EVENT-Retriever: Event-Aware Multimodal Image Retrieval for Realistic Captions
This addresses the problem of retrieving images for complex, realistic captions involving abstract events and narratives, which is incremental as it builds on existing vision-language methods with specific enhancements.
The paper tackled the challenge of event-based image retrieval from free-form captions by introducing a multi-stage framework that combines dense article retrieval, event-aware reranking, and multimodal matching, achieving the top-1 score on the private test set of Track 2 in the EVENTA 2025 Grand Challenge.
Event-based image retrieval from free-form captions presents a significant challenge: models must understand not only visual features but also latent event semantics, context, and real-world knowledge. Conventional vision-language retrieval approaches often fall short when captions describe abstract events, implicit causality, temporal context, or contain long, complex narratives. To tackle these issues, we introduce a multi-stage retrieval framework combining dense article retrieval, event-aware language model reranking, and efficient image collection, followed by caption-guided semantic matching and rank-aware selection. We leverage Qwen3 for article search, Qwen3-Reranker for contextual alignment, and Qwen2-VL for precise image scoring. To further enhance performance and robustness, we fuse outputs from multiple configurations using Reciprocal Rank Fusion (RRF). Our system achieves the top-1 score on the private test set of Track 2 in the EVENTA 2025 Grand Challenge, demonstrating the effectiveness of combining language-based reasoning and multimodal retrieval for complex, real-world image understanding. The code is available at https://github.com/vdkhoi20/EVENT-Retriever.