mlsanityData to 7 Oct 2026

HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

arXiv 1603.01249 ↗First posted 3 Mar 2016cs.CVcited by 103

Not on the map. Why?

Abstract (arXiv)

We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features. It exploits the synergy among the tasks which boosts up their individual performances. Additionally, we propose two variants of HyperFace: (1) HyperFace-ResNet that builds on the ResNet-101 model and achieves significant improvement in performance, and (2) Fast-HyperFace that uses a high recall fast face detector for generating region proposals to improve the speed of the algorithm. Extensive experiments show that the proposed models are able to capture both global and local information in faces and performs significantly better than many competitive algorithms for each of these four tasks.

Key facts. Cited by 103 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 22; 2023: 17; 2024: 18; 2025: 6; 2026: 4.

103 papers.

Sort:

By area:

  1. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
  2. 2021OTCE: A Transferability Metric for Cross-Domain Cross-Task Representationscited by 62
  3. 2022Where in the World is this Image? Transformer-based Geo-localization in the Wildcited by 58
  4. 2023PIGEON: Predicting Image Geolocationscited by 55
  5. 2021Deep Learning for Micro-expression Recognition: A Surveycited by 43
  6. 2022Task Adaptive Parameter Sharing for Multi-Task Learningcited by 42
  7. 2023SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimationcited by 38
  8. 2024FaceXFormer: A Unified Transformer for Facial Analysiscited by 34
  9. 2023Model Spider: Learning to Rank Pre-Trained Models Efficientlycited by 32
  10. 2022DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Imagecited by 31
  11. 2021Unsupervised Part Segmentation through Disentangling Appearance and Shapecited by 29
  12. 2021Pre-training strategies and datasets for facial representation learningcited by 25
38 more
  1. 2022Multi-task head pose estimation in-the-wildcited by 22
  2. 2023Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimationcited by 20
  3. 2022Part-based Face Recognition with Vision Transformerscited by 18
  4. 2025BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Modelscited by 18
  5. 2021Towards Accurate and Compact Architectures via Neural Architecture Transformercited by 17
  6. 2021MultiTask-CenterNet (MCN): Efficient and Diverse Multitask Learning using an Anchor Free Approachcited by 17
  7. 2021AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learningcited by 17
  8. 2022GazeOnce: Real-Time Multi-Person Gaze Estimationcited by 17
  9. 2024A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trendscited by 16
  10. 2021Graph-based Facial Affect Analysis: A Reviewcited by 14
  11. 2022DiSparse: Disentangled Sparsification for Multitask Model Compressioncited by 14
  12. 2021Facial-Sketch Synthesis: A New Challengecited by 13
  13. 2024Faceptor: A Generalist Model for Face Perceptioncited by 12
  14. 2024On the representation and methodology for wide and short range head pose estimationcited by 11
  15. 2024Face-MLLM: A Large Face Perception Modelcited by 11
  16. 2021ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimationcited by 10
  17. 2021Going Deeper Into Face Detection: A Surveycited by 10
  18. 2021A Deep Learning-based Quality Assessment and Segmentation System with a Large-scale Benchmark Dataset for Optical Coherence Tomographic Angiography Imagecited by 9
  19. 2021HHP-Net: A light Heteroscedastic neural network for Head Pose estimation with uncertaintycited by 9
  20. 2023Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learningcited by 8
  21. 2021Sejong Face Database: A Multi-Modal Disguise Face Databasecited by 7
  22. 2021Convolutional Neural Networks for Sleep Stage Scoring on a Two-Channel EEG Signalcited by 6
  23. 2021LOTR: Face Landmark Localization Using Localization Transformercited by 6
  24. 2022Multi-Order Networks for Action Unit Detectioncited by 6
  25. 2023DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Anglescited by 6
  26. 2025FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPOcited by 6
  27. 2021Few-Shot Model Adaptation for Customized Facial Landmark Detection, Segmentation, Stylization and Shadow Removalcited by 5
  28. 2023YOLOR-Based Multi-Task Learningcited by 5
  29. 2023BAND-2k: Banding Artifact Noticeable Database for Banding Detection and Quality Assessmentcited by 5
  30. 2024Task-adaptive Q-Facecited by 5
  31. 2021Instance-Level Task Parameters: A Robust Multi-task Weighting Frameworkcited by 4
  32. 2021Identification of Attack-Specific Signatures in Adversarial Examplescited by 4
  33. 2022LwPosr: Lightweight Efficient Fine-Grained Head Pose Estimationcited by 4
  34. 2022Composite Learning for Robust and Effective Dense Predictionscited by 4
  35. 2021Regional Attention Network (RAN) for Head Pose and Fine-grained Gesture Recognitioncited by 3
  36. 2021Is Gender "In-the-Wild" Inference Really a Solved Problem?cited by 3
  37. 2022ViewNet: Unsupervised Viewpoint Estimation from Conditional Generationcited by 3
  38. 2023EfficientFace: An Efficient Deep Network with Feature Enhancement for Accurate Face Detectioncited by 3

50 most cited of 103 All 103 (JSON)