DeepAI AI Chat
Log In Sign Up

On Attention Models for Human Activity Recognition

by   Vishvak S Murahari, et al.
Georgia Institute of Technology

Most approaches that model time-series data in human activity recognition based on body-worn sensing (HAR) use a fixed size temporal context to represent different activities. This might, however, not be apt for sets of activities with individ- ually varying durations. We introduce attention models into HAR research as a data driven approach for exploring relevant temporal context. Attention models learn a set of weights over input data, which we leverage to weight the temporal context being considered to model each sensor reading. We construct attention models for HAR by adding attention layers to a state- of-the-art deep learning HAR model (DeepConvLSTM) and evaluate our approach on benchmark datasets achieving sig- nificant increase in performance. Finally, we visualize the learned weights to better understand what constitutes relevant temporal context.


page 1

page 2

page 3

page 4


Human Activity Recognition from Wearable Sensor Data Using Self-Attention

Human Activity Recognition from body-worn sensor data poses an inherent ...

Hierarchical Self Attention Based Autoencoder for Open-Set Human Activity Recognition

Wearable sensor based human activity recognition is a challenging proble...

Multi-agent Attentional Activity Recognition

Multi-modality is an important feature of sensor based activity recognit...

Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention

Deep neural networks, including recurrent networks, have been successful...

Learning Attribute Representation for Human Activity Recognition

Attribute representations became relevant in image recognition and word ...

Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters

In this paper, we newly introduce the concept of temporal attention filt...

Augmenting Bag-of-Words: Data-Driven Discovery of Temporal and Structural Information for Activity Recognition

We present data-driven techniques to augment Bag of Words (BoW) models, ...