Xi Yang

18

Papers

141

Total Citations

Papers (18)

MLVU: Benchmarking Multi-task Long Video Understanding

PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection

Unraveling Batch Normalization for Realistic Test-Time Adaptation

Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs

Disentangling Tabular Data Towards Better One-Class Anomaly Detection

Semantic-Aware Data Augmentation for Text-to-Image Synthesis

LineArt: A Knowledge-guided Training-free High-quality Appearance Transfer for Design Drawing with Diffusion Model

Multi-Label Prototype Visual Spatial Search for Weakly Supervised Semantic Segmentation

Towards a Universal 3D Medical Multi-modality Generalization via Learning Personalized Invariant Representation

Get a Head Start: On-Demand Pedagogical Policy Selection in Intelligent Tutoring

Rethinking Multi-domain Generalization with A General Learning Objective

DIH-CLIP: Unleashing the Diversity of Multi-Head Self-Attention for Training-Free Open-Vocabulary Semantic Segmentation

Dual Domain Control via Active Learning for Remote Sensing Domain Incremental Object Detection

Dual Information Purification for Lightweight SAR Object Detection

Optimizing Label Assignment for Weakly Supervised Person Search

RoPaSS: Robust Watermarking for Partial Screen-Shooting Scenarios

Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis

MuST: Robust Image Watermarking for Multi-Source Tracing