{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/marlin-masked-autoencoder-for-facial-video","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","arxiv_id":"2211.06627","date":"2022-11-12","proceeding":"CVPR 2023 1","authors":["Zhixi Cai","Shreya Ghosh","Kalin Stefanov","Abhinav Dhall","Jianfei Cai","Hamid Rezatofighi","Reza Haffari","Munawar Hayat"],"abstract":"This paper proposes a self-supervised approach to learn universal facial representations from videos, that can transfer across a variety of facial analysis tasks such as Facial Attribute Recognition (FAR), Facial Expression Recognition (FER), DeepFake Detection (DFD), and Lip Synchronization (LS). Our proposed framework, named MARLIN, is a facial video masked autoencoder, that learns highly robust and generic facial embeddings from abundantly available non-annotated web crawled facial videos. As a challenging auxiliary task, MARLIN reconstructs the spatio-temporal details of the face from the densely masked facial regions which mainly include eyes, nose, mouth, lips, and skin to capture local and global aspects that in turn help in encoding generic and transferable features. Through a variety of experiments on diverse downstream tasks, we demonstrate MARLIN to be an excellent facial video encoder as well as feature extractor, that performs consistently well across a variety of downstream tasks including FAR (1.13% gain over supervised benchmark), FER (2.64% gain over unsupervised benchmark), DFD (1.86% gain over unsupervised benchmark), LS (29.36% gain for Frechet Inception Distance), and even in low data regime. Our code and models are available at https://github.com/ControlNet/MARLIN .","url_abs":"https://arxiv.org/abs/2211.06627v3","url_pdf":"https://arxiv.org/pdf/2211.06627v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"marlin-masked-autoencoder-for-facial-video","repo_url":"https://github.com/ControlNet/MARLIN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"deepfake-detection","task_name":"DeepFake Detection"},{"task_slug":"emotion-classification","task_name":"Emotion Classification"},{"task_slug":"face-swapping","task_name":"Face Swapping"},{"task_slug":"facial-attribute-classification","task_name":"Facial Attribute Classification"},{"task_slug":"facial-expression-recognition-1","task_name":"Facial Expression Recognition"},{"task_slug":"facial-expression-recognition","task_name":"Facial Expression Recognition (FER)"},{"task_slug":"multimodal-sentiment-analysis","task_name":"Multimodal Sentiment Analysis"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"lip-sync","task_name":"Unconstrained Lip-synchronization"}],"methods":[{"method_slug":"mae","method_name":"MAE"},{"method_slug":"marlin","method_name":"MARLIN"}],"datasets_introduced":[],"methods_introduced":[{"slug":"marlin","name":"MARLIN","full_name":"MARLIN"}],"results":[{"leaderboard":"/sota/action-classification-on-celebv-hq","task":"Action Classification","dataset":"CelebV-HQ","model":"MARLIN","rank_in_archive_order":1,"of":1,"metrics":{"AUC":"0.9406","Accuracy":"95.48"},"uses_additional_data":false},{"leaderboard":"/sota/deepfake-detection-on-faceforensics-1","task":"DeepFake Detection","dataset":"FaceForensics++","model":"MARLIN (ViT-L)","rank_in_archive_order":3,"of":6,"metrics":{"AUC":"0.9377"},"uses_additional_data":false},{"leaderboard":"/sota/deepfake-detection-on-faceforensics-1","task":"DeepFake Detection","dataset":"FaceForensics++","model":"MARLIN (ViT-B)","rank_in_archive_order":4,"of":6,"metrics":{"AUC":"0.9305"},"uses_additional_data":false},{"leaderboard":"/sota/deepfake-detection-on-faceforensics-1","task":"DeepFake Detection","dataset":"FaceForensics++","model":"MARLIN (ViT-S)","rank_in_archive_order":5,"of":6,"metrics":{"AUC":"0.8863"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-classification-on-cmu-mosei","task":"Emotion Classification","dataset":"CMU-MOSEI","model":"MARLIN (ViT-L)","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"80.63"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-classification-on-cmu-mosei","task":"Emotion Classification","dataset":"CMU-MOSEI","model":"MARLIN (ViT-B)","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"80.6"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-classification-on-cmu-mosei","task":"Emotion Classification","dataset":"CMU-MOSEI","model":"MARLIN (ViT-S)","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"80.38"},"uses_additional_data":false},{"leaderboard":"/sota/facial-attribute-classification-on-celebv-hq","task":"Facial Attribute Classification","dataset":"CelebV-HQ","model":"MARLIN","rank_in_archive_order":1,"of":1,"metrics":{"AUC":"0.9561","Accuracy":"93.9"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-sentiment-analysis-on-cmu-mosei-1","task":"Multimodal Sentiment Analysis","dataset":"CMU-MOSEI","model":"MARLIN (ViT-L)","rank_in_archive_order":12,"of":15,"metrics":{"Accuracy":"74.83"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-sentiment-analysis-on-cmu-mosei-1","task":"Multimodal Sentiment Analysis","dataset":"CMU-MOSEI","model":"MARLIN (ViT-B)","rank_in_archive_order":13,"of":15,"metrics":{"Accuracy":"73.7"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-sentiment-analysis-on-cmu-mosei-1","task":"Multimodal Sentiment Analysis","dataset":"CMU-MOSEI","model":"MARLIN (ViT-S)","rank_in_archive_order":14,"of":15,"metrics":{"Accuracy":"72.69"},"uses_additional_data":false},{"leaderboard":"/sota/lip-sync-on-lrs2","task":"Unconstrained Lip-synchronization","dataset":"LRS2","model":"Wav2Lip + ViT + MARLIN","rank_in_archive_order":1,"of":3,"metrics":{"FID":"3.452","LSE-C":"5.528","LSE-D":"7.127"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"ControlNet/MARLIN","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f397d938c3773576a8f20aa4fbd48db7ba2d1ebbb437b8b8bbf4bfaa5663ce13","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}