{"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":"/method/2-1-d-convolution","slug":"2-1-d-convolution","name":"(2+1)D Convolution","full_name":"(2+1)D Convolution","full_name_withheld":false,"description_markdown":"A **(2+1)D Convolution** is a type of [convolution](https://paperswithcode.com/method/convolution) used for action recognition convolutional neural networks, with a spatiotemporal volume. As opposed to applying a [3D Convolution](https://paperswithcode.com/method/3d-convolution) over the entire volume, which can be computationally expensive and lead to overfitting, a (2+1)D convolution splits computation into two convolutions: a spatial 2D convolution followed by a temporal 1D convolution.","description_state":"present","introduced_year":null,"introduced_by":{"title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","paper":"/paper/a-closer-look-at-spatiotemporal-convolutions","first_author":"Du Tran","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/a-closer-look-at-spatiotemporal-convolutions"},"source":{"url":"http://arxiv.org/abs/1711.11248v3","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/pytorch/vision/blob/9e474c3c46c0871838c021093c67a9c7eb1863ea/torchvision/models/video/resnet.py#L36","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutions","url":"/methods/category/convolutions","pwc_aliases":[]}],"n_papers_tagged":17,"archive_num_papers":17,"papers_newest_first":[{"paper":null,"slug":"multi-microphone-and-multi-modal-emotion","title":"Multi-Microphone and Multi-Modal Emotion Recognition in Reverberant Environment","date":"2024-09-14","arxiv_id":"2409.09545","n_code_links":0,"syntology":null},{"paper":null,"slug":"use-of-a-multiscale-vision-transformer-to","title":"Use of a Multiscale Vision Transformer to predict Nursing Activities Score from Low Resolution Thermal Videos in an Intensive Care Unit","date":"2024-05-30","arxiv_id":"2406.04364","n_code_links":0,"syntology":null},{"paper":null,"slug":"temporal-contrastive-learning-with-curriculum","title":"Temporal Contrastive Learning with Curriculum","date":"2022-09-02","arxiv_id":"2209.00760","n_code_links":0,"syntology":null},{"paper":"/paper/motion-focused-contrastive-learning-of-video-1","slug":"motion-focused-contrastive-learning-of-video-1","title":"Motion-Focused Contrastive Learning of Video Representations","date":"2022-01-11","arxiv_id":"2201.04029","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yihengzhang-cv/mcl-motion-focused-contrastive-learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/bytetrack-multi-object-tracking-by-1","slug":"bytetrack-multi-object-tracking-by-1","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","date":"2021-10-13","arxiv_id":"2110.06864","n_code_links":10,"syntology":{"ran":10,"of":12,"n_ran_checked":9,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ifzhang/ByteTrack"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/self-supervised-video-representation-learning-8","slug":"self-supervised-video-representation-learning-8","title":"Self-Supervised Video Representation Learning with Meta-Contrastive Network","date":"2021-08-19","arxiv_id":"2108.08426","n_code_links":0,"syntology":null},{"paper":null,"slug":"spatiotemporal-contrastive-learning-of-facial","title":"Spatiotemporal Contrastive Learning of Facial Expressions in Videos","date":"2021-08-06","arxiv_id":"2108.03064","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-video-representation-learning-7","slug":"self-supervised-video-representation-learning-7","title":"Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting","date":"2021-06-18","arxiv_id":"2106.10137","n_code_links":1,"syntology":null},{"paper":"/paper/you-only-learn-one-representation-unified","slug":"you-only-learn-one-representation-unified","title":"You Only Learn One Representation: Unified Network for Multiple Tasks","date":"2021-05-10","arxiv_id":"2105.04206","n_code_links":9,"syntology":null},{"paper":null,"slug":"the-3tconv-an-intrinsic-approach-to","title":"The 3TConv: An Intrinsic Approach to Explainable 3D CNNs","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-video-representation-learning-5","slug":"self-supervised-video-representation-learning-5","title":"Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics","date":"2020-08-31","arxiv_id":"2008.13426","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["laura-wang/video_repres_sts"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/late-temporal-modeling-in-3d-cnn","slug":"late-temporal-modeling-in-3d-cnn","title":"Late Temporal Modeling in 3D CNN Architectures with BERT for Action Recognition","date":"2020-08-03","arxiv_id":"2008.01232","n_code_links":2,"syntology":null},{"paper":null,"slug":"achieving-real-time-execution-of-3d","title":"RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices","date":"2020-07-20","arxiv_id":"2007.09835","n_code_links":0,"syntology":null},{"paper":"/paper/neural-graph-collaborative-filtering","slug":"neural-graph-collaborative-filtering","title":"Neural Graph Collaborative Filtering","date":"2019-05-20","arxiv_id":"1905.08108","n_code_links":21,"syntology":{"ran":7,"of":7,"n_ran_checked":3,"n_instrument":4,"unverified":0,"pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xiangwang1223/neural_graph_collaborative_filtering"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/spatiotemporal-cnns-for-pornography-detection","slug":"spatiotemporal-cnns-for-pornography-detection","title":"Spatiotemporal CNNs for Pornography Detection in Videos","date":"2018-10-24","arxiv_id":"1810.10519","n_code_links":1,"syntology":null},{"paper":"/paper/multi-fiber-networks-for-video-recognition","slug":"multi-fiber-networks-for-video-recognition","title":"Multi-Fiber Networks for Video Recognition","date":"2018-07-30","arxiv_id":"1807.11195","n_code_links":0,"syntology":null},{"paper":"/paper/a-closer-look-at-spatiotemporal-convolutions","slug":"a-closer-look-at-spatiotemporal-convolutions","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","date":"2017-11-30","arxiv_id":"1711.11248","n_code_links":24,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["facebookresearch/R2Plus1D"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"papers_shown":17,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":17,"with_a_code_link":9,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":17,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/method/2-1-d-convolution/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/2-1-d-convolution/papers/ran/1","json":"/method/2-1-d-convolution/papers/ran/1.json","rows":5}],"tasks":[{"task":"/task/action-recognition-in-videos","name":"Action Recognition","papers":8},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":5},{"task":"/task/representation-learning","name":"Representation Learning","papers":5},{"task":"/task/retrieval","name":"Retrieval","papers":4},{"task":"/task/video-retrieval","name":"Video Retrieval","papers":4},{"task":"/task/action-recognition","name":"Temporal Action Localization","papers":3},{"task":"/task/action-classification","name":"Action Classification","papers":2},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":2},{"task":"/task/optical-flow-estimation","name":"Optical Flow Estimation","papers":2},{"task":"/task/self-supervised-action-recognition","name":"Self-Supervised Action Recognition","papers":2},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":2},{"task":"/task/video-recognition","name":"Video Recognition","papers":2},{"task":"/task/action-recognition-in-videos-2","name":"Action Recognition In Videos","papers":1},{"task":"/task/code-generation","name":"Code Generation","papers":1},{"task":"/task/collaborative-filtering","name":"Collaborative Filtering","papers":1},{"task":"/task/emotion-recognition","name":"Emotion Recognition","papers":1},{"task":"/task/facial-expression-recognition-1","name":"Facial Expression Recognition","papers":1},{"task":"/task/facial-expression-recognition","name":"Facial Expression Recognition (FER)","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/link-prediction","name":"Link Prediction","papers":1}],"tasks_shown":20,"n_tasks":35,"usage_by_year":[{"year":"2017","papers":1},{"year":"2018","papers":2},{"year":"2019","papers":1},{"year":"2020","papers":3},{"year":"2021","papers":6},{"year":"2022","papers":2},{"year":"2024","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/2-1-d-convolution"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=%282%2B1%29D%20Convolution","read_at":"2026-10-05T00:51:11+00:00","query":"(2+1)D Convolution","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1711.11248","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named '(2+1)D Convolution' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["DEEP CONVOLUTION","Reverse Convolution","Similarity Convolution","peripheral convolution","Persistent Convolution","Convolution Exponential","Focal Sparse Convolution","Expert Binary Convolution"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"b1022375ba18c02915af6b31e5190d78f3a6faec79b9e11d6e20083adfc23713","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}