Abstract | ||
---|---|---|
This paper focuses on the temporal aspect for recognizing human activities in videos; an important visual cue that has long been undervalued. We revisit the conventional definition of activity and restrict it to Complex Action: a set of one-actions with a weak temporal pattern that serves a specific purpose. Related works use spatiotemporal 3D convolutions with fixed kernel size, too rigid to capture the varieties in temporal extents of complex actions, and too short for long-range temporal modeling. In contrast, we use multi-scale temporal convolutions, and we reduce the complexity of 3D convolutions. The outcome is Timeception convolution layers, which reasons about minute-long temporal patterns, a factor of 8 longer than best related works. As a result, Timeception achieves impressive accuracy in recognizing the human activities of Charades, Breakfast Actions and MultiTHUMOS. Further, we demonstrate that Timeception learns long-range temporal dependencies and tolerate temporal extents of complex actions. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/CVPR.2019.00034 | 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
Keywords | Field | DocType |
Action Recognition,Video Analytics | Kernel (linear algebra),Pattern recognition,Convolution,Computer science,Action recognition,Temporal modeling,Artificial intelligence,restrict | Journal |
Volume | ISSN | ISBN |
abs/1812.01289 | 1063-6919 | 978-1-7281-3294-5 |
Citations | PageRank | References |
10 | 0.47 | 10 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Noureldien Hussein | 1 | 12 | 1.50 |
efstratios gavves | 2 | 655 | 33.41 |
Arnold W. M. Smeulders | 3 | 6000 | 453.43 |