# Initialization Strategies of Spatio-Temporal Convolutional Neural Networks

Source: [Initialization Strategies of Spatio-Temporal Convolutional Neural Networks](<https://www.sota2.com/research/paper/68fa61ca1e209131ce9f5e72>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:06:28.249Z

Authors: Elman Mansimov, Nitish Srivastava, Ruslan Salakhutdinov

Published: 2015-03-25T03:41:47.000Z

## Abstract

We propose a new way of incorporating temporal information present in videos into Spatial Convolutional Neural Networks (ConvNets) trained on images, that avoids training Spatio-Temporal ConvNets from scratch. We describe several initializations of weights in 3D Convolutional Layers of Spatio-Temporal ConvNet using 2D Convolutional Weights learned from ImageNet. We show that it is important to initialize 3D Convolutional Weights judiciously in order to learn temporal representations of videos. We evaluate our methods on the UCF-101 dataset and demonstrate improvement over Spatial ConvNets.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1503.07274>)

[PDF](<https://arxiv.org/pdf/1503.07274.pdf>)