The Way Up: A Dataset for Hold Usage Detection in Sport Climbing

• URL: http://arxiv.org/abs/2505.12854v1
• Date: Mon, 19 May 2025 08:41:18 GMT
• Title: The Way Up: A Dataset for Hold Usage Detection in Sport Climbing
• Authors: Anna Maschek, David C. Schedl,
• Abstract summary: We introduce a dataset of 22 annotated climbing videos, providing ground-truth labels for hold locations, usage order, and time of use.<n>We also explore the application of keypoint-based 2D pose-estimation models for detecting hold usage in sport climbing.
• Score: 1.3812010983144802
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Detecting an athlete's position on a route and identifying hold usage are crucial in various climbing-related applications. However, no climbing dataset with detailed hold usage annotations exists to our knowledge. To address this issue, we introduce a dataset of 22 annotated climbing videos, providing ground-truth labels for hold locations, usage order, and time of use. Furthermore, we explore the application of keypoint-based 2D pose-estimation models for detecting hold usage in sport climbing. We determine usage by analyzing the key points of certain joints and the corresponding overlap with climbing holds. We evaluate multiple state-of-the-art models and analyze their accuracy on our dataset, identifying and highlighting climbing-specific challenges. Our dataset and results highlight key challenges in climbing-specific pose estimation and establish a foundation for future research toward AI-assisted systems for sports climbing.

Related papers

• Hand Held Multi-Object Tracking Dataset in American Football [9.92798361398834]
  Multi-Object Tracking (MOT) plays a critical role in analyzing player behavior from videos, enabling performance evaluation.<n>Current MOT methods are often evaluated using publicly available datasets.<n>No standardized dataset has been publicly available, making comparisons between methods difficult.<n>Our results demonstrate that accurate detection and tracking can be achieved even in crowded scenarios.
  arXiv  Detail & Related papers  (2025-11-12T16:15:18Z)
• TrackID3x3: A Dataset and Algorithm for Multi-Player Tracking with Identification and Pose Estimation in 3x3 Basketball Full-court Videos [8.70594963462731]
  We propose the first dataset specifically designed for multi-player tracking, player identification, and pose estimation in 3x3 basketball scenarios.<n>The dataset comprises three distinct subsets (Indoor fixed-camera, Outdoor fixed-camera, and Drone camera footage), capturing diverse full-court camera perspectives and environments.<n>To evaluate performance, we propose a baseline algorithm called Track-ID algorithm, tailored to assess tracking and identification quality.
  arXiv  Detail & Related papers  (2025-03-24T01:55:46Z)
• Deep Learning-Based Object Pose Estimation: A Comprehensive Survey [73.74933379151419]
  We discuss the recent advances in deep learning-based object pose estimation. Our survey also covers multiple input data modalities, degrees-of-freedom of output poses, object properties, and downstream tasks.
  arXiv  Detail & Related papers  (2024-05-13T14:44:22Z)
• Distillation-guided Representation Learning for Unconstrained Gait Recognition [50.0533243584942]
  We propose a framework, termed GAit DEtection and Recognition (GADER), for human authentication in challenging outdoor scenarios. GADER builds discriminative features through a novel gait recognition method, where only frames containing gait information are used. We evaluate our method on multiple State-of-The-Arts(SoTA) gait baselines and demonstrate consistent improvements on indoor and outdoor datasets.
  arXiv  Detail & Related papers  (2023-07-27T01:53:57Z)
• Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats [80.12253291709673]
  We propose a novel affine-combining autoencoder (ACAE) method to perform dimensionality reduction on the number of landmarks. Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model.
  arXiv  Detail & Related papers  (2022-12-29T22:22:49Z)
• Sports Video Analysis on Large-Scale Data [10.24207108909385]
  This paper investigates the modeling of automated machine description on sports video. We propose a novel large-scale NBA dataset for Sports Video Analysis (NSVA) with a focus on captioning.
  arXiv  Detail & Related papers  (2022-08-09T16:59:24Z)
• Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking [98.91894395941766]
  We propose a novel online approach to learning the pose dynamics, which are independent of pose detections in current fame. Specifically, we derive this prediction of dynamics through a graph neural network(GNN) that explicitly accounts for both spatial-temporal and visual information. Experiments on PoseTrack 2017 and PoseTrack 2018 datasets demonstrate that the proposed method achieves results superior to the state of the art on both human pose estimation and tracking tasks.
  arXiv  Detail & Related papers  (2021-06-07T16:36:50Z)
• Temporally Guided Articulated Hand Pose Tracking in Surgical Videos [22.752654546694334]
  Articulated hand pose tracking is an under-explored problem that carries the potential for use in an extensive number of applications.<n>We propose a novel hand pose estimation model, CondPose, which improves detection and tracking accuracy by incorporating a pose prior to its prediction.
  arXiv  Detail & Related papers  (2021-01-12T03:44:04Z)
• TAO: A Large-Scale Benchmark for Tracking Any Object [95.87310116010185]
  Tracking Any Object dataset consists of 2,907 high resolution videos, captured in diverse environments, which are half a minute long on average. We ask annotators to label objects that move at any point in the video, and give names to them post factum. Our vocabulary is both significantly larger and qualitatively different from existing tracking datasets.
  arXiv  Detail & Related papers  (2020-05-20T21:07:28Z)
• Generalizable Pedestrian Detection: The Elephant In The Room [82.37430109152383]
  We find that existing state-of-the-art pedestrian detectors, though perform quite well when trained and tested on the same dataset, generalize poorly in cross dataset evaluation. We illustrate that diverse and dense datasets, collected by crawling the web, serve to be an efficient source of pre-training for pedestrian detection.
  arXiv  Detail & Related papers  (2020-03-19T14:14:52Z)
• augKlimb: Interactive Data-Led Augmentation of Bouldering Training [0.0]
  Climbing is a popular sport, especially indoors, where climbers can train on man-made routes using artificial holds. Various aspects of adding computer-interaction to climbing have been studied in recent years. There is a large space for research into lightweight tools to aid recreational intermediate climbers.
  arXiv  Detail & Related papers  (2020-01-22T10:26:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.