Few-Shot and Weakly Supervised Repetition Counting With Body-Worn Accelerometers

Nishino, Yuuki; Maekawa, Taira; Hara, Takahiro

doi:10.3389/fcomp.2022.925108

Cited by 6 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing datasets for action counting from wearable devices (Mortazavi et al 2014;Nishino, Maekawa, and Hara 2022;Zelman et al 2020;Soro et al 2019b;Prabhu, O'Connor, and Moran 2020;Strömbäck, Huang, and Radu 2020) often lack diversity in terms of both count values and action categories. Additionally, each data sample from these datasets also lacks diversity in terms of the actions contained within the sample, with the actions of interest being the predominant class.…”

Section: The Dwc Datasetmentioning

confidence: 99%

Count What You Want: Exemplar Identification and Few-Shot Counting of Human Actions in the Wild

Huang,

Nguyen,

Nguyen

et al. 2024

AAAI

View full text Add to dashboard Cite

This paper addresses the task of counting human actions of interest using sensor data from wearable devices. We propose a novel exemplar-based framework, allowing users to provide exemplars of the actions they want to count by vocalizing predefined sounds ``one'', ``two'', and ``three''. Our method first localizes temporal positions of these utterances from the audio sequence. These positions serve as the basis for identifying exemplars representing the action class of interest. A similarity map is then computed between the exemplars and the entire sensor data sequence, which is further fed into a density estimation module to generate a sequence of estimated density values. Summing these density values provides the final count. To develop and evaluate our approach, we introduce a diverse and realistic dataset consisting of real-world data from 37 subjects and 50 action categories, encompassing both sensor and audio data. The experiments on this dataset demonstrate the viability of the proposed method in counting instances of actions from new classes and subjects that were not part of the training data. On average, the discrepancy between the predicted count and the ground truth value is 7.47, significantly lower than the errors of the frequency-based and transformer-based methods. Our project, code and dataset can be found at https://github.com/cvlab-stonybrook/ExRAC.

show abstract

Section: The Dwc Datasetmentioning

confidence: 99%

Count What You Want: Exemplar Identification and Few-Shot Counting of Human Actions in the Wild

Huang,

Nguyen,

Nguyen

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…An automated segmentation way and labeling of single-channel or multimodal biosignal data using a self-similarity matrix (SSM), generated with the feature-based representation of the signals, is proposed by the authors in [30]. Examples of data with the few-shot learning were employed by Nishino et al [31] to recognize workouts using a wearable sensor including data augmentation and diversification techniques for their data to achieve repetition counting.…”

Section: Introductionmentioning

confidence: 99%

Counting Activities Using Weakly Labeled Raw Acceleration Data: A Variable-Length Sequence Approach with Deep Learning to Maintain Event Duration Flexibility

Sopidis

Haslgrübler

Ferscha

2023

Sensors

View full text Add to dashboard Cite

This paper presents a novel approach for counting hand-performed activities using deep learning and inertial measurement units (IMUs). The particular challenge in this task is finding the correct window size for capturing activities with different durations. Traditionally, fixed window sizes have been used, which occasionally result in incorrectly represented activities. To address this limitation, we propose segmenting the time series data into variable-length sequences using ragged tensors to store and process the data. Additionally, our approach utilizes weakly labeled data to simplify the annotation process and reduce the time to prepare annotated data for machine learning algorithms. Thus, the model receives only partial information about the performed activity. Therefore, we propose an LSTM-based architecture, which takes into account both the ragged tensors and the weak labels. To the best of our knowledge, no prior studies attempted counting utilizing variable-size IMU acceleration data with relatively low computational requirements using the number of completed repetitions of hand-performed activities as a label. Hence, we present the data segmentation method we employed and the model architecture that we implemented to show the effectiveness of our approach. Our results are evaluated using the Skoda public dataset for Human activity recognition (HAR) and demonstrate a repetition error of ±1 even in the most challenging cases. The findings of this study have applications and can be beneficial for various fields, including healthcare, sports and fitness, human–computer interaction, robotics, and the manufacturing industry.

show abstract

“…Repetition counting takes advantage of the repeating motion patterns seen during an exercise set with multiple repetitions (see Figure 1 ). A change in the repetition phase (eccentric and concentric) of the exercise is represented by peaks and troughs in the inertial signal of interest [ 16 , 17 ]. Most studies on repetition counting start with a pre-processing step to smooth and remove the noise typically found in inertial data.…”

Section: Introductionmentioning

confidence: 99%

LEAN: Real-Time Analysis of Resistance Training Using Wearable Computing

Coates

Wahlström

2023

Sensors

View full text Add to dashboard Cite

The use of fitness apps to track physical exercise has been proven to promote weight loss and increase physical activity. The most popular forms of exercise are cardiovascular training and resistance training. The overwhelming majority of cardio tracking apps automatically track and analyse outdoor activity with relative ease. In contrast, nearly all commercially available resistance tracking apps only record trivial data, such as the exercise weight and repetition number via manual user input, a level of functionality not far from that of a pen and paper. This paper presents LEAN, a resistance training app and exercise analysis (EA) system for both the iPhone and Apple Watch. The app provides form analysis using machine learning, automatic repetition counting in real time, and other important but seldom studied exercise metrics, such as range of motion on a per-repetition level and average repetition time. All features are implemented using lightweight inference methods that enable real-time feedback on resource-constrained devices. The performance evaluation includes a user survey and benchmarking of all data science features using both ground-truth data from complementary modalities and comparisons with commercial apps.

show abstract

Few-Shot and Weakly Supervised Repetition Counting With Body-Worn Accelerometers

Cited by 6 publications

References 24 publications

Count What You Want: Exemplar Identification and Few-Shot Counting of Human Actions in the Wild

Count What You Want: Exemplar Identification and Few-Shot Counting of Human Actions in the Wild

Counting Activities Using Weakly Labeled Raw Acceleration Data: A Variable-Length Sequence Approach with Deep Learning to Maintain Event Duration Flexibility

LEAN: Real-Time Analysis of Resistance Training Using Wearable Computing

Contact Info

Product

Resources

About