This paper studies distributed online learning under Byzantine attacks. ...
This work aims to present a joint resource allocation method for a
fog-a...
In distributed learning systems, robustness issues may arise from two
so...
Existing matching-based approaches perform video object segmentation (VO...
This paper focuses on online kernel learning over a decentralized networ...
We present a simple yet effective fully convolutional one-stage 3D objec...
This paper presents a novel model training solution, denoted as
Adaptive...
We propose a direct, regression-based approach to 2D human pose estimati...
As a promising distributed learning technology, analog aggregation based...
We propose a fully convolutional multi-person pose estimation framework ...
Very recently, a variety of vision transformer architectures for dense
p...
Federated learning (FL) is an attractive paradigm for making use of rich...
For distributed learning among collaborative users, this paper develops ...
We propose a human pose estimation framework that solves the task in the...
Almost all visual transformers such as ViT or DeiT rely on predefined
po...
We propose a simple yet effective framework for instance and panoptic
se...
We present a high-performance method that can achieve mask-level instanc...
Recently, fully-convolutional one-stage networks have shown superior
per...
We present a private information retrieval (PIR) scheme that allows a us...
In computer vision, object detection is one of most important tasks, whi...
To date, instance segmentation is dominated by twostage methods, as pion...
We propose a simple yet effective instance segmentation framework, terme...
We present a method for depth estimation with monocular images, which ca...
3D point cloud semantic and instance segmentation is crucial and fundame...
Instance segmentation is one of the fundamental vision tasks. Recently, ...
We propose the first direct end-to-end multi-person pose estimation
fram...
Recent progress has been made on developing a unified framework for join...
In this paper, we propose a communication- and computation-efficient
alg...
The success of deep neural networks relies on significant architecture
e...
This paper proposes a class of distributed event-triggered algorithms th...
We propose a fully convolutional one-stage object detector (FCOS) to sol...
Both accuracy and efficiency are of significant importance to the task o...
Recent semantic segmentation methods exploit encoder-decoder architectur...
Text detection and recognition in natural images have long been consider...
We propose a novel Connectionist Text Proposal Network (CTPN) that accur...