{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/pytorchvideo-a-deep-learning-library-for","title":"PyTorchVideo: A Deep Learning Library for Video Understanding","arxiv_id":"2111.09887","date":"2021-11-18","proceeding":null,"authors":["Haoqi Fan","Tullie Murrell","Heng Wang","Kalyan Vasudev Alwala","Yanghao Li","Yilei Li","Bo Xiong","Nikhila Ravi","Meng Li","Haichuan Yang","Jitendra Malik","Ross Girshick","Matt Feiszli","Aaron Adcock","Wan-Yen Lo","Christoph Feichtenhofer"],"abstract":"We introduce PyTorchVideo, an open-source deep-learning library that provides a rich set of modular, efficient, and reproducible components for a variety of video understanding tasks, including classification, detection, self-supervised learning, and low-level processing. The library covers a full stack of video understanding tools including multimodal data loading, transformations, and models that reproduce state-of-the-art performance. PyTorchVideo further supports hardware acceleration that enables real-time inference on mobile devices. The library is based on PyTorch and can be used by any training framework; for example, PyTorchLightning, PySlowFast, or Classy Vision. PyTorchVideo is available at https://pytorchvideo.org/","url_abs":"https://arxiv.org/abs/2111.09887v1","url_pdf":"https://arxiv.org/pdf/2111.09887v1.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":"pytorchvideo-a-deep-learning-library-for","repo_url":"https://github.com/facebookresearch/pytorchvideo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.09887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09887"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/pytorchvideo","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"679b31ff3d94c9c4","entry":"cat_all_gather","repo":"facebookresearch/pytorchvideo","repo_kind":"official","path":"pytorchvideo/layers/distributed.py","file_url":"https://github.com/facebookresearch/pytorchvideo/blob/HEAD/pytorchvideo/layers/distributed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"679b31ff3d94c9c4"}},{"code_sha256_prefix":"3eb98239357e3133","entry":"drop_path","repo":"facebookresearch/pytorchvideo","repo_kind":"official","path":"pytorchvideo/layers/drop_path.py","file_url":"https://github.com/facebookresearch/pytorchvideo/blob/HEAD/pytorchvideo/layers/drop_path.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3eb98239357e3133"}},{"code_sha256_prefix":"8e6779a0a8e95e06","entry":"get_2d_sincos_pos_embed","repo":"facebookresearch/pytorchvideo","repo_kind":"official","path":"pytorchvideo/layers/positional_encoding.py","file_url":"https://github.com/facebookresearch/pytorchvideo/blob/HEAD/pytorchvideo/layers/positional_encoding.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"8e6779a0a8e95e06"}},{"code_sha256_prefix":"56a6ffa5c906c4e9","entry":"get_2d_sincos_pos_embed_from_grid","repo":"facebookresearch/pytorchvideo","repo_kind":"official","path":"pytorchvideo/layers/positional_encoding.py","file_url":"https://github.com/facebookresearch/pytorchvideo/blob/HEAD/pytorchvideo/layers/positional_encoding.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"56a6ffa5c906c4e9"}},{"code_sha256_prefix":"11dcb96392d4a3b1","entry":"get_3d_sincos_pos_embed","repo":"facebookresearch/pytorchvideo","repo_kind":"official","path":"pytorchvideo/layers/positional_encoding.py","file_url":"https://github.com/facebookresearch/pytorchvideo/blob/HEAD/pytorchvideo/layers/positional_encoding.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"11dcb96392d4a3b1"}},{"code_sha256_prefix":"0db49e21a865c248","entry":"make_fusion_layer","repo":"facebookresearch/pytorchvideo","repo_kind":"official","path":"pytorchvideo/layers/fusion.py","file_url":"https://github.com/facebookresearch/pytorchvideo/blob/HEAD/pytorchvideo/layers/fusion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0db49e21a865c248"}},{"code_sha256_prefix":"5e025646d89ffb82","entry":"make_multilayer_perceptron","repo":"facebookresearch/pytorchvideo","repo_kind":"official","path":"pytorchvideo/layers/mlp.py","file_url":"https://github.com/facebookresearch/pytorchvideo/blob/HEAD/pytorchvideo/layers/mlp.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5e025646d89ffb82"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}