Self-supervised monocular depth estimation methods typically rely on the...
Current image processing methods usually operate on the finest-granulari...
Incorporating contrastive learning objectives in sentence representation...
An open problem on the path to artificial intelligence is generalization...
Reinforcement Learning (RL)-based control system has received considerab...
Considering the increasing concerns about data copyright and privacy iss...
Given an aerial image, aerial scene parsing (ASP) targets to interpret t...
Video captioning aims to automatically generate natural language sentenc...
Video summarization aims to select representative frames to retain high-...
The past decade has witnessed great progress on remote sensing (RS) imag...
Predicting future frames in natural video sequences is a new challenge t...
Perinatal stroke (PS) is a serious condition that, if undetected and thu...
Object detection in aerial images is an active yet challenging task in
c...
Gait is an important biometric trait for surveillance and forensic
appli...
We present ActionXPose, a novel 2D pose-based algorithm for posture-leve...
Unseen Action Recognition (UAR) aims to recognise novel action categorie...
Robust object recognition systems usually rely on powerful feature extra...