D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detectionby Dinh Phat Do,…
VisionGPT-3D: A Generalized Multimodal Agent for Enhanced 3D Vision Understandingby Chris Kelly, Luhui Hu, Jiayin…
Knowledge Distillation in YOLOX-ViT for Side-Scan Sonar Object Detectionby Martin Aubard, László Antal, Ana Madureira,…
MOD-CL: Multi-label Object Detection with Constrained Lossby Sota Moriyama, Koji Watanabe, Katsumi Inoue, Akihiro TakemuraFirst…
Cross-domain and Cross-dimension Learning for Image-to-Graph Transformersby Alexander H. Berger, Laurin Lux, Suprosanna Shit, Ivan…
Genetic Learning for Designing Sim-to-Real Data Augmentationsby Bram Vanherle, Nick Michiels, Frank Van ReethFirst submitted…
Fine-Grained Pillar Feature Encoding Via Spatio-Temporal Virtual Grid for 3D Object Detectionby Konyul Park, Yecheol…
Bootstrapping Rare Object Detection in High-Resolution Satellite Imageryby Akram Zaytar, Caleb Robinson, Gilles Q. Hacheme,…
LLMs in Political Science: Heralding a New Era of Visual Analysisby Yu WangFirst submitted to…
FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO…