Transfer Learning for Activity Recognition: A Survey
By Diane Joyce Cook, Kyle D. Feuz, Narayanan Chatapuram Krishnan. Knowledge and Information Systems, 2013
451 citations recorded by the source corpus.
Many intelligent systems that focus on the needs of a human require information about the activities being performed by the human. At the core of this capability is activity recognition, which is a challenging and well-researched problem. Activity recognition algorithms require substantial amounts of labeled training data yet need to perform well under very diverse circumstances. As a result, researchers have been designing methods to identify and utilize subtle connections between activity recognition datasets, or to perform transfer-based activity recognition. In this paper, we survey the literature to highlight recent advances in transfer learning for activity recognition. We characterize existing approaches to transfer-based activity recognition by sensor modality, by differences between source and target environments, by data availability, and by type of information that is transferred. Finally, we present some grand challenges for the community to consider as this field is further developed.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/2f03b36a6e8077701da8fa58c46613bd08b707f4
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
Citations in the corpus
- Recent trends in machine learning for human activity recognition—A survey (2018, background): “Moreover, processing huge datasets incurs high computational costs and increases the training time of the model (Cook et al., 2013).”
- Cross-Domain WiFi Sensing with Channel State Information: A Survey (2022, background): “By deinition, feature representation transfer means that a "good" feature representation needs to be acquired to reduce the diferences between the training domain and testing domain [10, 54].”
- Instilling Social to Physical: Co-Regularized Heterogeneous Transfer Learning (2016, background): “Some studies (Cook et al. 2013; Hu and Yang 2011; Zheng et al. 2009) tried to alleviate this problem by transferring labelled data from one activity recognition task to another, but such studies were limited to transferring between physical sensor data only.”
- Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives (2022, background): “, 2020b; Wilson and Cook, 2020; Ramponi and Plank, 2020), and the broader problem of transfer learning (Pan and Yang, 2009; Cook et al., 2013; Lazaric, 2012; Shao et al., 2014; Tan et al., 2018; Zhang et al., 2019b).”
- Stratified Transfer Learning for Cross-domain Activity Recognition (2017, unknown): “A detailed survey is provided in [36].”
- A Comprehensive Survey on Transfer Learning (2019, background): “Besides, a number of surveys focus on specific application scenarios including activity recognition [25], visual categorization [26], collaborative recommendation [27], computer vision [24], and sentiment analysis [28].”
- A Survey of Unsupervised Deep Domain Adaptation (2018, background): “et data labels, will be the focus of this survey. A number of surveys have been created on the topic of domain adaptation [10, 21, 36, 41, 42, 106, 139,158,199,213,246]andmoregenerallytransferlearning[38,111,131,156,189,203,205,219,234], of which domain adaptation can be viewed as a special case [15”
- A Survey on Ambient Intelligence in Health Care (2013, unknown): “Generative probabilistic graphical models such as hidden Markov models [72], [70], [73], [74] and dynamic Bayesian networks [64], [48] have been used to model activity sequences and to smooth recognition results of an ensemble classifier [75].”