2 papers
cs.CV2019
EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency
Muhammad Faisal, Ijaz Akhter, Mohsen Ali +1
The existing approaches for salient motion segmentation are unable to explicitly learn geometric cues and often give false detections on prominent static objects. We exploit multiv…
cs.CV2019
Super-Trajectories: A Compact Yet Rich Video Representation
Ijaz Akhter, Cheong Loong Fah, Richard Hartley
We propose a new video representation in terms of an over-segmentation of dense trajectories covering the whole video. Trajectories are often used to encode long-temporal informati…