9 citations · 10 across the 5 of their papers we have counts for
7 papers
Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise Assignment
Xiao Zhang, Yuxin Chen, Zhixuan Liang +5
When diffusion policies were first introduced, they were expected to recover multi-modal action distributions. However, we find this expectation does not always hold, as diffusion…
Adaptive Visual Token Reduction for Accelerated Image Understanding
Seyoung Jeong, Jong Pil Yun, Sang Jun Lee
Large Vision-Language Models achieve strong VQA performance, but processing high-resolution, information-rich images requires substantial computation, motivating visual token reduc…
Beer-Lambert Guided Representation Learning for Unsupervised Anomaly Detection in Sub-THz Food Inspection Images
Gyutae Hwang, Sang Jun Lee
Food manufacturing requires reliable inspection systems to detect foreign material contamination and maintain product safety. Sub-THz transmission imaging provides material-depende…
Instance-Aware Knowledge Distillation for Semi-Supervised Learning of an On-Board Multi-Task Dense Prediction Model for Collision Avoidance System
Gyutae Hwang, Sang Jun Lee
Collision avoidance systems have evolved toward camera-based deep learning approaches for driving scene understanding. However, deployment in edge environments such as country club…
Periodic-MAE: Periodic Video Masked Autoencoder for rPPG Estimation
Jiho Choi, Sang Jun Lee
In this paper, we propose Periodic-MAE, a self-supervised framework for learning generalizable spatio-temporal representations of periodic physiological signals from unlabeled faci…
Phase-shifted remote photoplethysmography for estimating heart rate and blood pressure from facial video
Gyutae Hwang, Sang Jun Lee
Human health can be critically affected by cardiovascular diseases, such as hypertension, arrhythmias, and stroke. Heart rate and blood pressure are important biometric information…
Selective Distillation of Weakly Annotated GTD for Vision-based Slab Identification System
Sang Jun Lee, Sang Woo Kim, Wookyong Kwon +2
This paper proposes an algorithm for recognizing slab identification numbers in factory scenes. In the development of a deep-learning based system, manual labeling to make ground t…