Perception and Intelligence Laboratory
Notice
Notice
[2022-03-16] 본 연구실은 지도교수님의 은퇴가 가까워진 관계로, 석/박사 과정 학생을 선발하지 않습니다.
Recent Publications
Recent Publications
Gene-Gene Relationship Modeling Based on Genetic Evidence for Single-Cell RNA-Seq Data Imputation (NeurIPS, 2024)
Gene-Gene Relationship Modeling Based on Genetic Evidence for Single-Cell RNA-Seq Data Imputation (NeurIPS, 2024)
Learnable Negative Proposals Using Dual-Signed Cross-Entropy Loss for Weakly Supervised Video Moment Localization (MM, 2024)
Learnable Negative Proposals Using Dual-Signed Cross-Entropy Loss for Weakly Supervised Video Moment Localization (MM, 2024)
MoST: Motion Style Transformer between Diverse Action Contents (CVPR, 2024)
MoST: Motion Style Transformer between Diverse Action Contents (CVPR, 2024)
Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding
Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding
(AAAI, 2024)
(AAAI, 2024)
Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis (CVPR, 2023)
Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis (CVPR, 2023)
Balanced Energy Regularization Loss for Out-of-distribution Detection (CVPR, 2023)
Balanced Energy Regularization Loss for Out-of-distribution Detection (CVPR, 2023)
Confidence-Based Feature Imputation for Graphs with Partially Known Features (ICLR, 2023)
Confidence-Based Feature Imputation for Graphs with Partially Known Features (ICLR, 2023)
Research
Research
The goal of the PILab is to gain useful technologies on perception and intelligence which can be applied to visual surveillance systems, inspection machines, robots, etc.
We are developing perceptual primitives to detect, track, and recognize human/vehicles, faces and to understand abnormal behaviors and situations through visual information. In addition, we are developing incremental learning models including probabilistic learning machines for integrating multiple sensory modalities in the changing environments.