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

Papers archive 2025-07-28

18 shown of 18, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

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