Weakly Supervised Human Activity Recognition From Wearable Sensors by Recurrent Attention Learning

He, Jun; Zhang, Qian; Wang, Liqun; Pei, Ling

doi:10.1109/jsen.2018.2885796

Cited by 46 publications

(47 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding human activity recognition approaches, most of the related published studies address such a recognition using supervised learning [18][19][20][21][22] or semisupervised learning [23,24]. Transfer learning has also been investigated, whereby the instances or models for activities in one domain can be transferred to improve the recognition accuracy in another domain for the purpose of reducing the need for training data [25][26][27].…”

Section: Activity Recognition-based Supervised Learningmentioning

confidence: 99%

Zero-Shot Human Activity Recognition Using Non-Visual Sensors

Machot

Elkobaisi

Kyamakya

2020

Sensors

View full text Add to dashboard Cite

Due to significant advances in sensor technology, studies towards activity recognition have gained interest and maturity in the last few years. Existing machine learning algorithms have demonstrated promising results by classifying activities whose instances have been already seen during training. Activity recognition methods based on real-life settings should cover a growing number of activities in various domains, whereby a significant part of instances will not be present in the training data set. However, to cover all possible activities in advance is a complex and expensive task. Concretely, we need a method that can extend the learning model to detect unseen activities without prior knowledge regarding sensor readings about those previously unseen activities. In this paper, we introduce an approach to leverage sensor data in discovering new unseen activities which were not present in the training set. We show that sensor readings can lead to promising results for zero-shot learning, whereby the necessary knowledge can be transferred from seen to unseen activities by using semantic similarity. The evaluation conducted on two data sets extracted from the well-known CASAS datasets show that the proposed zero-shot learning approach achieves a high performance in recognizing unseen (i.e., not present in the training dataset) new activities.

show abstract

Section: Activity Recognition-based Supervised Learningmentioning

confidence: 99%

Zero-Shot Human Activity Recognition Using Non-Visual Sensors

Machot

Elkobaisi

Kyamakya

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Our task is closely related to the area where we learn models to predict user activities with limited training data. Unlike images or videos that human beings can easily label, strictly labeling long sequences of sensor data with different granularity of activity needs much more human labors [7,[21][22][23]. To extract information from weakly labeled sensor data by adaptively selecting a sequence of locations, a recurrent attention learning is proposed in [7].…”

Section: Semi-supervised Activity Recognitionmentioning

confidence: 99%

“…Unlike images or videos that human beings can easily label, strictly labeling long sequences of sensor data with different granularity of activity needs much more human labors [7,[21][22][23]. To extract information from weakly labeled sensor data by adaptively selecting a sequence of locations, a recurrent attention learning is proposed in [7]. Stikic et al [21] proposes a novel annotation strategies that substantially reduce the required amount of annotation, and explore two learning schemes to effectively leverage such sparsely labeled data together with more easily available unlabeled data.…”

Section: Semi-supervised Activity Recognitionmentioning

confidence: 99%

“…However, such (labeled) data is laborintensive to acquire and hence difficult to scale up. Prior work handling limited labeled data learning utilizes a semi-supervised learning technique, which combines a small amount of labeled data with a large amount of unlabeled data to train the model [7,[21][22][23]. However, these studies focus on traditional coarse-grained activities recognition only.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fine-grained activities recognition with coarse-grained labeled multi-modal data

Zhang

et al. 2020

Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of The

View full text Add to dashboard Cite

Fine-grained human activities recognition focuses on recognizing event-or action-level activities, which enables a new set of Internetof-Things (IoT) applications such as behavior analysis. Prior work on fine-grained human activities recognition relies on supervised sensing, which makes the fine-grained labeling labor-intensive and difficult to scale up. On the other hand, it is much more practical to collect coarse-grained label at the level of activity of daily living (e.g., cooking, working), especially for real-world IoT systems. In this paper, we present a framework that learns fine-grained human activities recognition with coarse-grained labeled and a small amount of fine-grained labeled multi-modal data. Our system leverages the implicit physical knowledge on the hierarchy of the coarse-and fine-grained labels and conducts data-driven hierarchical learning that take into account the coarse-grained supervised prediction for fine-grained semi-supervised learning. We evaluated our framework and CFR-TSVM algorithm on the data gathered from real-world experiments. Results show that our CFR-TSVM achieved an 81% recognition accuracy over 10 fine-grained activities, which reduces the prediction error of the semi-supervised learning baseline TSVM by half.

show abstract

“…), the position of limbs, and legs including background details. Most of the human activity recognition published literature consists of supervised learning [ 26 , 27 ] and semi-supervised learning [ 28 ]. In the case of human activity recognition, the deep models require large training data; to tackle this problem, the transfer learning approach has been thoroughly studied [ 29 ].…”

Section: Related Workmentioning

confidence: 99%

Human Sentiment and Activity Recognition in Disaster Situations Using Social Media Images Based on Deep Learning

Sadiq

Ahn

Choi

2020

Sensors

View full text Add to dashboard Cite

A rapidly increasing growth of social networks and the propensity of users to communicate their physical activities, thoughts, expressions, and viewpoints in text, visual, and audio material have opened up new possibilities and opportunities in sentiment and activity analysis. Although sentiment and activity analysis of text streams has been extensively studied in the literature, it is relatively recent yet challenging to evaluate sentiment and physical activities together from visuals such as photographs and videos. This paper emphasizes human sentiment in a socially crucial field, namely social media disaster/catastrophe analysis, with associated physical activity analysis. We suggest multi-tagging sentiment and associated activity analyzer fused with a a deep human count tracker, a pragmatic technique for multiple object tracking, and count in occluded circumstances with a reduced number of identity switches in disaster-related videos and images. A crowd-sourcing study has been conducted to analyze and annotate human activity and sentiments towards natural disasters and related images in social networks. The crowdsourcing study outcome into a large-scale benchmark dataset with three annotations sets each resolves distinct tasks. The presented analysis and dataset will anchor a baseline for future research in the domain. We believe that the proposed system will contribute to more viable communities by benefiting different stakeholders, such as news broadcasters, emergency relief organizations, and the public in general.

show abstract

Weakly Supervised Human Activity Recognition From Wearable Sensors by Recurrent Attention Learning

Cited by 46 publications

References 29 publications

Zero-Shot Human Activity Recognition Using Non-Visual Sensors

Zero-Shot Human Activity Recognition Using Non-Visual Sensors

Fine-grained activities recognition with coarse-grained labeled multi-modal data

Human Sentiment and Activity Recognition in Disaster Situations Using Social Media Images Based on Deep Learning

Contact Info

Product

Resources

About