Repetitive Action Counting

5 papers with code • 3 benchmarks • 3 datasets

Repetitive action counting aims to count the number of repetitive actions in a video.

Most implemented papers

Counting Out Time: Class Agnostic Video Repetition Counting in the Wild

materight/RepNet-pytorch CVPR 2020

We present an approach for estimating the period with which an action is repeated in a video.

TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting

sviprepetitioncounting/transrac CVPR 2022

Existing methods focus on performing repetitive action counting in short videos, which is tough for dealing with longer videos in more realistic scenarios.

PoseRAC: Pose Saliency Transformer for Repetitive Action Counting

miracledance/poserac 15 Mar 2023

Moreover, we introduce a pose-level method, PoseRAC, which is based on this representation and achieves state-of-the-art performance on two new version datasets by using Pose Saliency Annotation to annotate salient poses for training.

Every Shot Counts: Using Exemplars for Repetition Counting in Videos

sinhasaptarshi/EveryShotCounts 26 Mar 2024

We propose an exemplar-based approach that discovers visual correspondence of video exemplars across repetitions within target videos.

Rethinking temporal self-similarity for repetitive action counting

Luoadore/RACnet 12 Jul 2024

The number of repeated actions is then inferred from the action start probabilities.