activity
20142025
most citedDAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

400 citations · 652 across the 23 of their papers we have counts for

collaborators
Showing cs.CVShow all

12 papers · 1 filter

cs.CV2024

Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing

Ling-Hao Chen, Shunlin Lu, Wenxun Dai +5

This research delves into the problem of interactive editing of human motion generation. Previous motion diffusion models lack explicit modeling of the word-level text-motion corre…

cs.CV202310 cited

Spatial-Frequency Attention for Image Denoising

Shi Guo, Hongwei Yong, Xindong Zhang +2

The recently developed transformer networks have achieved impressive performance in image denoising by exploiting the self-attention (SA) in images. However, the existing methods m…

cs.CV202316 cited

Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation

Jie Yang, Ailing Zeng, Shilong Liu +3

This paper presents a novel end-to-end framework with Explicit box Detection for multi-person Pose estimation, called ED-Pose, where it unifies the contextual learning between huma…

cs.CV20234 cited

Adversarial Style Augmentation for Domain Generalization

Yabin Zhang, Bin Deng, Ruihuang Li +2

It is well-known that the performance of well-trained deep neural networks may degrade significantly when they are applied to data with even slightly shifted distributions. Recent…

cs.CV20221 cited

A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration

Ming Liu, Yuxiang Wei, Xiaohe Wu +2

Generative adversarial networks (GANs) have drawn enormous attention due to the simple yet effective training mechanism and superior image generation quality. With the ability to g…

cs.CV20227 cited

Box-supervised Instance Segmentation with Level Set Evolution

Wentong Li, Wenyu Liu, Jianke Zhu +3

In contrast to the fully supervised methods using pixel-wise mask labels, box-supervised instance segmentation takes advantage of the simple box annotations, which has recently att…