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 301–400 of 447
Pan, Z., & Yu, Y. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104203 · Cited by 3
CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation
Bueno-Benito, E., & Dimiccoli, M. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00998 · Cited by 3
“Ablation Study on the four datasets: Breakfast [21], YTI [2], 50Salads [42] and Desktop Assembly [23] , Activity-level.”
Timestamp Query Transformer for Temporal Action Segmentation
Wang, T., & Todorović, S. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00487 · Cited by 3
“For evaluation, we use the following benchmark datasets: GTEA [15], 50Salads [37] and Breakfast [18].”
On Multi-modal Fusion for Freehand Gesture Recognition
Schak, M., & Gepperth, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-61609-0_68 · Cited by 3
“A different fusion method at the classifier level is the non-linear combination method of using a Random Decision Forest [17].”
End-to-End Action Segmentation Transformer
Wang, T., & Todorović, S. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00313 · Cited by 3
“For evaluation, we use the GTEA [10], 50Salads [33], Breakfast [17], and Assembly101 [30] datasets.”
Positive and Negative Set Designs in Contrastive Feature Learning for Temporal Action Segmentation
Chen, Y.-C., & Chu, W.-T. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3417392 · Cited by 4
“Following the approach of most TAS methods, we evaluate performance based on three datasets: the Breakfast dataset [2], the 50Salads dataset [1], and the GTEA dataset [45].”
Not all samples are equal: Boosting action segmentation via selective incremental learning
Huang, F., Chen, X.-D., Wu, W., & Ma, W. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110334 · Cited by 5
Real-Time Video-Based Human Action Recognition on Embedded Platforms
Wang, R., Wang, Z., Gao, P., Li, M., Jeong, J., Xu, Y., Lee, Y., Baum, C. M., Connor, L. T., & Lu, C. (2025) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3761795 · Cited by 12
“The first benchmark, 50 Salads [54], comprises 50 top-view recordings at 30 FPS, capturing various steps involved in making salads.”
InfluentialTencent AVS: A Holistic Ads Video Dataset for Multi-Modal Scene Segmentation
Jiang, J., Li, Z., Xiong, J., Quan, R., Lu, Q., & Liu, W. (2022) · IEEE Access · doi:10.1109/access.2022.3227425 · Cited by 4
“These datasets commonly contain instructional videos [30,55,57] with human performing fine-grained actions and require algorithms to predict an action label for each frame with only visual information.”
BackgroundWeakly-Supervised Dense Action Anticipation
Zhang, H., Chen, F., & Yao, A. (2021) · British Machine Vision Conference (BMVC) · doi:10.5244/c.35.247 · Cited by 6
A Multimodal Benchmark Tool for Automated Eating Behaviour Recognition
Kakra, V. D., van der Aa, N. P., Noldus, L. P. J. J., Amft, O., Spink, A., Loijens, L. W. S., & Wołoszynowska-Fraser, M. U. (2014) · Cited by 3
Local depth patterns for fine-grained activity recognition in depth videos
Awwad, S., & Piccardi, M. (2016) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2016.7804453 · Cited by 3
Maekawa, T., Masuda, A., & Namioka, Y. (2016) · International Conference on Mobile and Ubiquitous Multimedia (MUM) · doi:10.1145/3012709.3012715 · Cited by 5
“…we focus on a ceiling-mounted depth camera that over-looks a table, which has already been used in many existing tabletop studies [15, 18, 25, 31, 37] related to recognizing assembly work in a factory, CSCW for tabletop displays, interactive dining tables, recognizing food preparation…”
BackgroundTask-Specific Surgical Skill Assessment with Neural Networks
Benmansour, M., Handouzi, W., & Malti, A. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-11884-6_15 · Cited by 3
Double Attention Network Based on Sparse Sampling
Dong, Z., Li, Y., Sun, Y., Hao, C., Liu, K., Sun, T., & Liu, S. (2022) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme52920.2022.9859819 · Cited by 3
“Combined with ASRF and BCN, it achieves state-of-the-art results on the standard benchmarks 50Salads [11], GTEA [12] and Breakfast [13].”
MethodWei, L., & Ye, Y. (2022) · Displays · doi:10.1016/j.displa.2022.102212 · Cited by 3
Rohrbach, M. (2014) · Max Planck Digital Library · doi:10.22028/d291-26562 · Cited by 3
“Here and similar in (Farhadi et al., 2010a; Fathi et al., 2011; Stein and McKenna, 2013) the camera view mainly shows hands and manipulated cooking ingredients.”
BackgroundHistogram of Oriented Depth Gradients for Action RecognitionPreprint
Bakr, N. A., & Crowley, J. L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.09477 · Cited by 3
“Experiments are performed on two publicly available datasets : 50 salads [1] and Actions of Cooking Eggs (ACE) [2].”
MethodLocally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection.Preprint
Mac, K.-N. C., Joshi, D., Yeh, R. A., Xiong, J., Feris, R., & Do, M. N. (2018) · arXiv (Cornell University) · Cited by 3
A multivariate Markov chain model for interpretable dense action anticipation
Qiu, Y., & Rajan, D. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127285 · Cited by 4
COM Kitchens: An Unedited Overhead-View Video Dataset as a Vision-Language Benchmark
Maeda, K., Hirasawa, T., Hashimoto, A., Harashima, J., Rybicki, L., Fukasawa, Y., & Ushiku, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73650-6_8 · Cited by 7
Cluster Assumption-Guided Timestamp-Supervised Temporal Action Segmentation
Ren, Z., Li, G., Cheng, N., Wu, A., Wang, N., & Gao, X. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3535331 · Cited by 3
“Finally,exten-siveexperimentsonthreebenchmarks, i.e. , GTEA [17], 50sal-ads [48], and Breakfast [25] show that the proposed method outperforms current state-of-the-art TS-TAS methods, and even achieve comparable results to fully-supervised methods.”
Unsupervised Action Segmentation via Multi-Scale Temporal-Interaction Enhancement
Song, Z.-Y., Chen, K.-X., Wang, P., Song, M.-L., & Zheng, N. (2026) · IEEE transactions on circuits and systems for video technology (Print) · doi:10.1109/tcsvt.2025.3596325 · Cited by 4
“50Salads [52] is a smaller dataset containing only 5.5 hours of video, in which individuals prepare mixed salads.”
InfluentialImproving action segmentation via explicit similarity measurement
Kamel, A., Zhang, W., Li, A., & Zhang, C. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113251 · Cited by 3
Generalizable Egocentric Task Verification via Cross-Modal Hybrid Hypergraph Matching
Jiang, X., Xu, X., Wang, Z., Song, J., Shen, F., & Shen, H. T. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3655147 · Cited by 5
Schroth, M., Ilg, A., Kohout, L., & Stork, W. (2022) · IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT) · doi:10.1109/iaict55358.2022.9887452 · Cited by 2
“Overall, their random forest model achieved a precision of 0.67 and a recall of 0.68 [9].”
InfluentialCEAT: Curvature Feature Extractor Using Action Based Triplet Learning for Action Segmentation
Jang, S., Moon, J.-H., Kim, S. Y., & Sohn, K.-A. (2023) · IEEE Access · doi:10.1109/access.2023.3298960 · Cited by 2
“Lastly, we incorporate the Breakfast dataset [26], a comprehensive collection of over 1,712 videos spanning 48 unique action classes.”
MethodLet Me Help You! Neuro-Symbolic Short-Context Action Anticipation
Bhagat, S., Li, S., Campbell, J., Xie, Y., Sycara, K. P., & Stepputtis, S. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3421848 · Cited by 7
Long-Tail Temporal Action Segmentation with Group-Wise Temporal Logit Adjustment
Pang, Z., Şener, F., Ramasubramanian, S., & Yao, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73404-5_19 · Cited by 6
FocalFormer: Leveraging focal modulation for efficient action segmentation in egocentric videos
Xi, J., & Liu, S. (2025) · Computers & Graphics · doi:10.1016/j.cag.2025.104381 · Cited by 2
Egocentric Action Anticipation for Personal Health
Rodin, I., Furnari, A., Mavroeidis, D., & Farinella, G. M. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096388 · Cited by 2
“The works of [13], [14], [15] show different applications of monitoring food consumption, making dietary advice based on third-person videos, while [16], [17], [18] utilize data recorded with wearable devices.”
BackgroundRetinaViT: Efficient Visual Backbone for Online Video Streams
Suzuki, T., & Aoki, Y. (2024) · Sensors · doi:10.3390/s24175457 · Cited by 2
“[70].”
BackgroundMethodInfluentialBoundary Voting Network for Ambiguity-Aware Timestamp-Supervised Action Segmentation
Zhang, R., Duan, Y., Chen, Y., Hu, W., Cai, C., Wang, S., & Tan, Y. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3571770 · Cited by 5
“A. Experimental Setup 1) Datasets: We conduct experiments on three real-world video datasets: Georgia Tech Egocentric Activities (GTEA) [53], 50Salads [54], and Breakfast [55].”
Privacy preserving recognition of object-based activities using near-infrared reflective markers
Korpela, J., & Maekawa, T. (2017) · Personal and Ubiquitous Computing · doi:10.1007/s00779-017-1070-9 · Cited by 2
“This task of cooking activity recognition has been studied in many wearable and Ubicomp studies [13, 16, 21, 23].”
BackgroundMethodSequential Recognition of Manipulation Actions Using Discriminative Superpixel Group Mining
Huang, T., & McKenna, S. J. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451451 · Cited by 2
“15132/10000120) of 50 videos of 25 people making mixed salads [10].”
BackgroundMethodSelf-citationFine-grained Human Action Recognition Based on Zero-Shot Learning
Zhao, Y., Shi, P. A., & You, J. (2019) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess47205.2019.9040818 · Cited by 2
“Several data sets commonly used in the field of fine-grained human action recognition are MPII Cooking Data Set [1], 50salad Data Set [4] and MPII Cooking 2 Data Set [3].”
BackgroundCTDA: Contrastive Temporal Domain Adaptation for Action Segmentation
Han, H., Lu, Z., & Wen, J.-R. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-27818-1_46 · Cited by 2
Are current long-term video understanding datasets long-term?
Strafforello, O., Schutte, K., & van Gemert, J. C. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00319 · Cited by 9
Representation and Boundary Enhancement for Action Segmentation Using Transformer
Chen, S., Wen, C.-X., Cheng, W.-H., & Hua, K. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448258 · Cited by 2
“The performance of our proposed method is evaluated on two challenging action segmentation datasets, 50Salads [25] and Georgia Tech Egocentric Activities (GTEA) [26].”
MethodModel-Based and Class-Based Fusion of Multisensor Data
Tsanousa, A., Chatzimichail, A., Μεδίτσκος, Γ., Vrochidis, S., & Kompatsiaris, I. Y. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-37734-2_50 · Cited by 2
“In [13] accelerometer and video data are combined in different stages of the classification process.”
MethodFuture Moment Assessment for Action Query
Ke, Q., Fritz, M., & Schiele, B. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00326 · Cited by 2
“50Salads Dataset [40] contains 50 videos of making salads performed by 25 subjects.”
BackgroundInfluentialVision-Based Human Activity Recognition
Mahmud, T., & Hasan, M. (2021) · Intelligent systems reference library · doi:10.1007/978-3-030-68590-4_1 · Cited by 5
Towards a generative approach to activity recognition and segmentation.Preprint
Kuehne, H., & Serre, T. (2015) · arXiv (Cornell University) · Cited by 2
Frontal Low-rank Random Tensors for Fine-grained Action SegmentationPreprint
Zhang, Y., Muandet, K., Ma, Q., Neumann, H., & Tang, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.01004 · Cited by 7
“In our experiments, we use the 50Salads dataset, [45], the GTEA dataset [46, 47], and the Breakfast dataset [48].”
Discerning Generic Event Boundaries in Long-Form Wild VideosPreprint
Ayush, K., Krishna, T., Dietlmeier, J., McGuinness, K., Smeaton, A. F., & O'Connor, N. E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.10090 · Cited by 5
“benchmarks for this task are GTEA [11] and 50Salads [18].”
MethodSequence-to-Sequence Modeling for Action Identification at High Temporal ResolutionPreprint
Kaku, A., Liu, K., Parnandi, A., Rajamohan, H. R., Venkataramanan, K., Venkatesan, A., Wirtanen, A., Pandit, N. G., Schambra, H. M., & Fernandez‐Granda, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.02521 · Cited by 5
“Existing benchmarks, such as 50Salads (Stein & McKenna, 2013), Breakfast (Kuehne et al., 2014), Jigsaws (Gao et al., 2014), Kinetics (Kay et al., 2017) or Fine-Gym (Shao et al., 2020), contain very few short-duration actions (see Figure 3).”
News-MESI: A Dataset for Multimodal News Excerpt Segmentation and Identification
Song, Q., Jia, Z., Jia, W., Zhao, W., Hu, M., & Liu, C. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3369866 · Cited by 2
Unsupervised Action Anticipation Through Action Cluster Prediction
Chen, J., Thakur, N., Chhabra, S., & Li, B. (2025) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2025.3578300 · Cited by 2
Obinata, T., Baba, K., Uehara, A., Kawamoto, H., & Sankai, Y. (2025) · Frontiers in Robotics and AI · doi:10.3389/frobt.2025.1462833 · Cited by 1
“The datasets commonly used to evaluate these methods include GTEA, 50 Salads, Breakfast, and Assembly101, which focus on cooking and assembly activities (Li et al., 2015; Stein and McKenna, 2013; Kuehne et al., 2014; Sener et al., 2022).”
Multiple temporal scale aggregate network for temporal action segmentation
Zheng, Z., Zhou, Y., Chen, Y., Gu, Y., Zhou, J., & Ji, Z. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112165 · Cited by 1
Multi-Level and Multi-Modal Action Anticipation
Kim, S., Kaviani, G., Prabhushankar, M., & AlRegib, G. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084357 · Cited by 4
Enhancing Temporal Action Segmentation with Large Language Models
Sasage, R., Qu, J., & Miwa, S. (2025) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea65512.2025.11148796 · Cited by 2
“We evaluated the performance of our proposed method, combined with existing approaches [1], [2], on several video datasets, including 50Salads [9] and Breakfast [7].”
Multimodal adaptive fusion for enhanced long-term action anticipation
Jing, Y., Xiao, Y., Fang, H., Mao, K., Zhao, J., & Xiao, X. (2025) · Machine Vision and Applications · doi:10.1007/s00138-025-01774-w · Cited by 1
“We evaluate SAFT on two public long-term action antici - pation datasets: Breakfast [11] and 50 Salads [12 ].”
Preliminary Action Recognition
Kawano, Y., Nagasaki, Y., Hara, K., Aoki, Y., & Kataoka, H. (2023) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.89.915 · Cited by 1
ChildPlay-Hand: A Dataset of Hand Manipulations in the Wild
Farkhondeh, A., Tafasca, S., & Odobez, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91578-9_6 · Cited by 1
User-Aware Collaborative Learning in Human-Robot Interactions
Gucsi, B., Tuyen, N. T. K., Chu, B., Tarapore, D., & Tran-Thanh, L. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128489 · Cited by 3
“The 50 Salads Dataset [41], captures 25 people preparing two salads each, suitably representing a manipulation and assistance context for an HRI scenario, in which individuals execute the same task following their own preferred way (as individuals take different steps when preparing the meal and…”
CHEF-VL: Detecting Cognitive Sequencing Errors in Cooking with Vision-language Models
Wang, R., Gao, P., Lynch, P., Liu, T., Lee, Y., Baum, C. M., Connor, L. T., & Lu, C. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3770714 · Cited by 3
Towards Generalizing Temporal Action Segmentation to Unseen Views
Bahrami, E., Zatsarynna, O., Francesca, G., & Gall, J. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-025-02703-0 · Cited by 2
SmartSeg: A non-parametric approach for wearable camera video temporal segmentation
Liu, Y., Wang, H. D., Fu, H., Mason, M. L., Li, F., Wise, A. F., Levin, D. T., Biswas, G., & Ma, M. (2026) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2026.102223 · Cited by 1
Exploring Temporal Action Segmentation Techniques for Enhanced Bird Behavior Recognition
Sancho-Deltell, B., Rodriguez-Juan, J., Benavent-Lledó, M., Mulero-Pérez, D., Ortiz-Pérez, D., & Garcia-Rodriguez, J. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-19763-4_49 · Cited by 1
Unconstrained Person Identification from Ceiling Using Multiview Learning for Tabletop Users
Namioka, Y., Masuda, A., & Maekawa, T. (2017) · Journal of Information Processing · doi:10.2197/ipsjjip.25.889 · Cited by 1
“To achieve unconstrained person identification for tabletop users, we focus on a ceiling-mounted depth camera that overlooks a table, which has already been used in many existing tabletop studies [6], [7] related to recognizing assembly work in a factory, CSCW for tabletop displays, interactive dining tables, recogniz-”
MethodRadial Loss for Learning Fine-grained Video Similarity Metric
Jain, A., Agarwal, P., Mujumdar, S., Gupta, N., Mehta, S., & Chattopadhyay, C. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683003 · Cited by 1
“There are single class datasets with fine-grained annotations such as 50 Salads[10], VB100 [11], JIGSAWS [12].”
BackgroundElangovan, N., Chang, C.-M., de Godoy, R. V., Sanches, F. P., Wang, K., Jarvis, P., & Liarokapis, M. V. (2022) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids53995.2022.10000248 · Cited by 1
“The food preparation dataset presented in [11] on the other hand, was collected from participants following a predetermined task order within a delimited space to prepare a single portion of salad.”
BackgroundConvolutional Transformer with Similarity-based Boundary Prediction for Action Segmentation
Du, D., Su, B., Li, Y., Qi, Z., Si, L., & Shan, Y. (2022) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai56018.2022.00131 · Cited by 2
“We empirically evaluate the performance of the proposed method on three datasets: the 50Salads dataset [16], the Georgia Tech Egocentric Activities (GTEA) dataset [3], and the Breakfast dataset [9].”
MethodMa, Z., & Li, K. (2023) · Mathematics · doi:10.3390/math12010057 · Cited by 1
CookingINWild: Unleashing the Challenges of Indian Cuisine Cooking Videos for Action Recognition
Khanna, S., Goyal, S., Chattopadhyay, C., & Kundu, S. (2024) · Joint International Conference on Data Science & Management of Data (CODS-COMAD) · doi:10.1145/3632410.3632429 · Cited by 2
“The 50 Salads dataset [13] comprises recordings of 25 individuals, each tasked with preparing salads in a controlled setting.”
Automated Analysis of Chemistry Experiment Videos: New Challenges for Video Understanding
Zheng, Z., Wang, B., Wang, Z., Chen, Y., Zhou, J., & Kong, L. J. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-0730-0_18 · Cited by 1
Context in Human Action through Motion Complementarity
Dessalene, E., Maynord, M., Fermuller, C. M., & Aloimonos, Y. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00640 · Cited by 3
“The primary contributions of our work are as follows: • A contrastive formulation for the modeling of context in a way that achieves complementarity with movement, implemented within a two-stream archicture.”
BackgroundMaekawa, T., Yoshimura, N., Morales, J., & Hara, T. (2024) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3675094.3677597 · Cited by 1
“Complex procedural activity datasets, like CMU-MMAC [14], 50 Salads [15], and Cooking Activity Dataset [5], focus on cooking activities.”
Hong, J., Long, Y., Luo, Y., Qi, Q., & Long, J. (2024) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme57554.2024.10688242 · Cited by 2
“The 50Salads dataset [25] contains 50 top-view videos of 17 action categories.”
BackgroundJoint-Temporal Action Segmentation via Multi-action Recognition
Kiftiyani, U., & Lee, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78354-8_20 · Cited by 1
Online Performance Prediction and Profiling of Human Activities by Observation
Hourdakis, E., Maniadakis, M., & Trahanias, P. E. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967707 · Cited by 1
“Task P 3M Progress Actual Progress Error Progress model Empty dishwasher (P19-emptydishwasher-ch0) [14] 63% 72% 9% # of utencils removed Clean the floor (P23-sweep-ch0) [14] 45% 53% 8% % of the floor that has been wiped Setup the table (P16-settable-ch0) [14] 87% 96% 9% # of utencils placed on the table Cut three ingr…”
BackgroundTowards Neural-Symbolic AI for Media Understanding
da Costa, P. B., Marques, G., Serra, A. C., Moraes, D. D. S., Busson, A. J. G., Guedes, Á. L. V., de Lima, G. L., & Colcher, S. (2020) · Brazilian Symposium on Multimedia and the Web · doi:10.5753/webmedia_estendido.2020.13083 · Cited by 1
Wang, L., Wang, X., Hawbani, A., & Xiong, Y. (2021) · Applied Sciences · doi:10.3390/app11114954 · Cited by 1
“The 50 Salads dataset is distributed by the Computer Vision Image Processing (CVIP) group at the University of Dundee, Scotland, UK; YouTube Instructions dataset is distributed by the Willow project team at the Computer Science Department of the Ecole Normale Superieure (DI ENS), Paris, France.”
MethodInfluentialCoarse-to-Fine Loss Based On Viterbi Algorithm for Weakly Supervised Action Segmentation
Sheng, L., Li, C., & Tian, Y. (2021) · 2021 International Conference on Signal Processing and Machine Learning (CONF-SPML) · doi:10.1109/conf-spml54095.2021.00009 · Cited by 2
Semantically Annotated Cooking Procedures for an Intelligent Kitchen Environment
Kondylakis, G., Galanakis, G., Partarakis, N., & Zabulis, X. (2022) · Electronics · doi:10.3390/electronics11193148 · Cited by 1
“[13] – ✓ – – – – ✓ [14] – – – ✓ – – – [4] – ✓ – ✓ – – – [16] – – – – – – – [15] – ✓ – – – – ✓ [12] – ✓ – ✓ – – ✓ [10] – ✓ – ✓ – ✓ – [7] – – – ✓ – – – [17] – ✓ – ✓ – ✓ – Present thesis ✓ – ✓ ✓ ✓ ✓ –”
BackgroundMethodInfluentialCooking in the kitchen: Recognizing and Segmenting Human Activities in VideosPreprint
Kuehne, H., Gall, J., & Serre, T. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1508.06073 · Cited by 1
“12: Sample frames from the datasets used for performance evaluation: a) Toy assembly [36], b) CMU MMAC [33], c) MPII Cooking [24], d) 50 Salads [34].”
BackgroundMethodPredicting Human Intentions from Motion Only: A 2D+3D Fusion ApproachPreprint
Zunino, A., Cavazza, J., Koul, A., Cavallo, A., Becchio, C., & Murino, V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.09526 · Cited by 1
“For instance, MPII-CAD [35] and Salad 50 [36] cover more articulated (cooking) actions, while UCF-101 [37] and HDMB51 [38] collect YouTube videos, thus guaranteeing a broad variability of backgrounds and context.”
BackgroundSegmental Spatiotemporal CNNs for Fine-grained Action SegmentationPreprint
Lea, C., Reiter, A., Vidal, R., & Hager, G. D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.02995 · Cited by 4
“University of Dundee 50 Salads: Stein and McKenna introduced 50 Salads [19] for evaluating fine-grained action recognition in the cooking domain.”
BackgroundMethodUnsupervised Action Segmentation with Self-supervised Feature Learning and Co-occurrence Parsing.Preprint
Wang, Z., Chen, H., Li, X., Liu, C., Xiong, Y., Tighe, J., & Fowlkes, C. C. (2021) · arXiv (Cornell University) · Cited by 1
Overview of Tencent Multi-modal Ads Video Understanding ChallengePreprint
Wang, Z., Wu, L., Li, Z., Xiong, J., & Lu, Q. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.07951 · Cited by 2
“4h 88 10 ✗ cooking actions 50Salads [45] 5.”
BackgroundKUSK Object Dataset : 調理作業中の物体への接触履歴データセットの作成 (データ工学)
橋本, 敦., 飯山, 将., 森, 信., & Minoh, M. (2015) · IEICE technical report. Speech
Superpixel Group Mining for Manipulation Action Recognition
Huang, T., & McKenna, S. J. (2018) · Discovery Research Portal (University of Dundee)
Self-citationHuman Action Recognition and Prediction for Robotics Applications
Rezazadegan, F. (2019) · Queensland University of Technology · doi:10.5204/thesis.eprints.127283
DDLSTM: Dual-Domain LSTM for Cross-Dataset Action RecognitionPreprint
Perrett, T., & Damen, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.08634 · Cited by 4
“50 Salads [40]: The 50 Salads dataset contains 50 videos, by 25 participants.”
BackgroundMethodDifferentiable Grammars for VideosPreprint
Piergiovanni, A., Angelova, A., & Ryoo, M. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.00505
“50 Salads: This dataset contains 50 videos of making sal-ads, e.g., cutting vegetables and mixing them.”
MethodFine-grained Action Detection in Long Surveillance Videos.
Aakur, S. N., Sawyer, D., Balážia, M., & Sarkar, S. (2018) · TRECVID
Precise Temporal Action Detection for Fine-grained Actions
Yang, Y., Lan, S., Zhang, S., Bu, Q., & Chen, Y. (2020) · International Conference on Culture-oriented Science & Technology (ICCST) · doi:10.1109/iccst50977.2020.00068
“We evaluted our methods on 50 Salads Dataset [5].”
MethodFiltjens, B., Ginis, P., Nieuwboer, A., Slaets, P., & Vanrumste, B. (2021) · arXiv (Cornell University)
Activity recognition and bioinspired approaches for robotics in intelligent environments
Ranieri, C. M. (2021) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.55.2021.tde-11082021-112227 · Cited by 1
Pyramid Dilated Attention Network for Action Segmentation
Du, Z., Mei, F., Lai, X., & Wang, Q. (2021) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp52459.2021.9613432
“, 50Salads [4], Georgia Tech Egocentric Activities (GTEA) [5] and the Breakfast dataset [6].”
BackgroundSupervised Sliding Window Smoothing Loss Function Based on MS-TCN for Video Segmentation
Yang, T. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-8885-0_24
Two-Stream Retentive Long Short-Term Memory Network for Dense Action Anticipation
Zhao, F., Zhao, J., Li, X., Zhang, Y., Guo, D., & Chen, W. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/4260247
“)e 50 Salads data set [19] contains 50 videos and consists of 17 action classes.”
BackgroundMethodJabeen, S., Ahsan, A., Kazmi, S. R. F., Alvi, M., Arshad, M. K., Asghar, H. A., Anoshi, A., & Mehjabeen, M. (2021) · Haya The Saudi Journal of Life Sciences · doi:10.36348/sjls.2021.v06i12.001
“As a result, this technique can increase the shelf life of the food over many days or even weeks [8-12].”
BackgroundPACE: Predictive and Contrastive Embedding for Unsupervised Action Segmentation
Wang, J., Qin, J., Wang, Y., & Li, A. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/198
Action Forecasting with Feature-wise Self-AttentionPreprint
Ng, Y. B., & Fernando, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.08579
Boundary-Match U-Shaped Temporal Convolutional Network for Vulgar Action SegmentationPreprint
Feng, X., Xu, R., He, Y., Qin, F., Toyoura, M., & Peng, Y. K. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4576778
Action Segmentation Based on Encoder-Decoder and Global Timing Information
Liu, Y., Sun, Y., Chen, Z., Feng, C., & Zhu, K. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-8211-0_26
Denoised Temporal Relation Network for Temporal Action Segmentation
Ma, Z., & Li, K. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8537-1_23
Ma, Z., & Li, K. (2024) · Machine Vision and Applications · doi:10.1007/s00138-023-01505-z
“In 50Salads [48], 25 actors preparing salads are recorded, andeachof them madetwotypes of salads, forming50videos with 17 action classes in the mid-level action granularity.”
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.