collaborators

5 papers

cs.CV2025

One-Cycle Structured Pruning via Stability-Driven Subnetwork Search

Deepak Ghimire, Dayoung Kil, Seonghwan Jeong +2

Existing structured pruning methods typically rely on multi-stage training procedures that incur high computational costs. Pruning at initialization aims to reduce this burden but…

cs.CV2025

Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration

Deepak Ghimire, Kilho Lee, Seong-heum Kim

Structured pruning is a well-established technique for compressing neural networks, making it suitable for deployment in resource-limited edge devices. This paper presents an effic…

cs.CV2025

Comparison of Two Methods for Stationary Incident Detection Based on Background Image

Deepak Ghimire, Joonwhoan Lee

In general, background subtraction-based methods are used to detect moving objects in visual tracking applications. In this paper, we employed a background subtraction-based scheme…

cs.CV2025

Study on Real-Time Road Surface Reconstruction Using Stereo Vision

Deepak Ghimire, Byoungjun Kim, Donghoon Kim +1

Road surface reconstruction plays a crucial role in autonomous driving, providing essential information for safe and smooth navigation. This paper enhances the RoadBEV [1] framewor…

cs.CV2025

Real-Time Sleepiness Detection for Driver State Monitoring System

Deepak Ghimire, Sunghwan Jeong, Sunhong Yoon +2

A driver face monitoring system can detect driver fatigue, which is a significant factor in many accidents, using computer vision techniques. In this paper, we present a real-time…