FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries

TL;DR

FLARE is a comprehensive benchmark for long-video audiovisual retrieval using user-simulated queries, addressing limitations of existing short-clip, single-modality datasets and evaluating multimodal retrieval performance.

Contribution

Introduces FLARE, a large-scale, diverse, full-modality long-video retrieval benchmark with user-simulated queries and a bimodal filtering constraint, enabling more realistic evaluation.

Findings

User-style queries significantly alter model behavior.

Strong caption-based performance does not always translate to query-based retrieval.

Audio-language alignment is a key bottleneck for audiovisual retrieval.

Abstract

As video becomes increasingly central to information dissemination and multimodal large language models (MLLMs) continue to advance, evaluating video retrieval has become increasingly important. In realistic search scenarios, this requires matching short user queries to long-form content using both visual and auditory evidence. Yet existing retrieval benchmarks are still dominated by short clips, single modalities, and caption-based evaluation. We introduce FLARE, a full-modality long-video audiovisual retrieval benchmark with user-simulated queries. Built from 399 carefully screened Video-MME videos (10--60 min, 225.4 h) to ensure source quality and diversity, FLARE contains 87,697 clips annotated with vision, audio, and unified audiovisual captions, together with 274,933 user-style queries. Cross-modal queries are further filtered by a hard bimodal constraint, requiring retrieval to fail under either modality alone but succeed when both are combined. FLARE evaluates models under two regimes, caption-based and query-based retrieval, across vision, audio, and unified audiovisual settings. Experiments with 15 representative retrievers show that user-style queries substantially change model behavior, strong caption-based performance does not always transfer to query-based retrieval, and audio--language alignment remains a key bottleneck for unified audiovisual retrieval. Our code and data are released at https://flarebench.github.io/