3 papers
cs.CV2026
Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label
Mengke Li, Haiquan Ling, Yiqun Zhang +2
Real-world data often exhibit long-tailed distributions with numerous noisy labels, substantially degrading the performance of deep models. While prior research has made progress i…
cs.CV2025
ADNet: A Large-Scale and Extensible Multi-Domain Benchmark for Anomaly Detection Across 380 Real-World Categories
Hai Ling, Jia Guo, Zhulin Tao +6
Anomaly detection (AD) aims to identify defects using normal-only training data. Existing anomaly detection benchmarks (e.g., MVTec-AD with 15 categories) cover only a narrow range…
cs.IR2025
AUV-Fusion: Cross-Modal Adversarial Fusion of User Interactions and Visual Perturbations Against VARS
Hai Ling, Tianchi Wang, Xiaohao Liu +3
Modern Visual-Aware Recommender Systems (VARS) exploit the integration of user interaction data and visual features to deliver personalized recommendations with high precision. How…