AI Paper Atlas

Research map / Video / Video-language understanding

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval

Dohwan Ko, Ji Soo Lee, Minhyuk Choi, Zihang Meng, Hyunwoo J. Kim

ICCV 2025 · Video › Video-language understanding · approach: Text-video retrieval · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add query likelihood estimation to candidate likelihood (QLE vs CLE) (ablation)BLiM no CPN · avg R@1 four text-video datasetsR@1: 27.3 -> 60.5Improved
combine candidate and query likelihoods (BLE vs QLE) (ablation)BLiM no CPN · avg R@1 four text-video datasetsR@1: 60.5 -> 61.3Improved
add Candidate Prior Normalization to candidate likelihood (ablation)CLE · avg R@1 four text-video datasetsR@1: 34.4 -> 59.2 (DiDeMo)Improved
add Candidate Prior Normalization to bidirectional estimation (ablation)BLiM BLE · avg R@1 four text-video datasetsR@1: 74.1 -> 81.3 (DiDeMo)Improved
fine-tune with bidirectional likelihood instead of zero-shot BLiM-BLiM · DiDeMo text-to-videoR@1: 69.8 -> 86.4Improved
rerank with BLiM instead of InternVideo2 6BBLiM · DiDeMo text-to-videoR@1: 74.2 -> 86.4Improved
use BLiM instead of other MLLM rerankers (RagVL)BLiM · DiDeMo text-to-videoR@1: 83.2 -> 86.4Improved
apply CPN decoding to VideoChat2VideoChat2 · VideoMME w/o subtitleaccuracy: 42.2 -> 47.1Improved
apply CPN decoding to LLaVA-OnevisionLLaVA-Onevision · VideoMME w/o subtitleaccuracy: 58.5 -> 61.7Improved
apply CPN decoding to InternVL2InternVL2 · MLVUaccuracy: 50.8 -> 55.1Improved
apply BLiM to text-image retrievalBLiM · COCO image-to-textR@1: 85.4 -> 84.2Hurt
apply CPN in text-to-video retrieval with CLE (ablation)CLE · DiDeMo text-to-videoR@1: 45.1 -> 45.1No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy