Methods › Computer Vision › Generative Video Models › TimeSformer

TimeSformer

18 papers tagged archive 2025-07-28

Introduced by Gedas Bertasius et al. in Is Space-Time Attention All You Need for Video Understanding?

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

TimeSformer is a convolution-free approach to video classification built exclusively on self-attention over space and time. It adapts the standard Transformer architecture to video by enabling spatiotemporal feature learning directly from a sequence of frame-level patches. Specifically, the method adapts the image model [Vision Transformer](https://paperswithcode.com/method/vision-transformer) (ViT) to video by extending the self-attention mechanism from the image space to the space-time 3D volume. As in ViT, each patch is linearly mapped into an embedding and augmented with positional information. This makes it possible to interpret the resulting sequence of vector

PaperSourceSee Code · pwc-1/paper1

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 16 in the graph, strongest link: official). This answer is about arXiv:2102.05095, the paper the archive credits with this method.

Origin paper of this answer, arXiv:2102.05095 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 35 ran (of which 17 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 14 where Syntology's instrument failed) · 8 unverified (of 43 harvested samples) · 14 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 18 · with a code link: 5 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2 of 18 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 18 of 18, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 46 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Action Recognition3
Classification3
Video Understanding3
Action Classification2
Sign Language Recognition2
Video Classification2
Video Question Answering2
Action Detection1
Action Triplet Detection1
Action Triplet Recognition1
Age Classification1
Age Estimation1
All1
Anomaly Detection1
Automatic Speech Recognition1
Automatic Speech Recognition (ASR)1
Computational Efficiency1
Data Augmentation1
DeepFake Detection1
Domain Adaptation1

Usage over time archive 2025-07-28

Papers per year tagged with TimeSformer: 2021 to 2025, peak 4 4 0 2021: 2 papers 2021 2022: 4 papers 2022 2023: 4 papers 2023 2024: 4 papers 2024 2025: 4 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (18 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Generative Video Models

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