activity
20162024
most citedSparse R-CNN: End-to-End Object Detection with Learnable Proposals

103 citations · 217 across the 23 of their papers we have counts for

collaborators
Showing cs.CVShow all

32 papers · 1 filter

cs.CV2024

Deep Understanding of Soccer Match Videos

Shikun Xu, Yandong Zhu, Gen Li +1

Soccer is one of the most popular sport worldwide, with live broadcasts frequently available for major matches. However, extracting detailed, frame-by-frame information on player a…

cs.CV202223 cited

Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation

Bo Yuan, Danpei Zhao, Shuai Shao +2

Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. Present UDA models focus on alleviati…

cs.CV20222 cited

Content-Variant Reference Image Quality Assessment via Knowledge Distillation

Guanghao Yin, Wei Wang, Zehuan Yuan +4

Generally, humans are more skilled at perceiving differences between high-quality (HQ) and low-quality (LQ) images than directly judging the quality of a single LQ image. This situ…

cs.CV2021

Weakly Supervised Person Search with Region Siamese Networks

Chuchu Han, Kai Su, Dongdong Yu +5

Supervised learning is dominant in person search, but it requires elaborate labeling of bounding boxes and identities. Large-scale labeled training data is often difficult to colle…

cs.CV2021

Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning

Chi Zhang, Henghui Ding, Guosheng Lin +3

Few-shot learning aims to adapt knowledge learned from previous tasks to novel tasks with only a limited amount of labeled data. Research literature on few-shot learning exhibits g…

cs.CV20211 cited

Memory Based Video Scene Parsing

Zhenchao Jin, Dongdong Yu, Kai Su +2

Video scene parsing is a long-standing challenging task in computer vision, aiming to assign pre-defined semantic labels to pixels of all frames in a given video. Compared with ima…