Title | ||
---|---|---|
Self-Attention Temporal Convolutional Network for Long-Term Daily Living Activity Detection |
Abstract | ||
---|---|---|
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 convolutional 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. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/AVSS.2019.8909841 | 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) |
Keywords | Field | DocType |
long-term temporal patterns,temporal convolutional filters,long-range dependencies,complex activity patterns,self-attention - temporal convolutional network,long-term untrimmed videos,long-term daily living activity detection,low inter-class variation,high intra-class variation,SA-TCN,daily home life activity dataset,DAHLIA,breakfast datasets | Computer vision,Daily living,Computer science,Speech recognition,Activity detection,Artificial intelligence | Conference |
ISSN | ISBN | Citations |
2643-6205 | 978-1-7281-0991-6 | 0 |
PageRank | References | Authors |
0.34 | 13 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rui Dai | 1 | 49 | 14.71 |
Luca Minciullo | 2 | 1 | 2.38 |
Lorenzo Garattoni | 3 | 0 | 0.34 |
Gianpiero Francesca | 4 | 91 | 11.26 |
FrançOis BréMond | 5 | 655 | 63.64 |