ViViT: A Video Vision Transformer

by   Anurag Arnab, et al.

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 will release code and models.


CLIP2Video: Mastering Video-Text Retrieval via Image CLIP

We present CLIP2Video network to transfer the image-language pre-trainin...

Video Swin Transformer

The vision community is witnessing a modeling shift from CNNs to Transfo...

Leveraging Local Temporal Information for Multimodal Scene Classification

Robust video scene classification models should capture the spatial (pix...

ViR:the Vision Reservoir

The most recent year has witnessed the success of applying the Vision Tr...

TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval

Text-Video retrieval is a task of great practical value and has received...

Benchmarking the Robustness of Spatial-Temporal Models Against Corruptions

The state-of-the-art deep neural networks are vulnerable to common corru...

Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space

This paper explores the feasibility of finding an optimal sub-model from...

Code Repositories


Implementation of ViViT: A Video Vision Transformer

view repo