Saved in:
Bibliographic Details
Main Authors: Sinha, Saptarshi, Stergiou, Alexandros, Damen, Dima
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.18074
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916435891060736
author Sinha, Saptarshi
Stergiou, Alexandros
Damen, Dima
author_facet Sinha, Saptarshi
Stergiou, Alexandros
Damen, Dima
contents Video repetition counting infers the number of repetitions of recurring actions or motion within a video. We propose an exemplar-based approach that discovers visual correspondence of video exemplars across repetitions within target videos. Our proposed Every Shot Counts (ESCounts) model is an attention-based encoder-decoder that encodes videos of varying lengths alongside exemplars from the same and different videos. In training, ESCounts regresses locations of high correspondence to the exemplars within the video. In tandem, our method learns a latent that encodes representations of general repetitive motions, which we use for exemplar-free, zero-shot inference. Extensive experiments over commonly used datasets (RepCount, Countix, and UCFRep) showcase ESCounts obtaining state-of-the-art performance across all three datasets. Detailed ablations further demonstrate the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2403_18074
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Every Shot Counts: Using Exemplars for Repetition Counting in Videos
Sinha, Saptarshi
Stergiou, Alexandros
Damen, Dima
Computer Vision and Pattern Recognition
Image and Video Processing
Video repetition counting infers the number of repetitions of recurring actions or motion within a video. We propose an exemplar-based approach that discovers visual correspondence of video exemplars across repetitions within target videos. Our proposed Every Shot Counts (ESCounts) model is an attention-based encoder-decoder that encodes videos of varying lengths alongside exemplars from the same and different videos. In training, ESCounts regresses locations of high correspondence to the exemplars within the video. In tandem, our method learns a latent that encodes representations of general repetitive motions, which we use for exemplar-free, zero-shot inference. Extensive experiments over commonly used datasets (RepCount, Countix, and UCFRep) showcase ESCounts obtaining state-of-the-art performance across all three datasets. Detailed ablations further demonstrate the effectiveness of our method.
title Every Shot Counts: Using Exemplars for Repetition Counting in Videos
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2403.18074