2 papers
cs.CV2021
Unsupervised Motion Representation Enhanced Network for Action Recognition
Xiaohang Yang, Lingtong Kong, Jie Yang
Learning reliable motion representation between consecutive frames, such as optical flow, has proven to have great promotion to video understanding. However, the TV-L1 method, an e…
cs.CV2021
OAS-Net: Occlusion Aware Sampling Network for Accurate Optical Flow
Lingtong Kong, Xiaohang Yang, Jie Yang
Optical flow estimation is an essential step for many real-world computer vision tasks. Existing deep networks have achieved satisfactory results by mostly employing a pyramidal co…