AI Paper Atlas

Research map / Video / Video-language understanding

DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models

Xinlong Chen, Weihong Lin, Jingyun Hua, Linli Yao, Yue Ding, Bozhou Li, Bohan Zeng, Yang Shi, Qiang Liu, Yuanxing Zhang, Pengfei Wan, Liang Wang

ECCV 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 15 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 SFT on 85K synthesized dialogue-aware captions (ablation)AVoCaDO · DiaDemBench (overall)REF / ASR: 38.7 / 51.7 -> 59.3 / 74.0Improved
add SFT on 85K synthesized captions (ablation)AVoCaDO · video-SALMONN-2 testsetTotal error: 37.3 -> 42.0Hurt
add GRPO stage 1 after SFT (ablation)DiaDem · DiaDemBench (overall)REF / ASR: 59.3 / 74.0 -> 64.7 / 77.6Improved
add GRPO stage 2 on duplicated high-difficulty subset (ablation)DiaDem · DiaDemBench (overall)REF / ASR: 64.7 / 77.6 -> 65.9 / 79.3Improved
add GRPO after SFT to fix SALMONN-2 degradation (ablation)DiaDem · video-SALMONN-2 testsetTotal error: 42.0 -> 36.5Improved
use staged training instead of single merged phase (ablation)GRPO · DiaDemBench (overall)REF / ASR: 64.5 / 78.2 -> 65.9 / 79.3Improved
add easy-sample filtering (ablation)GRPO · DiaDemBench (overall)REF / ASR: 63.2 / 78.2 -> 65.9 / 79.3Improved
add the dialogue reward (ablation)GRPO · DiaDemBench (overall)REF / ASR: 60.1 / 74.3 -> 65.9 / 79.3Improved
add dialogue reward (ablation)GRPO · UGC-VideoCapAvg. score: 75.2 -> 75.6No clear effect
use GRPO data as extra SFT data instead of RL (ablation)SFT model · DiaDemBench (overall)REF / ASR: 59.3 / 74.0 -> 59.2 / 73.6No clear effect
replace AVoCaDO dialogue reward with enhanced dialogue reward (ablation)GRPO Stage-2 · DiaDemBench (overall)REF / ASR: 63.7 / 77.2 -> 65.9 / 79.3Improved
post-train AVoCaDO into DiaDemAVoCaDO · UGC-VideoCapAvg. score: 73.2 -> 75.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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