{"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/procedural-generation-of-videos-to-train-deep","title":"Procedural Generation of Videos to Train Deep Action Recognition Networks","arxiv_id":"1612.00881","date":"2016-12-02","proceeding":"CVPR 2017 7","authors":["César Roberto de Souza","Adrien Gaidon","Yohann Cabon","Antonio Manuel López Peña"],"abstract":"Deep learning for human action recognition in videos is making significant\nprogress, but is slowed down by its dependency on expensive manual labeling of\nlarge video collections. In this work, we investigate the generation of\nsynthetic training data for action recognition, as it has recently shown\npromising results for a variety of other computer vision tasks. We propose an\ninterpretable parametric generative model of human action videos that relies on\nprocedural generation and other computer graphics techniques of modern game\nengines. We generate a diverse, realistic, and physically plausible dataset of\nhuman action videos, called PHAV for \"Procedural Human Action Videos\". It\ncontains a total of 39,982 videos, with more than 1,000 examples for each\naction of 35 categories. Our approach is not limited to existing motion capture\nsequences, and we procedurally define 14 synthetic actions. We introduce a deep\nmulti-task representation learning architecture to mix synthetic and real\nvideos, even if the action categories differ. Our experiments on the UCF101 and\nHMDB51 benchmarks suggest that combining our large set of synthetic videos with\nsmall real-world datasets can boost recognition performance, significantly\noutperforming fine-tuning state-of-the-art unsupervised generative models of\nvideos.","url_abs":"http://arxiv.org/abs/1612.00881v2","url_pdf":"http://arxiv.org/pdf/1612.00881v2.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":[],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition-in-videos-2","task_name":"Action Recognition In Videos"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[{"slug":"procedural-human-action-videos","name":"Procedural Human Action Videos","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.00881","atlas_url":"https://app.syntology.ai/?focus=1612.00881","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":"1612.00881"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1612.00881\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1612.00881"},"call":"get_concepts_for_paper(arxiv_id=\"1612.00881\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0e74d083a787b2adcf328792a3d82f66c959e8c61f311cc17a0e19cd563d83dc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}