{"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/expnet-landmark-free-deep-3d-facial","title":"ExpNet: Landmark-Free, Deep, 3D Facial Expressions","arxiv_id":"1802.00542","date":"2018-02-02","proceeding":null,"authors":["Feng-Ju Chang","Anh Tuan Tran","Tal Hassner","Iacopo Masi","Ram Nevatia","Gerard Medioni"],"abstract":"We describe a deep learning based method for estimating 3D facial expression\ncoefficients. Unlike previous work, our process does not relay on facial\nlandmark detection methods as a proxy step. Recent methods have shown that a\nCNN can be trained to regress accurate and discriminative 3D morphable model\n(3DMM) representations, directly from image intensities. By foregoing facial\nlandmark detection, these methods were able to estimate shapes for occluded\nfaces appearing in unprecedented in-the-wild viewing conditions. We build on\nthose methods by showing that facial expressions can also be estimated by a\nrobust, deep, landmark-free approach. Our ExpNet CNN is applied directly to the\nintensities of a face image and regresses a 29D vector of 3D expression\ncoefficients. We propose a unique method for collecting data to train this\nnetwork, leveraging on the robustness of deep networks to training label noise.\nWe further offer a novel means of evaluating the accuracy of estimated\nexpression coefficients: by measuring how well they capture facial emotions on\nthe CK+ and EmotiW-17 emotion recognition benchmarks. We show that our ExpNet\nproduces expression coefficients which better discriminate between facial\nemotions than those obtained using state of the art, facial landmark detection\ntechniques. Moreover, this advantage grows as image scales drop, demonstrating\nthat our ExpNet is more robust to scale changes than landmark detection\nmethods. Finally, at the same level of accuracy, our ExpNet is orders of\nmagnitude faster than its alternatives.","url_abs":"http://arxiv.org/abs/1802.00542v1","url_pdf":"http://arxiv.org/pdf/1802.00542v1.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":"expnet-landmark-free-deep-3d-facial","repo_url":"https://github.com/fengju514/Expression-Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-face-reconstruction","task_name":"3D Face Reconstruction"},{"task_slug":"3d-facial-expression-recognition","task_name":"3D Facial Expression Recognition"},{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"facial-landmark-detection","task_name":"Facial Landmark Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-face-reconstruction-on-realy","task":"3D Face Reconstruction","dataset":"REALY","model":"ExpNet","rank_in_archive_order":22,"of":24,"metrics":{"@cheek":"1.717 (±0.590)","@forehead":"3.084 (±1.005)","@mouth":"1.912 (±0.450)","@nose":"2.509 (±0.486)","all":"2.306"},"uses_additional_data":false},{"leaderboard":"/sota/3d-face-reconstruction-on-realy-side-view","task":"3D Face Reconstruction","dataset":"REALY (side-view)","model":"ExpNet","rank_in_archive_order":19,"of":19,"metrics":{"@cheek":"1.842 (±0.609)","@forehead":"3.393 (±1.076)","@mouth":"2.160 (±0.448)","@nose":"2.508 (±0.491)","all":"2.476"},"uses_additional_data":false},{"leaderboard":"/sota/3d-facial-expression-recognition-on-2017_test","task":"3D Facial Expression Recognition","dataset":"2017_test set","model":"aan","rank_in_archive_order":1,"of":1,"metrics":{"14 gestures accuracy":"2"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.00542","atlas_url":"https://app.syntology.ai/?focus=1802.00542","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1802.00542"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1802.00542\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1802.00542"},"call":"get_concepts_for_paper(arxiv_id=\"1802.00542\")"}],"by_repo":[{"repo":"fengju514/Expression-Net","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":"462b087266996eaad5dfd23453c73c935b087f2c86edf5c65445430eeee66693","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}