activity
20212024
most citedRobust Region Feature Synthesizer for Zero-Shot Object Detection

3 citations · 12 across the 13 of their papers we have counts for

collaborators

10 papers

cs.CV20242 cited

AUG: A New Dataset and An Efficient Model for Aerial Image Urban Scene Graph Generation

Yansheng Li, Kun Li, Yongjun Zhang +2

Scene graph generation (SGG) aims to understand the visual objects and their semantic relationships from one given image. Until now, lots of SGG datasets with the eyelevel view are…

math.ST2024

Statistical inference for multi-regime threshold Ornstein-Uhlenbeck processes

Yuecai Han, Dingwen Zhang

In this paper, we investigate the parameter estimation for threshold OrnsteinUhlenbeck processes. Least squares method is used to obtain continuous-type and discrete-ty…

cs.CV2024

Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure

De Cheng, Yanling Ji, Dong Gong +4

In real-world applications, image degeneration caused by adverse weather is always complex and changes with different weather conditions from days and seasons. Systems in real-worl…

cs.CV2023

SegGPT Meets Co-Saliency Scene

Yi Liu, Shoukun Xu, Dingwen Zhang +1

Co-salient object detection targets at detecting co-existed salient objects among a group of images. Recently, a generalist model for segmenting everything in context, called SegGP…

cs.CV20231 cited

Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics

Chaowei Fang, Dingwen Zhang, Wen Zheng +4

Recently, long-tailed image classification harvests lots of research attention, since the data distribution is long-tailed in many real-world situations. Piles of algorithms are de…

cs.CV20231 cited

Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt

Hao Li, Dingwen Zhang, Nian Liu +5

Recently, inspired by DETR variants, query-based end-to-end instance segmentation (QEIS) methods have outperformed CNN-based models on large-scale datasets. Yet they would lose eff…