We describe a novel cross-modal embedding space for actions, named Action2Vec, which combines linguistic cues from class labels with spatio-temporal features derived from video …
Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for spatial-temporal modeling in videos. In this …
S Broomé, E Pokropek, B Li… - Proceedings of the …, 2023 - openaccess.thecvf.com
Most action recognition models today are highly parameterized, and evaluated on datasets with appearance-wise distinct classes. It has also been shown that 2D Convolutional Neural …
In egocentric videos, actions occur in quick succession. We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order …
Much research on human action recognition has been oriented toward the performance gain on lab-collected datasets. Yet real-world videos are more diverse, with more complicated …
U Ahsan, R Madhok, I Essa - 2019 IEEE Winter Conference on …, 2019 - ieeexplore.ieee.org
We propose a self-supervised learning method to jointly reason about spatial and temporal context for video recognition. Recent self-supervised approaches have used spatial context …
Action recognition in videos is a challenging task due to the complexity of the spatio- temporal patterns to model and the difficulty to acquire and learn on large quantities of video …
Y Tian, Y Yan, G Zhai, G Guo, Z Gao - International Journal of Computer …, 2022 - Springer
Efficiently modeling spatial–temporal information in videos is crucial for action recognition. To achieve this goal, state-of-the-art methods typically employ the convolution operator and …
Deep models have the risk of utilizing spurious clues to make predictions, eg, recognizing actions via classifying the background scene. This problem severely degrades the open-set …