collaborators

5 papers

cs.CV2024

Selectively Dilated Convolution for Accuracy-Preserving Sparse Pillar-based Embedded 3D Object Detection

Seongmin Park, Minjae Lee, Junwon Choi +1

Pillar-based 3D object detection has gained traction in self-driving technology due to its speed and accuracy facilitated by the artificial densification of pillars for GPU-friendl…

cs.CV20241 cited

Learning Equi-angular Representations for Online Continual Learning

Minhyuk Seo, Hyunseo Koh, Wonje Jeung +7

Online continual learning suffers from an underfitted solution due to insufficient training for prompt model update (e.g., single-epoch training). To address the challenge, we prop…

eess.AS2023

Rethinking Session Variability: Leveraging Session Embeddings for Session Robustness in Speaker Verification

Hee-Soo Heo, KiHyun Nam, Bong-Jin Lee +4

In the field of speaker verification, session or channel variability poses a significant challenge. While many contemporary methods aim to disentangle session information from spea…

cs.AI2023

Leveraging Skill-to-Skill Supervision for Knowledge Tracing

Hyeondey Kim, Jinwoo Nam, Minjae Lee +2

Knowledge tracing plays a pivotal role in intelligent tutoring systems. This task aims to predict the probability of students answering correctly to specific questions. To do so, k…

cs.SD2023

Encoder-decoder multimodal speaker change detection

Jee-weon Jung, Soonshin Seo, Hee-Soo Heo +5

The task of speaker change detection (SCD), which detects points where speakers change in an input, is essential for several applications. Several studies solved the SCD task using…