mlsanityData to 14 Oct 2026

PoseSync: Robust pose based video synchronization

arXiv 2308.12600 ↗First posted 24 Aug 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Pose based video sychronization can have applications in multiple domains such as gameplay performance evaluation, choreography or guiding athletes. The subject's actions could be compared and evaluated against those performed by professionals side by side. In this paper, we propose an end to end pipeline for synchronizing videos based on pose. The first step crops the region where the person present in the image followed by pose detection on the cropped image. This is followed by application of Dynamic Time Warping(DTW) on angle/ distance measures between the pose keypoints leading to a scale and shift invariant pose matching pipeline.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 6 of its 17 references that are in the map. First posted on arXiv 24 Aug 2023.

Builds on

6 of 17 references.

References · 6

  1. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  4. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  5. 2020TransPose: Keypoint Localization via Transformercited by 126
  6. 2020UniPose: Unified Human Pose Estimation in Single Images and Videoscited by 49

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.