Papers › Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks

Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks

11 Apr 2016arXiv:1604.02878archive 2025-07-28

Kaipeng Zhang, Zhanpeng Zhang, Zhifeng Li, Yu Qiao

Face detection and alignment in unconstrained environment are challenging due to various poses, illuminations and occlusions. Recent studies show that deep learning approaches can achieve impressive performance on these two tasks. In this paper, we propose a deep cascaded multi-task framework which exploits the inherent correlation between them to boost up their performance. In particular, our framework adopts a cascaded structure with three stages of carefully designed deep convolutional networks that predict face and landmark location in a coarse-to-fine manner. In addition, in the learning process, we propose a new online hard sample mining strategy that can improve the performance automatically without manual sample selection. Our method achieves superior accuracy over the state-of-the-art techniques on the challenging FDDB and WIDER FACE benchmark for face detection, and AFLW benchmark for face alignment, while keeps real time performance.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 4 repositories linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 9 samples from 4 repositories, 4 ran (3 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

42 repositories listed; official and paper-mentioned ones first.

Ander02/FaceRecognition mentioned on GitHubpytorchSyntology: not harvested report
Anuranjan-Kumar/Face-Detection mentioned on GitHubtfSyntology: not harvested report
DaneyAlex5/Live-Face-Verification-Using-Deep-Learning mentioned on GitHubtfSyntology: not harvested report
DaneyAlex5/Webcam-based-Face-Recognition-using-Deep-Learning- mentioned on GitHubtfSyntology: not harvested report
Dou-Yu-xuan/vggface2-pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to VGGFace2: A dataset for recognising faces across pose and age (arXiv:1710.08092; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
Jagannathrk2020/Face-detection-and-counting- mentioned on GitHubtfSyntology: not harvested report
KarthikBalakrishnan11/Face_Recognition_FaceNet mentioned on GitHubSyntology: not harvested report
Mrnoorsingh/QRCode-and-Face-Recognition-for-Access-Control mentioned on GitHubSyntology: not harvested report
SSusantAchary/FaceDetection-counting-using-MTCNN mentioned on GitHubtfUnlicenseSyntology: not harvested report
Team-Neighborhood/awesome-face-detection mentioned on GitHubpytorchSyntology: not harvested report
TropComplique/mtcnn-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
aannirajpatel/COMP562-Face-Mask-Detect mentioned on GitHubpytorchSyntology: not harvested report
alexattia/ExtendedTinyFaces mentioned on GitHubtfSyntology: not harvested report
arsfutura/face-recognition mentioned on GitHubpytorchBSD-3-ClauseSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
bielcarvalho/RPII-EP mentioned on GitHubpytorchSyntology: not harvested report
cydonia999/VGGFace2-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
dengpingfan/fsgan mentioned on GitHubpytorchSyntology: not harvested report
dheerajsingh7351/facedetect mentioned on GitHubtfSyntology: not harvested report
espressif/esp-who mentioned on GitHubSyntology: not harvested report
guppykang/joshFaceV2 mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
gurushantj/MTCNN mentioned on GitHubtfSyntology: not harvested report
iitmcvg/Demo-of-face-detection-and-counting- mentioned on GitHubtfSyntology: not harvested report
jimmy0087/faceai-master mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
jmysu/ESP32CAM-FaceDetect-Line-Notify mentioned on GitHubSyntology: not harvested report
krantirk/Face-detection-and-counting- mentioned on GitHubtfSyntology: not harvested report
kuaikuaikim/DFace mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FaceNet: A Unified Embedding for Face Recognition and Clustering (arXiv:1503.03832; that paper's own run record: 99 ran (of which 19 constructed an object rather than computing a result; 83 with no instrument failure: 11 honoured, 11 violated, 61 with no contract checked; 16 where Syntology's instrument failed) · 55 unverified); nothing checks that they implement this paper's method. report
mdsarfarazulh/face-verification-facenet-mtcnn mentioned on GitHubtfMITSyntology: not harvested report
njordsir/Clustering-Faces mentioned on GitHubtfSyntology: not harvested report
omaarelsherif/Face-Detection-Using-Deep-Learning mentioned on GitHubSyntology: not harvested report
omaarelsherif/Face-Detection-Using-MTCNN mentioned on GitHubSyntology: not harvested report
pengsongyou/OMG-ADSC mentioned on GitHubpytorchMITSyntology: not harvested report
polarisZhao/mtcnn-pytorch mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
ram-ch/RealTimeFaceRecognition mentioned on GitHubSyntology: not harvested report
rohith2506/facedetect mentioned on GitHubSyntology: not harvested report
tamnil/esp32-xtensa-study mentioned on GitHubSyntology: not harvested report
tuyentv2009/Face-Recognition- mentioned on GitHubtfSyntology: not harvested report
wanjinchang/MTCNN_USE_TF_E2E mentioned on GitHubtfSyntology: not harvested report
Mind23-2/MindCode-59 mindsporeSyntology: not harvested report
WangChen0902/MTCNN-Paddle paddleSyntology: not harvested report
icey-zhang/MTCNN_paddle paddleSyntology: not harvested report
matlab-deep-learning/mtcnn-face-detection NOASSERTIONSyntology: not harvested report
serengil/deepface tfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RetinaFace: Single-stage Dense Face Localisation in the Wild (arXiv:1905.00641; that paper's own run record: 73 ran (of which 0 constructed an object rather than computing a result; 58 with no instrument failure: 1 honoured, 4 violated, 53 with no contract checked; 15 where Syntology's instrument failed) · 18 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

9 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran; the contract check could not run
3ran
5unverified

Licence: 3 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

TropComplique/mtcnn-pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
detect_faces src/detector.py unverified MIT (permissive) · 940d375d4ec839b7 · report
arsfutura/face-recognition community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
normalise_dict_keys util/generate_embeddings.py ran BSD-3-Clause (permissive) · b4bf3ca25cb1e95c · report fixture: signature dictionary:dict/0/? · returned dict · level recorded 2026-09-26
normalise_string util/generate_embeddings.py ran fingerprinted BSD-3-Clause (permissive) · 6f537664906253d8 · report fixture: signature string:str/0/str · returned str · level recorded 2026-09-26
to_predictions face_recognition/face_recogniser.py ran BSD-3-Clause (permissive) · 9bed057ef256b3c3 · report fixture: signature idx_to_class:dict/0/?, probs:list/1/float · returned list · level recorded 2026-09-26
recognise_faces inference/classifier.py unverified BSD-3-Clause (permissive) · cb83b57d1ca95e64 · report
top_prediction face_recognition/face_recogniser.py unverified BSD-3-Clause (permissive) · b89fd852269ef386 · report
guppykang/joshFaceV2 community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
computeArea mtcnn/get_landmarks.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 54c248fb38a3eae3 · report fixture: signature points:ndarray/2/float · returned float64 · level recorded 2026-09-22
polarisZhao/mtcnn-pytorch community (archive-listed) 2 samples, 0 ran · 2 unverified
detect_faces src/detector.py unverified no licence file found · pointer only · 58ec7027d9109cc9 · report
run_first_stage src/detector.py unverified no licence file found · pointer only · 5ee1d0de79fb2a59 · report

Tasks

Code GenerationFace AlignmentFace Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Detection WIDER Face (Easy) Multitask Cascade CNN AP 0.851 #26 of 27 Archive leaderboard report
Face Detection WIDER Face (Hard) Multitask Cascade CNN AP 0.607 #34 of 40 Archive leaderboard report
Face Detection WIDER Face (Medium) Multitask Cascade CNN AP 0.820 #31 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections