AI Paper Atlas

Research map / Video / Video-language understanding

Factorized Learning for Temporally Grounded Video-Language Models

Wenzheng Zeng, Difei Gao, Mike Zheng Shou, Hwee Tou Ng

ICCV 2025 · Video › Video-language understanding · approach: Long video understanding · 2 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
decompose grounding and answering into grounding-then-answer objective (ablation)D2VLM · E.T. Bench GroundingAvg F1: 21.2 -> 28.9Improved
decompose grounding and answering into grounding-then-answer objective (ablation)D2VLM · E.T. Bench Dense CaptioningAvg Sim: 11.3 -> 16.0Improved
use interleaved text-evi token generation in answering (ablation)D2VLM · E.T. Bench GroundingAvg F1: 28.9 -> 35.6Improved
use interleaved text-evi token generation in answering (ablation)D2VLM · E.T. Bench Dense CaptioningAvg F1: 23.1 -> 34.3Improved
add consistency constraint between the two evi stages (ablation)D2VLM · E.T. Bench GroundingAvg F1: 35.6 -> 39.5Improved
add consistency constraint between the two evi stages (ablation)D2VLM · E.T. Bench Dense CaptioningAvg Sim: 19.8 -> 21.2Improved
add event-level modeling of evi token (ablation)D2VLM · E.T. Bench GroundingAvg F1: 26.1 -> 39.5Improved
add event-level modeling of evi token (ablation)D2VLM · E.T. Bench Dense CaptioningAvg Sim: 16.2 -> 21.2Improved
add visual semantic capture into evi token (ablation)D2VLM · E.T. Bench Dense CaptioningAvg F1: 27.5 -> 35.0Improved
add visual semantic capture into evi token (ablation)D2VLM · E.T. Bench GroundingAvg F1: 37.1 -> 39.5Improved
add factorized preference optimization (FPO) (ablation)D2VLM · E.T. Bench GroundingAvg F1: 39.5 -> 42.3Improved
add factorized preference optimization (FPO) (ablation)D2VLM · E.T. Bench Dense CaptioningAvg F1: 35.0 -> 37.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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