Action2Activity: Recognizing Complex Activities from Sensor Data
By Ye Liu, Liqiang Nie, Lei Han, Luming Zhang, David S. Rosenblum. International Joint Conference on Artificial Intelligence, 2015
369 citations recorded by the source corpus.
As compared to simple actions, activities are much more complex, but semantically consistent with a human's real life. Techniques for action recognition from sensor generated data are mature. However, there has been relatively little work on bridging the gap between actions and activities. To this end, this paper presents a novel approach for complex activity recognition comprising of two components. The first component is temporal pattern mining, which provides a mid-level feature representation for activities, encodes temporal relatedness among actions, and captures the intrinsic properties of activities. The second component is adaptive Multi-Task Learning, which captures relatedness among activities and selects discriminant features. Extensive experiments on a real-world dataset demonstrate the effectiveness of our work.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/d00b4a1a2b64d1b96853e387f351de6ac7166efa
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
- Daniel Preotiuc-Pietro
- Lyle Ungar
- Daniel Hopkins
- Parisa Rashidi
- Graziano Pravadelli
- Ye Liu
- Azra Bihorac
- Florenc Demrozi
In Computer Vision and Pattern Recognition
- Daniel Preotiuc-Pietro
- Lyle Ungar
- Parisa Rashidi
- Graziano Pravadelli
- Azra Bihorac
- Florenc Demrozi
- Diane Joyce Cook
Citations in the corpus
- Human Activity Recognition using Inertial, Physiological and Environmental Sensors: A Comprehensive Survey (2020, methodology): “In [4], [60] and [170], the methodologies are based on the mining of temporal patterns and their symbolic representation, or as in [43] were, authors make use of”
- Beyond Binary Labels: Political Ideology Prediction of Twitter Users (2017, background): “Multi-task learning (MTL) is a learning paradigm that jointly learns multiple related tasks and can achieve better generalization performance than learning each task individually, especially when presented with insufficient training samples (Liu et al., 2015, 2016b,d).”