Existing dense or paragraph video captioning approaches rely on holistic...
Recent advances in pixel-level tasks (e.g., segmentation) illustrate the...
We propose a bootstrapping framework to enhance human optical flow and p...
Neural Radiance Fields (NeRFs) increase reconstruction detail for novel ...
Human pose estimation from single images is a challenging problem that i...
The problem of language grounding has attracted much attention in recent...
We present an online SLAM system specifically designed to track pan-tilt...
Calibrating sports cameras is important for autonomous broadcasting and
...
In the real world, a learning system could receive an input that looks
n...
This work addresses camera selection, the task of predicting which camer...
Calibrating narrow field of view soccer cameras is challenging because t...
In this work, we address the problem of 3D human pose estimation from a
...
Camera relocalization plays a vital role in many robotics and computer v...
Camera relocalization plays a vital role in many robotics and computer v...
Vision based player detection is important in sports applications. Accur...
Following the success of deep convolutional networks, state-of-the-art
m...
Video games are a compelling source of annotated data as they can readil...
Commonly used human motion capture systems require intrusive attachment ...
Recently, Babenko and Lempitsky introduced Additive Quantization (AQ), a...
This paper introduces a novel self-learning framework that automates the...