activity
20192022
most citedSelf-supervised Graph-level Representation Learning with Local and Global Structure

28 citations · 56 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV20222 cited

HIRL: A General Framework for Hierarchical Image Representation Learning

Minghao Xu, Yuanfan Guo, Xuanyu Zhu +5

Learning self-supervised image representations has been broadly studied to boost various visual understanding tasks. Existing methods typically learn a single level of image semant…

cs.CV2022

HCSC: Hierarchical Contrastive Selective Coding

Yuanfan Guo, Minghao Xu, Jiawen Li +4

Hierarchical semantic structures naturally exist in an image dataset, in which several semantically relevant image clusters can be further integrated into a larger cluster with coa…

cs.CV2021

Cross-category Video Highlight Detection via Set-based Learning

Minghao Xu, Hang Wang, Bingbing Ni +3

Autonomous highlight detection is crucial for enhancing the efficiency of video browsing on social media platforms. To attain this goal in a data-driven way, one may often face the…

cs.CV20209 cited

Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation

Hang Wang, Minghao Xu, Bingbing Ni +1

Transferring knowledges learned from multiple source domains to target domain is a more practical and challenging task than conventional single-source domain adaptation. Furthermor…

cs.CV2020

Cross-domain Detection via Graph-induced Prototype Alignment

Minghao Xu, Hang Wang, Bingbing Ni +2

Applying the knowledge of an object detector trained on a specific domain directly onto a new domain is risky, as the gap between two domains can severely degrade model's performan…

cs.CV20198 cited

Adversarial Domain Adaptation with Domain Mixup

Minghao Xu, Jian Zhang, Bingbing Ni +4

Recent works on domain adaptation reveal the effectiveness of adversarial learning on filling the discrepancy between source and target domains. However, two common limitations exi…