Browse SoTA > Computer Vision > Action Recognition > Self-Supervised Action Recognition

Self-Supervised Action Recognition

4 papers with code ยท Computer Vision
Subtask of Action Recognition

Benchmarks

Latest papers without code

SpeedNet: Learning the Speediness in Videos

CVPR 2020

We demonstrate how those learned features can boost the performance of self supervised action recognition, and can be used for video retrieval.

SELF-SUPERVISED ACTION RECOGNITION VIDEO RETRIEVAL

SpeedNet: Learning the Speediness in Videos

CVPR 2020

We demonstrate how those learned features can boost the performance of self-supervised action recognition, and can be used for video retrieval.

SELF-SUPERVISED ACTION RECOGNITION VIDEO RETRIEVAL

Self-Supervised Spatio-Temporal Representation Learning Using Variable Playback Speed Prediction

5 Mar 2020

Without semantic labels, we learn the spatio-temporal representation of the video by leveraging the variations in the visual appearance according to different playback speeds under the assumption of temporal coherence.

REPRESENTATION LEARNING SELF-SUPERVISED ACTION RECOGNITION SELF-SUPERVISED LEARNING

Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction

CVPR 2019

Our method can learn the spatiotemporal representation of the video by predicting the order of shuffled clips from the video.

SELF-SUPERVISED ACTION RECOGNITION

Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction

28 Nov 2018

The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections.

SELF-SUPERVISED ACTION RECOGNITION VIDEO UNDERSTANDING

Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles

24 Nov 2018

Self-supervised tasks such as colorization, inpainting and zigsaw puzzle have been utilized for visual representation learning for still images, when the number of labeled images is limited or absent at all.

COLORIZATION REPRESENTATION LEARNING SELF-SUPERVISED ACTION RECOGNITION

Learning and Using the Arrow of Time

CVPR 2018

We seek to understand the arrow of time in videos -- what makes videos look like they are playing forwards or backwards?

SELF-SUPERVISED ACTION RECOGNITION VIDEO FORENSICS

Self-Supervised Video Representation Learning With Odd-One-Out Networks

CVPR 2017

On action classification, our method obtains 60. 3\% on the UCF101 dataset using only UCF101 data for training which is approximately 10% better than current state-of-the-art self-supervised learning methods.

ACTION CLASSIFICATION ACTION CLASSIFICATION REPRESENTATION LEARNING SELF-SUPERVISED ACTION RECOGNITION SELF-SUPERVISED LEARNING