{"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/2103-15691","title":"ViViT: A Video Vision Transformer","arxiv_id":"2103.15691","date":"2021-03-29","proceeding":"ICCV 2021 10","authors":["Anurag Arnab","Mostafa Dehghani","Georg Heigold","Chen Sun","Mario Lučić","Cordelia Schmid"],"abstract":"We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatio-temporal tokens from the input video, which are then encoded by a series of transformer layers. In order to handle the long sequences of tokens encountered in video, we propose several, efficient variants of our model which factorise the spatial- and temporal-dimensions of the input. Although transformer-based models are known to only be effective when large training datasets are available, we show how we can effectively regularise the model during training and leverage pretrained image models to be able to train on comparatively small datasets. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple video classification benchmarks including Kinetics 400 and 600, Epic Kitchens, Something-Something v2 and Moments in Time, outperforming prior methods based on deep 3D convolutional networks. To facilitate further research, we release code at https://github.com/google-research/scenic/tree/main/scenic/projects/vivit","url_abs":"https://arxiv.org/abs/2103.15691v2","url_pdf":"https://arxiv.org/pdf/2103.15691v2.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":"2103-15691","repo_url":"https://github.com/google-research/scenic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"2103-15691","repo_url":"https://github.com/Abdulrahman-Adel/Real-Life-Violence-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"2103-15691","repo_url":"https://github.com/KSonPham/ViVit-a-Pytorch-implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"2103-15691","repo_url":"https://github.com/SforAiDl/vformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"2103-15691","repo_url":"https://github.com/drv-agwl/ViViT-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"2103-15691","repo_url":"https://github.com/mx-mark/videotransformer-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"2103-15691","repo_url":"https://github.com/rishikksh20/ViViT-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"2103-15691","repo_url":"https://github.com/MS-P3/code7/tree/main/vivit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"2103-15691","repo_url":"https://github.com/keras-team/keras-io/blob/master/examples/vision/vivit.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"2103-15691","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/1/vivit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"ViViT-H/16x2 (JFT)","rank_in_archive_order":61,"of":207,"metrics":{"Acc@1":"84.9","Acc@5":"95.8"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"ViViT-L/16x2 320","rank_in_archive_order":203,"of":207,"metrics":{"Acc@5":"94.7"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"ViViT-H/16x2 (JFT)","rank_in_archive_order":29,"of":65,"metrics":{"Top-1 Accuracy":"85.8","Top-5 Accuracy":"96.5"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"ViViT-L/16x2","rank_in_archive_order":34,"of":65,"metrics":{"Top-1 Accuracy":"84.3","Top-5 Accuracy":"95.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"ViViT-L/16x2 (320x320)","rank_in_archive_order":42,"of":65,"metrics":{"Top-1 Accuracy":"83.0","Top-5 Accuracy":"95.7"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-moments-in-time","task":"Action Classification","dataset":"MiT","model":"ViViT-L/16x2","rank_in_archive_order":28,"of":29,"metrics":{"Top 5 Accuracy":"64.9"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-on-epic-kitchens-100","task":"Action Recognition","dataset":"EPIC-KITCHENS-100","model":"ViViT-L/16x2 Fact. encoder","rank_in_archive_order":23,"of":32,"metrics":{"Action@1":"44.0","Noun@1":"56.8","Verb@1":"66.4"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"ViViT-L/16x2 Fact. encoder","rank_in_archive_order":88,"of":123,"metrics":{"Top-1 Accuracy":"65.4","Top-5 Accuracy":"89.8"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.15691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15691"}},"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/KSonPham/ViVit-a-Pytorch-implementation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/1/vivit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Abdulrahman-Adel/Real-Life-Violence-Detection","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keras-team/keras-io/blob/master/examples/vision/vivit.py","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/google-research/scenic","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mx-mark/videotransformer-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/drv-agwl/ViViT-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SforAiDl/vformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MS-P3/code7/tree/main/vivit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rishikksh20/ViViT-pytorch","reach":null}],"summary":{"ran_fixture":1,"ran":12,"ran_honours":1,"unverified":7},"by_repo_kind":{"listed":{"samples":20,"ran":13,"repositories":4}},"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":1,"samples":[{"code_sha256_prefix":"7d8eaf5537f699e4","entry":"np2th","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"7d8eaf5537f699e4"}},{"code_sha256_prefix":"9650a9a4002b76d8","entry":"Attention","repo":"KSonPham/ViVit-a-Pytorch-implementation","repo_kind":"listed","path":"models/modeling.py","file_url":"https://github.com/KSonPham/ViVit-a-Pytorch-implementation/blob/HEAD/models/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9650a9a4002b76d8"}},{"code_sha256_prefix":"f7522b96704eba2a","entry":"BaseClassificationModel","repo":"SforAiDl/vformer","repo_kind":"listed","path":"vformer/models/classification/vivit.py","file_url":"https://github.com/SforAiDl/vformer/blob/HEAD/vformer/models/classification/vivit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7522b96704eba2a"}},{"code_sha256_prefix":"4a0e3dfe29d9f024","entry":"Embeddings3D","repo":"KSonPham/ViVit-a-Pytorch-implementation","repo_kind":"listed","path":"models/modeling.py","file_url":"https://github.com/KSonPham/ViVit-a-Pytorch-implementation/blob/HEAD/models/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a0e3dfe29d9f024"}},{"code_sha256_prefix":"74f97add2ae8db6e","entry":"FDATransformerEncoder","repo":"drv-agwl/ViViT-pytorch","repo_kind":"listed","path":"models.py","file_url":"https://github.com/drv-agwl/ViViT-pytorch/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74f97add2ae8db6e"}},{"code_sha256_prefix":"f4f644381533aebd","entry":"FDAttention","repo":"drv-agwl/ViViT-pytorch","repo_kind":"listed","path":"models.py","file_url":"https://github.com/drv-agwl/ViViT-pytorch/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f4f644381533aebd"}},{"code_sha256_prefix":"fc843fa02ae99869","entry":"FSATransformerEncoder","repo":"drv-agwl/ViViT-pytorch","repo_kind":"listed","path":"models.py","file_url":"https://github.com/drv-agwl/ViViT-pytorch/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc843fa02ae99869"}},{"code_sha256_prefix":"2261806fbb78432d","entry":"FSAttention","repo":"drv-agwl/ViViT-pytorch","repo_kind":"listed","path":"models.py","file_url":"https://github.com/drv-agwl/ViViT-pytorch/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2261806fbb78432d"}},{"code_sha256_prefix":"f04db9370cd8032a","entry":"MLPDecoder","repo":"SforAiDl/vformer","repo_kind":"listed","path":"vformer/models/classification/vivit.py","file_url":"https://github.com/SforAiDl/vformer/blob/HEAD/vformer/models/classification/vivit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f04db9370cd8032a"}},{"code_sha256_prefix":"35965045e79a53f5","entry":"Mlp","repo":"KSonPham/ViVit-a-Pytorch-implementation","repo_kind":"listed","path":"models/modeling.py","file_url":"https://github.com/KSonPham/ViVit-a-Pytorch-implementation/blob/HEAD/models/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35965045e79a53f5"}},{"code_sha256_prefix":"20fb836cf685bd0e","entry":"Registry","repo":"SforAiDl/vformer","repo_kind":"listed","path":"vformer/models/classification/vivit.py","file_url":"https://github.com/SforAiDl/vformer/blob/HEAD/vformer/models/classification/vivit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"20fb836cf685bd0e"}},{"code_sha256_prefix":"acb104726aac5d2f","entry":"Transformer","repo":"rishikksh20/ViViT-pytorch","repo_kind":"listed","path":"vivit.py","file_url":"https://github.com/rishikksh20/ViViT-pytorch/blob/HEAD/vivit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"acb104726aac5d2f"}},{"code_sha256_prefix":"2aecd388beda0ef3","entry":"ViViT","repo":"rishikksh20/ViViT-pytorch","repo_kind":"listed","path":"vivit.py","file_url":"https://github.com/rishikksh20/ViViT-pytorch/blob/HEAD/vivit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2aecd388beda0ef3"}},{"code_sha256_prefix":"7deb3c28da2b4c81","entry":"pair","repo":"SforAiDl/vformer","repo_kind":"listed","path":"vformer/models/classification/vivit.py","file_url":"https://github.com/SforAiDl/vformer/blob/HEAD/vformer/models/classification/vivit.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7deb3c28da2b4c81"}},{"code_sha256_prefix":"3aeaa3af2d538769","entry":"Block","repo":"KSonPham/ViVit-a-Pytorch-implementation","repo_kind":"listed","path":"models/modeling.py","file_url":"https://github.com/KSonPham/ViVit-a-Pytorch-implementation/blob/HEAD/models/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3aeaa3af2d538769"}},{"code_sha256_prefix":"a13ffe0da0765ccb","entry":"Encoder","repo":"KSonPham/ViVit-a-Pytorch-implementation","repo_kind":"listed","path":"models/modeling.py","file_url":"https://github.com/KSonPham/ViVit-a-Pytorch-implementation/blob/HEAD/models/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a13ffe0da0765ccb"}},{"code_sha256_prefix":"f3febe06012a3d59","entry":"MyViViT","repo":"KSonPham/ViVit-a-Pytorch-implementation","repo_kind":"listed","path":"models/modeling.py","file_url":"https://github.com/KSonPham/ViVit-a-Pytorch-implementation/blob/HEAD/models/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3febe06012a3d59"}},{"code_sha256_prefix":"085322a052a6aa56","entry":"Transformer","repo":"KSonPham/ViVit-a-Pytorch-implementation","repo_kind":"listed","path":"models/modeling.py","file_url":"https://github.com/KSonPham/ViVit-a-Pytorch-implementation/blob/HEAD/models/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"085322a052a6aa56"}},{"code_sha256_prefix":"a639c271341e65f0","entry":"VanillaEncoder","repo":"SforAiDl/vformer","repo_kind":"listed","path":"vformer/models/classification/vivit.py","file_url":"https://github.com/SforAiDl/vformer/blob/HEAD/vformer/models/classification/vivit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a639c271341e65f0"}},{"code_sha256_prefix":"893bed9821ea5367","entry":"ViViTBackbone","repo":"drv-agwl/ViViT-pytorch","repo_kind":"listed","path":"models.py","file_url":"https://github.com/drv-agwl/ViViT-pytorch/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"893bed9821ea5367"}},{"code_sha256_prefix":"e4a0f20e13c6ea01","entry":"ViViTModel2","repo":"SforAiDl/vformer","repo_kind":"listed","path":"vformer/models/classification/vivit.py","file_url":"https://github.com/SforAiDl/vformer/blob/HEAD/vformer/models/classification/vivit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4a0f20e13c6ea01"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}