Papers › Video Swin Transformer
Video Swin Transformer
Ze Liu, Jia Ning, Yue Cao, Yixuan Wei, Zheng Zhang, Stephen Lin, Han Hu
The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers that globally connect patches across the spatial and temporal dimensions. In this paper, we instead advocate an inductive bias of locality in video Transformers, which leads to a better speed-accuracy trade-off compared to previous approaches which compute self-attention globally even with spatial-temporal factorization. The locality of the proposed video architecture is realized by adapting the Swin Transformer designed for the image domain, while continuing to leverage the power of pre-trained image models. Our approach achieves state-of-the-art accuracy on a broad range of video recognition benchmarks, including on action recognition (84.9 top-1 accuracy on Kinetics-400 and 86.1 top-1 accuracy on Kinetics-600 with ~20x less pre-training data and ~3x smaller model size) and temporal modeling (69.6 top-1 accuracy on Something-Something v2). The code and models will be made publicly available at https://github.com/SwinTransformer/Video-Swin-Transformer.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2106.13230")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2106.13230", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2106.13230")
Code
Syntology 32 code samples harvested from 7 repositories linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 3 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 29 samples from 6 repositories, 16 ran (12 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:
- innat/VideoSwin, community (archive-listed): harvested for another paper, listed under the repository
- open-mmlab/mmaction2, community (archive-listed): harvested for another paper, listed under the repository
- wangjk666/stts, community (archive-listed): harvested for another paper, listed under the repository
- towhee-io/towhee, community (archive-listed): harvested for 12 other papers, listed under the repository
Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
15 repositories listed; official and paper-mentioned ones first.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
32 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 7 of the 32 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 7 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
95ad82b70e901f5c · report
fixture: signature result_queue:deque/0/?, text_info:dict/0/?, thr:float/0/float, msg:str/0/str, ind:str/0/str, out_json:dict/0/? · returned tuple · level recorded 2026-09-25 aad0ea11cb13d353 · report
fixture: signature x_size:list/1/int, window_size:list/1/int, shift_size:list/1/int · returned tuple · level recorded 2026-09-22 8bfa8e676c9b169b · report
fixture: signature result_queue:deque/0/?, text_info:dict/0/?, thr:float/0/float, msg:str/0/str, frame:ndarray/3/int, video_writer:MockVideoWriter/0/?, label_color:tuple/1/int, msg_color:tuple/1/int · returned dict · level recorded 2026-09-25 d0ddd50f31a39641 · report
fixture: signature name:str/0/str · returned str · level recorded 2026-09-24 476b2e68d2861ca3 · report
fixture: signature h:str/0/str · returned tuple · level recorded 2026-09-24 3fd874d90e302675 · report
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 5, kind float, dtype float32 mmaction/models/backbones/swin_transformer.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) here; the stored copy is pointer only ·
4876d8faacbd6927 · report
fixture: signature x:Tensor/5/float, window_size:tuple/1/int · returned Tensor · level recorded 2026-09-22 75fd6fbfca7a246c · report
fixture: signature windows:Tensor/5/float, window_size:tuple/1/int, B:int/0/int, D:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22 0eaf5f857d6c4cff · report
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 5, kind float, dtype float32 video_swin_transformer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) here; the stored copy is pointer only ·
c33b3de22ecbd051 · report
fixture: signature x:Tensor/5/float, window_size:tuple/1/int · returned Tensor · level recorded 2026-09-22 ce51a79a418f8860 · report
fixture: signature windows:Tensor/4/float, window_size:tuple/1/int, B:int/0/int, D:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22 293dab24489b41d1 · report
fixture: signature arg_value:int/0/int, arg_type:callable/0/?, arg_name:str/0/str, prim_name:str/0/str · returned int · level recorded 2026-09-24 5f78a574a8661438 · report
fixture: signature input_size:tuple/1/int, window_size:tuple/1/int, shift_size:tuple/1/int · returned tuple · level recorded 2026-09-24 d6a99ec714147ac1 · report
fixture: signature current_step:int/0/int, warmup_steps:int/0/int, base_lr:float/0/float, init_lr:float/0/float · returned float · level recorded 2026-09-24 64bc6885f46ca205 · report
fixture: signature d:dict/0/? · returned dict · level recorded 2026-09-24 1a80346f67ccb9cf · report
fixture: signature lr:float/0/float, steps_per_epoch:int/0/int, warmup_epochs:int/0/int, max_epoch:int/0/int, t_max:int/0/int, eta_min:float/0/float · returned ndarray · level recorded 2026-09-24 e90ba252e203e0e9 · report
fixture: signature lr:float/0/float, lr_epochs:list/1/int, steps_per_epoch:int/0/int, warmup_epochs:int/0/int, max_epoch:int/0/int, gamma:float/0/float · returned ndarray · level recorded 2026-09-24 8ce6bc3f1fabc927 · report
e5f77ac329bf7def · report
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket src/models/swin3d.py unverified Apache-2.0 (permissive) ·
d6d654c50d77a727 · report
ec28a256d8bb4236 · report
5f86f604143de119 · report
fixture: signature gt_scenes:ndarray/2/int, pred_scenes:ndarray/2/int, n_frames_miss_tolerance:int/0/int · returned tuple · level recorded 2026-09-25 c434ee22884ca564 · report
fixture: signature bboxes:ndarray/2/float, scale:float/0/float · returned ndarray · level recorded 2026-09-25 bdec6fff71733f82 · report
fixture: signature video_id:str/0/str, timestamp:float/0/float · returned str · level recorded 2026-09-26 3da0df168740c1aa · report
fixture: signature predictions:ndarray/1/int · returned ndarray · level recorded 2026-09-25 53a344650c2ae128 · report
bd2c60c19da90ad9 · report
5dfa351278eb7273 · report
c5410bba5ff1d47e · report
47873a8759273c0e · report
3dc760b0bc6bfea5 · report
1e52fb40ae4513b2 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Action Classification | Kinetics-400 | Swin-L (384x384, ImageNet-21k pretrain) | Acc@1 | 84.9 | #60 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | Swin-L (384x384, ImageNet-21k pretrain) | Acc@5 | 96.7 | #60 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | Swin-L (ImageNet-21k pretrain) | Acc@1 | 83.1 | #69 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | Swin-L (ImageNet-21k pretrain) | Acc@5 | 95.9 | #69 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | Swin-B (ImageNet-21k pretrain) | Acc@1 | 82.7 | #74 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | Swin-B (ImageNet-21k pretrain) | Acc@5 | 95.5 | #74 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | Swin-B (ImageNet-1k pretrain) | Acc@1 | 80.6 | #94 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | Swin-B (ImageNet-1k pretrain) | Acc@5 | 94.6 | #94 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | Swin-S (ImageNet-1k pretrain) | Acc@1 | 80.6 | #95 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | Swin-S (ImageNet-1k pretrain) | Acc@5 | 94.5 | #95 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | Swin-T (ImageNet-1k pretrain) | Acc@1 | 78.8 | #123 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | Swin-T (ImageNet-1k pretrain) | Acc@5 | 93.6 | #123 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-600 | Swin-L (384x384, ImageNet-21k pretrain) | Top-1 Accuracy | 86.1 | #28 of 65 | Archive leaderboard | report |
| Action Classification | Kinetics-600 | Swin-L (384x384, ImageNet-21k pretrain) | Top-5 Accuracy | 97.3 | #28 of 65 | Archive leaderboard | report |
| Action Classification | Kinetics-600 | Swin-B (ImageNet-21k pretrain) | Top-1 Accuracy | 84.0 | #35 of 65 | Archive leaderboard | report |
| Action Classification | Kinetics-600 | Swin-B (ImageNet-21k pretrain) | Top-5 Accuracy | 96.5 | #35 of 65 | Archive leaderboard | report |
| Action Recognition | Something-Something V2 | Swin-B (IN-21K + Kinetics400 pretrain) | GFLOPs | 321x3 | #43 of 123 | Archive leaderboard | report |
| Action Recognition | Something-Something V2 | Swin-B (IN-21K + Kinetics400 pretrain) | Parameters | 89 | #43 of 123 | Archive leaderboard | report |
| Action Recognition | Something-Something V2 | Swin-B (IN-21K + Kinetics400 pretrain) | Top-1 Accuracy | 69.6 | #43 of 123 | Archive leaderboard | report |
| Action Recognition | Something-Something V2 | Swin-B (IN-21K + Kinetics400 pretrain) | Top-5 Accuracy | 92.7 | #43 of 123 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections