SGCCNet: Single-Stage 3D Object Detector With Saliency-Guided Data Augmentation and Confidence Correction Mechanismby Ao Liang,…
View-Invariant Pixelwise Anomaly Detection in Multi-object Scenes with Adaptive View Synthesisby Subin Varghese, Vedhus HoskereFirst…
Beyond Visual Appearances: Privacy-sensitive Objects Identification via Hybrid Graph Reasoningby Zhuohang Jiang, Bingkui Tong, Xia…
QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQLby Yinggang Sun, Ziming Guo, Haining Yu, Chuanyi…
SViTT-Ego: A Sparse Video-Text Transformer for Egocentric Videoby Hector A. Valdez, Kyle Min, Subarna TripathiFirst…
Test-Time Fairness and Robustness in Large Language Modelsby Leonardo Cotta, Chris J. MaddisonFirst submitted to…
Comparing Data Augmentation Methods for End-to-End Task-Oriented Dialog Systemsby Christos Vlachos, Themos Stafylakis, Ion AndroutsopoulosFirst…
Data Augmentation in Earth Observation: A Diffusion Model Approachby Tiago Sousa, Benoît Ries, Nicolas GuelfiFirst…
Improving Deep Learning-based Automatic Cranial Defect Reconstruction by Heavy Data Augmentation: From Image Registration to…
Solution for CVPR 2024 UG2+ Challenge Track on All Weather Semantic Segmentationby Jun Yu, Yunxiang…