].”
S^3FD: Single Shot Scale-Invariant Face Detector (2017, methodology): “Besides the cascade structure, [30, 51, 63] introduce deformable part models (DPM) into face detection tasks and achieve remarkable performance.”
Deep Expectation of Real and Apparent Age from a Single Image Without Facial Landmarks (2016, methodology): “Enjuto team (6th place in LAP challenge) use face detection (Mathias et al. 2014) and face landmark detection (Kazemi and Sullivan 2014) and six CNNs for classification in three age groups and for local (part face) and global (whole face) prediction of age.”
Filtered channel features for pedestrian detection (2015, background): “Colour has shown to be an effective feature for pedestrian detection and hence multiple colour spaces have been explored (both hand-crafted and learned) [8, 17, 18, 22].”
DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild (2016, methodology): “Figure 7 (bottom) presents some self-evaluations in which we compare the quality of initialization for deformable modelling between DenseReg and two other standard face detection techniques (HOG-SVM [23], DPM [30]).”
MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking (2015, background): “Nonetheless, and following the work in [35], we commit to standardizing the set of annotations for all sequences following a common strict set of rules.”
Aff-Wild: Valence and Arousal ‘In-the-Wild’ Challenge (2017, methodology): “From each frame, we detected the faces using the method described in [26].”
MOT20: A benchmark for multi object tracking in crowded scenes (2020, methodology): “For all these cases where the class is very similar to our target class (see Figure 4), we adopt a similar strategy as in [7].”
Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification (2018, methodology): “Megaface, which to date is the largest publicly available set of facial images, was composed utilizing Head Hunter (Mathias et al., 2014) to select one million images from the Yahoo Flicker 100M image dataset (Thomee et al., 2015; Kemelmacher-Shlizerman et al., 2016).”
Object Detection With Deep Learning: A Review (2018, methodology): “The evaluated models cover DDFD [168], CascadeCNN [180], ACF-multiscale [181], Pico [182], HeadHunter [183], 0 0.”
A survey on face detection in the wild: Past, present and future (2015, background): “These verysimpleschemesachievecompetitivepedestrianandfacedetectionperformance[100] [26] [101].”
Learning from Video and Text via Large-Scale Discriminative Clustering (2017, methodology): “To obtain tracks of faces in the video, we run the multi-view face detector [25] based on the DPM model [12].”