In this study, we address the challenge of 3D scene structure recovery f...
The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 ha...
Modern supervised semantic segmentation methods are usually finetuned ba...
Compared to the multi-stage self-supervised multi-view stereo (MVS) meth...
Since the advent of Neural Radiance Fields, novel view synthesis has rec...
Data-driven medium-range weather forecasting has attracted much attentio...
Vision Transformers have shown great potential in computer vision tasks....
Despite the promising results, existing oriented object detection method...
Modern incremental learning for semantic segmentation methods usually le...
It's a meaningful and attractive topic to build a general and inclusive
...
We present PolyBuilding, a fully end-to-end polygon Transformer for buil...
The rapid advancement of artificial intelligence technologies has given ...
In this paper, we address monocular depth estimation with deep neural
ne...
Recent masked image modeling (MIM) has received much attention in
self-s...
Domain generalization (DG) aims to learn a model on one or more differen...
Federated learning (FL) over resource-constrained wireless networks has
...
Point annotations are considerably more time-efficient than bounding box...
Rotated object detection in aerial images is still challenging due to
ar...
Data-driven approaches for medium-range weather forecasting are recently...
We propose a direct, regression-based approach to 2D human pose estimati...
We propose a human pose estimation framework that solves the task in the...
Supervised learning based object detection frameworks demand plenty of
l...
Triangle counting is a building block for a wide range of graph applicat...
We show a simple NMS-free, end-to-end object detection framework, of whi...
Over-the-air computation (AirComp) based federated learning (FL) is capa...