Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

Temporal Transformer Encoder

A temporal transformer encoder is a neural network component designed to model time-dependent dependencies and dynamic interactions across sequential feature representations. In video understanding and sequence processing architectures that factorize space and time, it operates on sequence-level tokens or frame representations, such as aggregated feature vectors extracted from individual video frames by a preceding spatial encoder. By applying multi-head self-attention specifically across the temporal dimension rather than computing joint attention across all spatial and temporal tokens simultaneously, the temporal transformer encoder captures motion patterns, transitions, and chronological context while substantially reducing computational complexity.

1 item

ViViT: A Video Vision Transformer

ViViT: A Video Vision Transformer

Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lučić, Cordelia Schmid

OrganizationsGoogle

Why you should read this

Introduces ViViT, an efficient pure-transformer framework for video classification that factorizes spatio-temporal dimensions and leverages pretrained image models to surpass standard 3D convolutional networks across major benchmarks.

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 this https URL

Added

2026-09-12