DIFFAR: Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition

We present a differentiable frequency-based method for aerial video recognition. Our differentiable static-dynamic frequency mask provides a prior for disentangled regions relevant to action recognition. This mask is used to guide the learning of disentangled features within the layers of the neural network using an identity function. Further, we propose a frame sampling strategy that chooses the best frame within each uniform video segment, at test time, using the static-dynamic frequency mask and temporal difference.

Abstract: We present a learning algorithm for human activity recognition in videos. Our approach is designed for UAV videos, which are mainly acquired from obliquely placed dynamic cameras that contain a human actor along with background motion. Typically, the human actors occupy less than one-tenth of the spatial resolution. Our approach simultaneously harnesses the benefits of frequency domain representations, a classical analysis tool in signal processing, and data driven neural networks. We build a differentiable staticdynamic frequency mask prior to model the salient static and dynamic pixels in the video, crucial for the underlying task of action recognition. We use this differentiable mask prior to enable the neural network to intrinsically learn disentangled feature representations via an identity loss function. Our formulation empowers the network to inherently compute disentangled salient features within its layers. Further, we propose a cost-function encapsulating temporal relevance and spatial content to sample the most important frame within uniformly spaced video segments. We conduct extensive experiments on the UAV Human dataset and the NEC Drone dataset and demonstrate relative improvements of 5.72%−13.00% over the state-of-the-art and 14.28% − 38.05% over the corresponding baseline model.

@article{kothandaraman2022differentiable,
  title={Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition},
  author={Kothandaraman, Divya and Lin, Ming and Manocha, Dinesh},
  journal={arXiv preprint arXiv:2209.09194},
  year={2022}
}