Self-Attention Temporal Convolutional Network for Long-Term Daily Living Activity Detection
- Others:
- Spatio-Temporal Activity Recognition Systems (STARS) ; Inria Sophia Antipolis - Méditerranée (CRISAM) ; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
- Toyota Motor Europe (BELGIUM) ; Toyota Motor Europe
- Toyota Motor Europe
Description
In this paper, we address the detection of daily living activities in long-term untrimmed videos. The detection of daily living activities is challenging due to their long temporal components, low inter-class variation and high intra-class variation. To tackle these challenges, recent approaches based on Temporal Convolutional Networks (TCNs) have been proposed. Such methods can capture long-term temporal patterns using a hierarchy of temporal convolutional filters, pooling and up sampling steps. However, as one of the important features of con-volutional networks, TCNs process a local neighborhood across time which leads to inefficiency in modeling the long-range dependencies between these temporal patterns of the video. In this paper, we propose Self-Attention-Temporal Convolutional Network (SA-TCN), which is able to capture both complex activity patterns and their dependencies within long-term untrimmed videos. We evaluate our proposed model on DAily Home LIfe Activity Dataset (DAHLIA) and Breakfast datasets. Our proposed method achieves state-of-the-art performance on both DAHLIA and Breakfast dataset.
Abstract
International audience
Additional details
- URL
- https://hal.archives-ouvertes.fr/hal-02357161
- URN
- urn:oai:HAL:hal-02357161v1
- Origin repository
- UNICA