Combining embedded accelerometers with computer vision for recognizing food preparation activities
The DOI matches its Crossref record; 32 of the 33 references it cites were found in a registry or an index.
Abstract
This paper introduces a publicly available dataset of complex activities that involve manipulative gestures. The dataset captures people preparing mixed salads and contains more than 4.5 hours of accelerometer and RGB-D video data, detailed annotations, and an evaluation protocol for comparison of activity recognition algorithms. Providing baseline results for one possible activity recognition task, this paper further investigates modality fusion methods at different stages of the recognition pipeline: (i) prior to feature extraction through accelerometer localization, (ii) at feature level via feature concatenation, and (iii) at classification level by combining classifier outputs. Empirical evaluation shows that fusing information captured by these sensor types can considerably improve recognition performance.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The 50Salads dataset contains 50 videos with 17 action classes.”
From MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation (2023) · cites this paper as [25]
In the citing paper
“Our model achieves state-of-the-art results on three challenging datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset.”
From MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation (2023) · cites this paper as [25]
Citations
Cites
A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection
Kohavi, R. (1995) · Zenodo · doi:10.5281/zenodo.19712698 · Cited by 10,909
Kittler, J., Hatef, M., Duin, R. P. W., & Matas, J. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.667881 · Cited by 5,290 · cited 2×
“For classifier fusion we tried the sum-rule and the product-rule [11] as well as Random Decision Forests as a non-linear combination method.”
MethodRecognizing human actions: A local SVM approach
Schüldt, C., Laptev, I., & Barbara Caputo, B. (2004) · Cited by 2,906
Laptev, I. (2005) · International Journal of Computer Vision · doi:10.1007/s11263-005-1838-7 · Cited by 2,629
Action recognition by dense trajectories
Wang, H., Klaser, A., Schmid, C., & Liu, C.-L. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995407 · Cited by 2,154 · cited 3×
“In addition to yielding low recognition performance, extracting local descriptors around densely sampled locations as proposed in [26] is computationally demanding in real-time, e.”
BackgroundMethodHuman activity analysis: A review
Aggarwal, J. K., & Ryoo, M. S. (2011) · ACM Computing Surveys · doi:10.1145/1922649.1922653 · Cited by 2,056
Marszalek, M., Laptev, I., & Schmid, C. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206557 · Cited by 1,168 · cited 3×
“, KTH [23], YouTube [14], Hollywood2 [15] and URADL [17]).”
BackgroundRecognizing realistic actions from videos “in the wild”
Liu, J., Luo, J., & Shah, M. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206744 · Cited by 1,075
Collecting complex activity datasets in highly rich networked sensor environments
Roggen, D., Calatroni, A., Rossi, M., Holleczek, T., Forster, K., Troster, G., Lukowicz, P., Bannach, D., Pirkl, G., Ferscha, A., et al. (2010) · 2010 Seventh International Conference on Networked Sensing Systems (INSS) · doi:10.1109/inss.2010.5573462 · Cited by 788
Criminisi, A. (2011) · now publishers, Inc. eBooks · doi:10.1561/9781601985415 · Cited by 703
Research works printed but not linked: 6
- 10.5555/2029024 · doi:10.5555/2029024
- 10.5555/2283516.2283683 · doi:10.5555/2283516.2283683
- M. E. Pollack . Intelligent technology for an aging population: The use of AI to assist elders with cognitive impairment . AI Magazine , 26 ( 2 ), 2005 . M. E. Pollack. Intelligent technology for an aging population: The use of AI to assist elders with cognitive impairment. AI Magazine, 26(2), 2005.
- 10.5555/2354409.2354909 · doi:10.5555/2354409.2354909
- 10.5555/1018429.1020906 · doi:10.5555/1018429.1020906
- 10.5555/1786014.1786017 · doi:10.5555/1786014.1786017
Cited by
Items 401–447 of 447
MS-MH-TCN: Multi-Stage and Multi-Head Temporal Convolutional Network for Action Segmentation
Kang, Z., & Chu, Z. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-0885-7_5
SmallTAL: Real-Time Egocentric Online Temporal Action Localization for the Data-Impoverished
Joyce, E. C., Chen, Y., Neeter, E., & Mordohai, P. (2023) · PRESENCE Virtual and Augmented Reality · doi:10.1162/pres_a_00408
“The Max Planck cooking set (Rohrbach et al., 2012), 50 Salads (Stein & McKenna, 2013), and Breakfast (Kuehne et al., 2014) come closer to our use-case in that they focus on procedural tasks executed by single actors.”
BackgroundImproved Sliding Window Smoothing for Video Temporal Action Segmentation and Recognition
Li, C., Tian, Y., Sheng, L., Chen, J., Wang, T., & Wei, X. (2023) · China Automation Congress (CAC) · doi:10.1109/cac59555.2023.10450614
Boundary-Match U-Shaped Temporal Convolutional Network for Vulgar Action Segmentation
Shen, Z., Xu, R., Zhang, Y., Qin, F., Ge, R., Wang, C., & Toyoura, M. (2024) · Mathematics · doi:10.3390/math12060899
Boundary-sensitive denoised temporal reasoning network for video action segmentation
Ma, Z., & Li, K. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03199-w
“The 50Salads [19] dataset contains 50 videos of 17 action categories for preparing salad activities.”
ASGSA: global semantic-aware network for action segmentation
Bian, Q., Zhang, C., Ren, K., Yue, T., & Zhang, Y. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09776-x
“Due to the massive human labor required for labeling untrimmed long videos, the sizes of action segmentation datasets [16–18] are relatively limited.”
InfluentialImproving Temporal Action Segmentation and Detection with Hierarchical Task Grammar
Yihui, Q., & Rajan, D. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78110-0_13 · Cited by 2
SteadySeg: Improving maritime trajectory staging by steadiness recognition
Qiu, S., Luo, Y., Luo, Q., & Tang, J. (2024) · Ocean Engineering · doi:10.1016/j.oceaneng.2024.120136 · Cited by 1
Semantic Smoothness Optimization via Graph-CutEnergy Minimization for Temporal Action SegmentationPreprint
Ansari, M., & Fazl-Ersi, E. (2025) · Research Square · doi:10.21203/rs.3.rs-5946071/v1
DLM-VMTL:A Double LayerMapper For Heterogeneous Data Video Multi-Task Prompt Learning
Bo, Z., Jin, Y., & Sun, W. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888058
“Action Segmentation: We used 50salads[29], Breakfast[30] and gtea[31].”
Cluster-Refined Optimal Transport for Unsupervised Action Segmentation
Wang, S., Zhang, J., Liu, Y., Li, S., & Feng, L. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10887693
“The 50Salads dataset [24] consists of 50 videos, and each video contains 19 action classes.”
Learning Improved Dense Trajectories in Guided Feature Space
Verma, D., & Nigam, N. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.457
Long, X., Wang, S., & Chen, Y. (2025) · Sensors · doi:10.3390/s25185644
2s-TAS: Two-Stream Transformer for Multi-modal Human Action Segmentation
Guo, X., Li, C., Jiang, Z., & Wan, F. (2025) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew68306.2025.11152185 · Cited by 1
“50Salads [18] dataset contains 50 videos of salad making at an FPS of 30.”
Flexible Streaming Temporal Action Segmentation with Diffusion Models
Zhang, J., Wen, W., Liu, S., Zhang, S., Ding, Y., & Feng, L. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11210093 · Cited by 1
“Three datasets (Gtea [21], 50Salads [22], and Breakfast [23]) are used to evaluate our method.”
Unsupervised Temporal Action Segmentation Based on Wavelet Feature Processing
Lin, X., Zhang, J., & Feng, L. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229403
Fine-grained Action Segmentation Network Based on Boundary Perception
Liu, Z., Chen, Y., Zhang, S., Tang, M., & Li, J. (2025) · International Conference on Intelligent Perception and Computer Vision (CIPCV) · doi:10.1109/cipcv65863.2025.00013
“Due to possible differences in the experimental environment, this experiment focuses on comparing the proposed algorithm with the results reproduced by ASRF [41].”
InfluentialFLICSNet: A Novel Framework for Cooking Action Segmentation from Video
Khanna, S., Chattopadhyay, C., & Kundu, S. (2025) · doi:10.1145/3746264.3760478
Temporal2Seq: A Unified Framework for Temporal VideoUnderstanding TasksPreprint
Yang, M., Zhang, Z., & Wang, L. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5899043
CaASR: A Causal Lens for Refining Temporal Action Segmentation
Du, K., Yang, X., & Chen, H. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3664960
Difformer for Action Segmentation
Aziere, N., Wang, T., & Todorović, S. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00314 · Cited by 2
“Our experimental results demonstrate that Difformer outperforms SOTA models on the benchmark Breakfast [29], GTEA [15], 50Salads [43], and Assembly101 [39] datasets, while also reducing both the number of model parameters and overall time complexity.”
InfluentialLow-Confidence Nearest Neighbor Substitution for Human-Centric Action Segmentation
Wang, X.-Z., Li, J.-J., Shan-qing, Z., Huang, Y., & Chang, C.-C. (2026) · 電腦學刊 · doi:10.63367/199115992026023701016
Recognition and Modeling of Manipulation Actions
Bakr, N. A. (2020) · theses.fr (ABES) · doi:10.70675/165d1ebez10d8z4384zb307zb6d622a552a0
Learning to localize goal-oriented actions with weak supervision
Zhukov, D. (2021) · theses.fr (ABES) · doi:10.70675/46949df1z20a0z45b9zaa69ze59147934f9d
Learning effective video representations for action recognition
Yang, D. (2024) · theses.fr (ABES) · doi:10.70675/4046013fz7818z4acdza84bze9be293f2334 · Cited by 1
Measuring and Reducing Intrinsic Boundary Noise in Temporal Action Segmentation
Matsuoka, T., & Satoh, S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462721
Video feature guidance for temporal action segmentation
Li, Y., Fu, Z., & Gao, R. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00734-2
Xu, M., Zhang, J., Fan, J., Xiao, C., Liu, S., Wang, Z., & Feng, L. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116065
Tang, Z., Krishnan, R. M., Yu, Z., & Sun, C. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00435 · Cited by 1
“Whereas most of the existing procedural video benchmarks are sourced from daily household scenarios [10, 19, 20, 26, 51, 53], the Spacewalk-18 dataset comprises video clips from 18 recorded extravehic-This WACV paper is the Open Access version, provided by the Computer Vision Foundation.”
Learning Action Hierarchies via Hybrid Geometric Diffusion
Kaushik, A. R., Ratha, N., & Govindaraju, V. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00306
“We evaluate our approach on three widely used benchmarks for TAS: GTEA [23], 50Salads [65], and Break-fast [40].”
InfluentialUnsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities
Yang, F., Xie, Q., Moteki, A., Masui, S., Jiang, S., Uchino, K., Bisk, Y., & Neubig, G. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00564 · Cited by 1
“We compare our work with prior SAS studies [4, 26, 28, 40, 49, 72, 79, 81] across diverse applications.”
Everyday Activity Science and Engineering Table Setting Dataset
Meier, M., Hartmann, Y., Ouahabi, Y. E., Bredereke, L., Putze, F., & Schultz, T. (2026) · Scientific Data · doi:10.1038/s41597-026-07077-7 · Cited by 1
Li, Z., Wen, Y., Yang, L., Pan, J., & Zhou, P. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2026.3695575
Beyond image generation: visual data analysis with diffusion models—a comprehensive survey
Olechno, B., & Mańdziuk, J. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11615-5
Learning Probabilistic Embeddings for Unsupervised Action Segmentation
Li, S., Vu, D. M., & Gall, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37429-5_25 · Cited by 1
Egocentric Online Action Segmentation via Parametric Context Memory Learning
Jiang, X., Xu, X., Liu, C., Wang, Z., Song, J., Sun, Z., Cichocki, A. S., & Shen, H. T. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3714835 · Cited by 3
“3) Cross-View Generalization on Third-Person Videos: To further validate the generalizability of our PCML paradigm beyond egocentric domains, we conduct preliminary experiments on the 50Salads dataset [59], a widely used third-person benchmark for temporal action segmentation.”
PAL: Predictive Action Logic for online action segmentation
Xu, T., Zhang, R., Tian, X., Chen, Y., Zheng, Z., & Zhou, J. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104891
Improving Temporal Action Segmentation via Constraint-Aware Decoding
Ee, Y. K., Roy, D., Li, C., Zhang, H., & Fernando, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31452-9_5
Deep Kernel Video Approximation for Unsupervised Action Segmentation
Pintea, S. L., & Dijkstra, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31335-5_3
EgoDatasets: A Dataset-Centric Survey and Taxonomy for Egocentric Vision and Action Anticipation
Mitsou, A., & Spyrou, E. (2026) · Applied Sciences · doi:10.3390/app162010268
He, S., Guo, Y., Kou, J., Kang, J., Tao, S., & Feng, L. (2026) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot70864.2026.00024
“The 50Salads dataset [25] consists of 50 videos recording the process of making salads.”
Adaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensation
Gauthier-Villar, A., Ding, G., & Yao, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37359-5_21
Causal Yet Future-Aware: Dual-Path Temporal Modeling for Online Action Segmentation
Zheng, Z., Ma, P., Zhou, Y., Kong, L., & Zhou, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37321-2_37
Action-incrementer: Action-incremental learning for temporal action segmentation
Kim, G.-H., Jin, H., Han, D., & Kim, E. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104963
Bridging Design and Quality: A Technical Overview of IFMs in Manufacturing
Hsu, C.-F., Chiou, Y.-H., Huang, P., Liao, Y.-C., Yang, S. H., Tang, J.-Z., Chang, Y.-L., & Chang, M.-C. (2026) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr70517.2026.00009
“Early benchmarks such as Breakfast [63], 50 Salads [64], and YouTube Instructions [65] focus on long-horizon instructional videos.”
Stein, S. (2014)
Self-citation
Metadata
- Authors
- Stein, S., & McKenna, S. J.
- Affiliations
- University of Dundee (GB)
- Venue
- Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing
- Publisher
- ACM
- Published
- 2013-09-08
- Pages
- 729-738
- OpenAlex
- W2109698606
- Cited by
- 448
- References
- 33
- Citations by year
- 2026: 26 · 2025: 41 · 2024: 56 · 2023: 56 · 2022: 54 · 2021: 50 · 2020: 37 · 2019: 49 · 2018: 26 · 2017: 15 · 2016: 24 · 2015: 7 · 2014: 5 · 2013: 2
- FWCI
- 8.08
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) (publishedVersion)
- Discovery Research Portal (University of Dundee) (submittedVersion)
- ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam) (submittedVersion)
- Funders
- Research Councils UK
- Engineering and Physical Sciences Research Council (EP/G066019/1)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Keywords
- activity recognition, embedded accelerometers, RGB-D video, multimodal fusion, cooking, salad preparation, node localization, feature-level fusion, annotated dataset
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.