Unsupervised optical flow estimation for differently exposed images in ldr domain
Differently exposed low dynamic range (LDR) images are often captured sequentially using
a smart phone or a digital camera with movements. Optical flow thus plays an important role …
a smart phone or a digital camera with movements. Optical flow thus plays an important role …
Survey on unsupervised learning methods for optical flow estimation
Optical flow is an important component in many computer vision applications. Thanks to
deep learning, there have been great improvements in optical flow estimation in the past …
deep learning, there have been great improvements in optical flow estimation in the past …
[HTML][HTML] Behaviour recognition based on the integration of multigranular motion features in the Internet of Things
L Zhang, Y Wang, K Yan, Y Su, N Alharbe… - Digital Communications …, 2022 - Elsevier
With the adoption of cutting-edge communication technologies such as 5G/6G systems and
the extensive development of devices, crowdsensing systems in the Internet of Things (IoT) …
the extensive development of devices, crowdsensing systems in the Internet of Things (IoT) …
Explicit State Representation Guided Video-based Pedestrian Attribute Recognition
The pedestrian attribute recognition aims to generate a structured description of pedestrians,
which serves an important role in surveillance. Current works usually assume that the …
which serves an important role in surveillance. Current works usually assume that the …
[HTML][HTML] Regularization for Unsupervised Learning of Optical Flow
Regularization is an important technique for training deep neural networks. In this paper, we
propose a novel shared-weight teacher–student strategy and a content-aware regularization …
propose a novel shared-weight teacher–student strategy and a content-aware regularization …
Self-supervised Learning of Occlusion Aware Flow Guided 3D Geometry Perception with Adaptive Cross Weighted Loss from Monocular Videos
J Fang, G Liu - arXiv preprint arXiv:2108.03893, 2021 - arxiv.org
Self-supervised deep learning-based 3D scene understanding methods can overcome the
difficulty of acquiring the densely labeled ground-truth and have made a lot of advances …
difficulty of acquiring the densely labeled ground-truth and have made a lot of advances …
Behavior Recognition Based on the Integration of Multigranular Motion Features
L Zhang, Y Wang, B Hui, X Zhang, S Liu… - arXiv preprint arXiv …, 2022 - arxiv.org
The recognition of behaviors in videos usually requires a combinatorial analysis of the
spatial information about objects and their dynamic action information in the temporal …
spatial information about objects and their dynamic action information in the temporal …
Self-supervised Learning of Occlusion Aware Flow Guided 3D Geometry Perception with Adaptive Cross Weighted Loss from Monocular Videos
F Jiaojiao, L Guizhong - 2021 IEEE International Conference …, 2021 - ieeexplore.ieee.org
Self-supervised deep learning-based 3D scene understanding methods can overcome the
difficulty of acquiring the densely labeled ground-truth and have made a lot of advances …
difficulty of acquiring the densely labeled ground-truth and have made a lot of advances …