WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition

• URL: http://arxiv.org/abs/2304.05088v4
• Date: Tue, 15 Oct 2024 07:48:59 GMT
• Title: WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition
• Abstract summary: We introduce WEAR, an outdoor sports dataset for both vision- and inertial-based human activity recognition (HAR) Data from 22 participants performing a total of 18 different workout activities was collected with synchronized inertial (acceleration) and camera (egocentric video) data recorded at 11 different outside locations. Benchmark results show that through our sensor placement, each modality interestingly offers complementary strengths and weaknesses in their prediction performance.
• Score: 22.988658969594276
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Research has shown the complementarity of camera- and inertial-based data for modeling human activities, yet datasets with both egocentric video and inertial-based sensor data remain scarce. In this paper, we introduce WEAR, an outdoor sports dataset for both vision- and inertial-based human activity recognition (HAR). Data from 22 participants performing a total of 18 different workout activities was collected with synchronized inertial (acceleration) and camera (egocentric video) data recorded at 11 different outside locations. WEAR provides a challenging prediction scenario in changing outdoor environments using a sensor placement, in line with recent trends in real-world applications. Benchmark results show that through our sensor placement, each modality interestingly offers complementary strengths and weaknesses in their prediction performance. Further, in light of the recent success of single-stage Temporal Action Localization (TAL) models, we demonstrate their versatility of not only being trained using visual data, but also using raw inertial data and being capable to fuse both modalities by means of simple concatenation. The dataset and code to reproduce experiments is publicly available via: mariusbock.github.io/wear/.

Related papers

• HARMES: A Multi-Modal Dataset for Wearable Human Activity Recognition with Motion, Environmental Sensing and Sound [22.090898322586824]
  This work introduces HARMES, a multi-modal wearable dataset combining three wrist-recorded modalities.<n>HarMES totals over 80 hours of recorded data, with approximately three hours of labeled activity data per participant.<n>To the best of our knowledge, HARMES is the first dataset to combine this particular sensor trio.
  arXiv  Detail & Related papers  (2026-05-04T13:47:41Z)
• StrengthSense: A Dataset of IMU Signals Capturing Everyday Strength-Demanding Activities [3.091489211147152]
  textitStrengthSense is an open dataset that encompasses IMU signals capturing strength-demanding activities.<n>The dataset was collected from 29 healthy subjects utilizing 10 IMUs placed on limbs and the torso.
  arXiv  Detail & Related papers  (2025-10-30T15:41:28Z)
• LookOut: Real-World Humanoid Egocentric Navigation [61.14016011125957]
  We introduce the challenging problem of predicting a sequence of future 6D head poses from an egocentric video.<n>To solve this task, we propose a framework that reasons over temporally aggregated 3D latent features.<n>Motivated by the lack of training data in this space, we present a dataset collected through this approach.
  arXiv  Detail & Related papers  (2025-08-20T06:43:36Z)
• DISCOVER: Data-driven Identification of Sub-activities via Clustering and Visualization for Enhanced Activity Recognition in Smart Homes [52.09869569068291]
  We introduce DISCOVER, a method to discover fine-grained human sub-activities from unlabeled sensor data without relying on pre-segmentation. We demonstrate its effectiveness through a re-annotation exercise on widely used HAR datasets.
  arXiv  Detail & Related papers  (2025-02-11T20:02:24Z)
• Advancing Location-Invariant and Device-Agnostic Motion Activity Recognition on Wearable Devices [6.557453686071467]
  We conduct a comprehensive evaluation of the generalizability of motion models across sensor locations. Our analysis highlights this challenge and identifies key on-body locations for building location-invariant models. We present deployable on-device motion models reaching 91.41% frame-level F1-score from a single model irrespective of sensor placements.
  arXiv  Detail & Related papers  (2024-02-06T05:10:00Z)
• Learning Human Action Recognition Representations Without Real Humans [66.61527869763819]
  We present a benchmark that leverages real-world videos with humans removed and synthetic data containing virtual humans to pre-train a model. We then evaluate the transferability of the representation learned on this data to a diverse set of downstream action recognition benchmarks. Our approach outperforms previous baselines by up to 5%.
  arXiv  Detail & Related papers  (2023-11-10T18:38:14Z)
• VALERIE22 -- A photorealistic, richly metadata annotated dataset of urban environments [5.439020425819001]
  The VALERIE tool pipeline is a synthetic data generator developed to contribute to the understanding of domain-specific factors. The VALERIE22 dataset was generated with the VALERIE procedural tools pipeline providing a photorealistic sensor simulation. The dataset provides a uniquely rich set of metadata, allowing extraction of specific scene and semantic features.
  arXiv  Detail & Related papers  (2023-08-18T15:44:45Z)
• Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment [71.16699226211504]
  We propose to learn fine-grained action features that are invariant to the viewpoints by aligning egocentric and exocentric videos in time. To this end, we propose AE2, a self-supervised embedding approach with two key designs. For evaluation, we establish a benchmark for fine-grained video understanding in the ego-exo context.
  arXiv  Detail & Related papers  (2023-06-08T19:54:08Z)
• Do I Have Your Attention: A Large Scale Engagement Prediction Dataset and Baselines [9.896915478880635]
  The degree of concentration, enthusiasm, optimism, and passion displayed by individual(s) while interacting with a machine is referred to as user engagement' To create engagement prediction systems that can work in real-world conditions, it is quintessential to learn from rich, diverse datasets. Large scale multi-faceted engagement in the wild dataset EngageNet is proposed.
  arXiv  Detail & Related papers  (2023-02-01T13:25:54Z)
• Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning [21.68009790164824]
  We present a multi-modal egocentric activity dataset for continual learning named UESTC-MMEA-CL. It contains synchronized data of videos, accelerometers, and gyroscopes, for 32 types of daily activities, performed by 10 participants. Results of egocentric activity recognition are reported when using separately, and jointly, three modalities: RGB, acceleration, and gyroscope.
  arXiv  Detail & Related papers  (2023-01-26T04:32:00Z)
• Video-based Pose-Estimation Data as Source for Transfer Learning in Human Activity Recognition [71.91734471596433]
  Human Activity Recognition (HAR) using on-body devices identifies specific human actions in unconstrained environments. Previous works demonstrated that transfer learning is a good strategy for addressing scenarios with scarce data. This paper proposes using datasets intended for human-pose estimation as a source for transfer learning.
  arXiv  Detail & Related papers  (2022-12-02T18:19:36Z)
• Multi-Environment Pretraining Enables Transfer to Action Limited Datasets [129.24823721649028]
  In reinforcement learning, available data of decision making is often not annotated with actions. We propose combining large but sparsely-annotated datasets from a emphtarget environment of interest with fully-annotated datasets from various other emphsource environments. We show that utilizing even one additional environment dataset of sequential labelled data during IDM pretraining gives rise to substantial improvements in generating action labels for unannotated sequences.
  arXiv  Detail & Related papers  (2022-11-23T22:48:22Z)
• HighlightMe: Detecting Highlights from Human-Centric Videos [52.84233165201391]
  We present a domain- and user-preference-agnostic approach to detect highlightable excerpts from human-centric videos. We use an autoencoder network equipped with spatial-temporal graph convolutions to detect human activities and interactions. We observe a 4-12% improvement in the mean average precision of matching the human-annotated highlights over state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-10-05T01:18:15Z)
• TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild [77.59069361196404]
  TRiPOD is a novel method for predicting body dynamics based on graph attentional networks. To incorporate a real-world challenge, we learn an indicator representing whether an estimated body joint is visible/invisible at each frame. Our evaluation shows that TRiPOD outperforms all prior work and state-of-the-art specifically designed for each of the trajectory and pose forecasting tasks.
  arXiv  Detail & Related papers  (2021-04-08T20:01:00Z)

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.