|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Third, beyond two-view depth estimation, we further extend the above networks to fuse depth information from multiple target images and estimate the depth map of the source image.
When adding our network layer to state-of-the-art networks for optical flow and semantic segmentation, boundary artifacts are removed and the accuracy is improved.
Most of current Convolution Neural Network (CNN) based methods for optical flow estimation focus on learning optical flow on synthetic datasets with groundtruth, which is not practical.
We introduce a self-supervised method for learning visual correspondence from unlabeled video.
However, extracting motion information, specifically in the form of optical flow features, is extremely computationally expensive, especially for large-scale video classification.
Exploration bonuses derived from the novelty of observations in an environment have become a popular approach to motivate exploration for reinforcement learning (RL) agents in the past few years.
Our method is ranked first in the public leaderboard of the EPIC-Kitchens egocentric action anticipation challenge 2019.
Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes.