7 papers
ToLL: Topological Layout Learning with Asymmetric Cross-View Structural Distillation for 3D Scene Graph Generation Pretraining
Yucheng Huang, Luping Ji, Xiangwei Jiang +2
3D Scene Graph (3DSG) generation plays a pivotal role in spatial understanding and affordance perception. To mitigate generalization issues from data scarcity, joint-embedding and…
H2VLR: Heterogeneous Hypergraph Vision-Language Reasoning for Few-Shot Anomaly Detection
Jianghong Huang, Luping Ji, Weiwei Duan +1
As a classic vision task, anomaly detection has been widely applied in industrial inspection and medical imaging. In this task, data scarcity is often a frequently-faced issue. To…
Weakly-supervised Contrastive Learning with Quantity Prompts for Moving Infrared Small Target Detection
Weiwei Duan, Luping Ji, Shengjia Chen +3
Different from general object detection, moving infrared small target detection faces huge challenges due to tiny target size and weak background contrast.Currently, most existing…
BeltCrack: the First Sequential-image Industrial Conveyor Belt Crack Detection Dataset and Its Baseline with Triple-domain Feature Learning
Jianghong Huang, Luping Ji, Xin Ma +1
Conveyor belts are important equipment in modern industry, widely applied in production and manufacturing. Their health is much critical to operational efficiency and safety. Crack…
LGU-SLAM: Learnable Gaussian Uncertainty Matching with Deformable Correlation Sampling for Deep Visual SLAM
Yucheng Huang, Luping Ji, Hudong Liu +1
Deep visual Simultaneous Localization and Mapping (SLAM) techniques, e.g., DROID, have made significant advancements by leveraging deep visual odometry on dense flow fields. In gen…
Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification
Jiaxiang Gou, Luping Ji, Pei Liu +1
Whole Slide Image (WSI) classification has very significant applications in clinical pathology, e.g., tumor identification and cancer diagnosis. Currently, most research attention…