Egocentric Daily Activity Recognition via Multitask Clustering

Yan, Yan; Ricci, Elisa; Liu, Gaowen; Sebe, Nicu

doi:10.1109/tip.2015.2438540

Cited by 139 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In most fields comprising computer vision, bioinformatics, health informatics, speech and natural language processing, web applications and ubiquitous computing, MTL is used to enhance the overall performance of the applications involved. Learning paradigms including supervised learning (e.g., classification or regression problems) [14][15][16], unsupervised learning [17][18][19][20][21][22][23], semi-supervised learning [24][25][26][27], active learning [28][29][30][31], reinforcement learning [32][33][34][35], multi-view learning [21,[36][37][38], and graphical models [39][40][41] are generally combined with MTL [42,43].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Majority Voting Based Multi-Task Clustering of Air Quality Monitoring Network in Turkey

2019

View full text Add to dashboard Cite

Air pollution, which is the result of the urbanization brought by modern life, has a dramatic impact on the global scale as well as local and regional scales. Since air pollution has important effects on human health and other living things, the issue of air quality is of great importance all over the world. Accordingly, many studies based on classification, clustering and association rule mining applications for air pollution have been proposed in the field of data mining and machine learning to extract hidden knowledge from environmental parameters. One approach is to model a region in a way that cities having similar characteristics are determined and placed into the same clusters. Instead of using traditional clustering algorithms, a novel algorithm, named Majority Voting based Multi-Task Clustering (MV-MTC), is proposed and utilized to consider multiple air pollutants jointly. Experimental studies showed that the proposed method is superior to five well-known clustering algorithms: K-Means, Expectation Maximization, Canopy, Farthest First and Hierarchical clustering methods.

show abstract

Section: Related Workmentioning

confidence: 99%

“…MTC has been applied in many different areas including bioinformatics, text mining, web mining, image mining, daily activity recognition and so on [18][19][20][21][22][23]45]. The resulting clustering template of MTC has generally outperformed any single clustering algorithm's outputs.…”

Section: Related Workmentioning

confidence: 99%

Majority Voting Based Multi-Task Clustering of Air Quality Monitoring Network in Turkey

2019

View full text Add to dashboard Cite

show abstract

“…Among the approaches using wearable sensors, the technique of using a wearable camera to recognize the environment and user's activity is called a first-person vision or an egocentric vision method, and has been attracting attention in recent years [13]. Yan et al proposed a multitask clustering framework to classify daily activities [14]. They introduced two novel clustering algorithms to determine partitions that are coherent among related tasks.…”

Section: Related Workmentioning

confidence: 99%

Activity Recognition Using Gazed Text and Viewpoint Information for User Support Systems

Chiba

Miyazaki

Sugaya

et al. 2018

JSAN

View full text Add to dashboard Cite

The development of information technology has added many conveniences to our lives. On the other hand, however, we have to deal with various kinds of information, which can be a difficult task for elderly people or those who are not familiar with information devices. A technology to recognize each person’s activity and providing appropriate support based on that activity could be useful for such people. In this paper, we propose a novel fine-grained activity recognition method for user support systems that focuses on identifying the text at which a user is gazing, based on the idea that the content of the text is related to the activity of the user. It is necessary to keep in mind that the meaning of the text depends on its location. To tackle this problem, we propose the simultaneous use of a wearable device and fixed camera. To obtain the global location of the text, we perform image matching using the local features of the images obtained by these two devices. Then, we generate a feature vector based on this information and the content of the text. To show the effectiveness of the proposed approach, we performed activity recognition experiments with six subjects in a laboratory environment.

show abstract

“…Over the last decade, the field of activity recognition has received significant attention [12], [16], [18], [20], [32], [34]. For further studies, the activity prediction field has attracted serious consideration and has been approached with various technologies, including sensors, wearable devices, mobile devices, images and video [5], [19], [21], [28].…”

Section: Related Workmentioning

confidence: 99%

Next-Activity Set Prediction Based on Sequence Partitioning to Reduce Activity Pattern Complexity in the Multi-User Smart Space

Kim

Lee

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYHuman activity prediction has become a prerequisite for service recommendation and anomaly detection systems in a smart space including ambient assisted living (AAL) and activities of daily living (ADL). In this paper, we present a novel approach to predict the nextactivity set in a multi-user smart space. Differing from the majority of the previous studies considering single-user activity patterns, our study considers multi-user activities that occur with a large variety of patterns. Its complexity increases exponentially according to the number of users. In the multi-user smart space, there can be inevitably multiple next-activity candidates after multi-user activities occur. To solve the next-activity problem in a multi-user situation, we propose activity set prediction rather than one activity prediction. We also propose activity sequence partitioning to reduce the complexity of the multi-user activity pattern. This divides an activity sequence into start, ongoing, and finish zones based on the features in the tendency of activity occurrences. The majority of the activities in a multi-user environment occur at the beginning or end, rather than the middle, of an activity sequence. Furthermore, the types of activities typically occurring in each zone can be sufficiently distinguishable. Exploiting these characteristics, we suggest a two-step procedure to predict the nextactivity set utilizing a long short-term memory (LSTM) model. The first step identifies the zones to which current activities belong. In the next step, we construct three different LSTM models to predict the next-activity set in each zone. To evaluate the proposed approach, we experimented using a real dataset generated from our campus testbed. Our experiments confirmed the complexity reduction and high accuracy in the next-activity set prediction. Thus, it can be effectively utilized for various applications with context-awareness in a multi-user smart space. key words: activity prediction, sequence partitioning, multi-user smart space, LSTM

show abstract

Egocentric Daily Activity Recognition via Multitask Clustering

Cited by 139 publications

References 40 publications

Majority Voting Based Multi-Task Clustering of Air Quality Monitoring Network in Turkey

Majority Voting Based Multi-Task Clustering of Air Quality Monitoring Network in Turkey

Activity Recognition Using Gazed Text and Viewpoint Information for User Support Systems

Next-Activity Set Prediction Based on Sequence Partitioning to Reduce Activity Pattern Complexity in the Multi-User Smart Space

Contact Info

Product

Resources

About