3 papers
cs.CV2026
Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks
Jie Li, Hongyi Cai, Mingkang Dong +4
Automatically detecting abnormal events in videos is crucial for modern autonomous systems, yet existing Video Anomaly Detection (VAD) benchmarks lack the scene diversity, balanced…
cs.IR2026
When Vision Meets Texts in Listwise Reranking
Hongyi Cai
Recent advancements in information retrieval have highlighted the potential of integrating visual and textual information, yet effective reranking for image-text documents remains…
cs.CV2025
CFPFormer: Feature-pyramid like Transformer Decoder for Segmentation and Detection
Hongyi Cai, Mohammad Mahdinur Rahman, Wenzhen Dong +1
Feature pyramids have been widely adopted in convolutional neural networks and transformers for tasks in medical image segmentation. However, existing models generally focus on the…