{"id":26911312,"url":"https://github.com/kimrass/vivit","last_synced_at":"2025-08-21T05:34:06.570Z","repository":{"id":237125052,"uuid":"793860068","full_name":"KimRass/ViViT","owner":"KimRass","description":"PyTorch implementation of 'ViViT' (Arnab et al., 2021) from scratch.","archived":false,"fork":false,"pushed_at":"2024-09-30T06:47:22.000Z","size":6160,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-01T14:43:45.485Z","etag":null,"topics":["timm","vit","vivit"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/KimRass.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-04-30T02:21:00.000Z","updated_at":"2024-09-30T06:47:25.000Z","dependencies_parsed_at":"2024-05-02T10:04:49.805Z","dependency_job_id":"fa61a19c-b996-4550-b5a8-2d4b54cc56fc","html_url":"https://github.com/KimRass/ViViT","commit_stats":null,"previous_names":["kimrass/vivit"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/KimRass/ViViT","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KimRass%2FViViT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KimRass%2FViViT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KimRass%2FViViT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KimRass%2FViViT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/KimRass","download_url":"https://codeload.github.com/KimRass/ViViT/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KimRass%2FViViT/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271430887,"owners_count":24758416,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-21T02:00:08.990Z","response_time":74,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["timm","vit","vivit"],"created_at":"2025-04-01T14:37:41.183Z","updated_at":"2025-08-21T05:34:06.533Z","avatar_url":"https://github.com/KimRass.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ViViT: A Video Vision Transformer\n\n# 1. How to Use\n```python\nfrom vivit import (\n    SpatTempoAttnViViT, # Model 1: 'Spatio-temporal attention'\n    FactorEncViViT, # Model 2: 'Factorised encoder'\n    FactorSelfAttnViViT, # Model 3: 'Factorised self-attention'\n)\n\n# e.g.,\nnum_frames = 16\nimg_size = 224\nvideo = torch.randn((4, 3, num_frames, img_size, img_size))\n\nvit = timm.create_model(\"vit_base_patch16_224\", pretrained=True)\ntempo_patch_size = 4\nspat_patch_size = 16\nnum_classes = 1000\npooling_mode=\"cls\"\nmodel = FactorEncViViT(\n    vit=vit,\n    num_frames=num_frames,\n    img_size=img_size,\n    tempo_patch_size=tempo_patch_size,\n    spat_patch_size=spat_patch_size,\n    num_classes=num_classes,\n    pooling_mode=pooling_mode,\n)\n\ndevice = torch.device(\"cuda\")\nmodel = model.to(device)\nvideo = video.to(device)\n\nout = model(video) # (B, `num_classes`)\n```\n\n# 2. Citation\n```bibtext\n@misc{arnab2021vivit,\n    title={ViViT: A Video Vision Transformer}, \n    author={Anurag Arnab and Mostafa Dehghani and Georg Heigold and Chen Sun and Mario Lučić and Cordelia Schmid},\n    year={2021},\n    eprint={2103.15691},\n    archivePrefix={arXiv},\n    primaryClass={cs.CV}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkimrass%2Fvivit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkimrass%2Fvivit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkimrass%2Fvivit/lists"}