activity
20242026
collaborators

6 papers

cs.CV2026

Distill, Diffuse, Segment: Unsupervised 3D Semantic Segmentation for Autonomous Driving Based on Multi-Level Distillation and Graph Diffusion

Yijing Wang, Ruonan Li, Qilin Wang +2

LiDAR-based semantic segmentation is essential for autonomous-driving perception, yet dense point-wise annotations are costly, and long-tailed outdoor scenes make small safety-crit…

cs.LG2026

IGADA-IoT: IoT Sensor Energy Optimization in Wireless Sensor Networks Driven by Automatic Data Augmentation

Mingchun Sun, Rongqiang Zhao, Muhammad Abdul Munnaf +1

In wireless sensor networks (WSNs), data augmentation is a novel method to improve sampling-frequency decision performance, thereby enabling energy optimization for IoT (Internet o…

cs.CV2026

Feature Recalibration Based Olfactory-Visual Multimodal Model for Enhanced Rice Deterioration Detection

Rongqiang Zhao, Hengrui Hu, Yijing Wang +2

Multimodal methods are widely used in rice deterioration detection, but they exhibit limited capability in representing and extracting fine-grained abnormal features. Moreover, the…

cs.LG2026

IT-OSE: Exploring Optimal Sample Size for Industrial Data Augmentation

Mingchun Sun, Rongqiang Zhao, Zhennan Huang +2

In industrial scenarios, data augmentation is an effective approach to improve model performance. However, its benefits are not unidirectionally beneficial. There is no theoretical…

cs.LG2025

DS-Diffusion: Data Style-Guided Diffusion Model for Time-Series Generation

Mingchun Sun, Rongqiang Zhao, Hengrui Hu +2

Diffusion models are the mainstream approach for time series generation tasks. However, existing diffusion models for time series generation require retraining the entire framework…

cs.CV2024

DIVESPOT: Depth Integrated Volume Estimation of Pile of Things Based on Point Cloud

Yiran Ling, Rongqiang Zhao, Yixuan Shen +3

Non-contact volume estimation of pile-type objects has considerable potential in industrial scenarios, including grain, coal, mining, and stone materials. However, using existing m…