Bidirectional Likelihood Estimation With Multi-modal Large Language Models For Text-video Retrieval

Abstract

Text-Video Retrieval aims to find the most relevant text (or video) candidate given a video (or text) query from large-scale online databases. Recent work leverages multi-modal large language models (MLLMs) to improve retrieval, especially for long or complex query-candidate pairs. However, we observe that the naive application of MLLMs, i.e., retrieval based on candidate likelihood, introduces candidate prior bias, favoring candidates with inherently higher priors over those more relevant to the query. To this end, we propose a novel retrieval framework, Bidirectional Likelihood Estimation with MLLM (BLiM), which leverages both query and candidate likelihoods by training the model to generate text from a given video as well as video features from a given text. Furthermore, we introduce Candidate Prior Normalization (CPN), a simple yet effective training-free score calibration module designed to mitigate candidate prior bias in candidate likelihood. On four Text-Video Retrieval benchma

Stats

• citations0
• S2 citations—
• github stars23
• HF likes0
• heat score2.76
• arxiv keyko2025bidirectional

Related papers

• Indexing Multimodal Language Models For Large-scale Image Retrieval (2026)0.00
• Mm-embed: Universal Multimodal Retrieval With Multimodal Llms (2024)0.00
• Vidvec: Unlocking Video MLLM Embeddings For Video-text Retrieval (2026)0.00
• MERLIN: Multimodal Embedding Refinement Via Llm-based Iterative Navigation For Text-video Retrieval-rerank Pipeline (2024)5.84
• RETLLM: Training And Data-free Mllms For Multimodal Information Retrieval (2026)1.57
• Context-enhanced Video Moment Retrieval With Large Language Models (2024)5.84
• Modality-balanced Embedding For Video Retrieval (2022)7.16
• Verve: Versatile Retrieval For Videos Via Unified Embeddings (2026)0.00