Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval
The GENAI4E team's solution to AI City Challenge 2026 Track 4 builds upon a strong retrieval backbone and progressively integrates heterogeneous vision-language embedding models through score alignment and iterative ensemble fusion, followed by disagreement-aware VLM reranking for ambiguous queries.