AI Paper Atlas

Research map / Video / Video-language understanding

Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning

Wenzheng Zeng, Siyi Jiao, Chen Gao, Hwee Tou Ng, Mike Zheng Shou

ECCV 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 0 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 latent global planning tokens (ablation)Video-SALMONN 2+ 3B · ChronusAV DVCF1 / Sim: F1 32.7 -> 61.5; Sim 17.6 -> 38.4Improved
use textual planning instead of none (ablation)baseline · ChronusAV DVCF1 / Sim: F1 32.7 -> 37.4; Sim 17.6 -> 19.4Improved
latent instead of textual planning (ablation)PadCaptioner · ChronusAV DVCF1: 37.4 -> 61.5Improved
add event-factorized parallel decoding (ablation)PadCaptioner with planning · ChronusAV DVCT/token: 22.9 -> 13.8 msImproved
add parallel decoding (ablation)PadCaptioner with planning · ChronusAV DVCF1 / Sim: F1 61.5 -> 61.8; Sim 38.4 -> 38.8No clear effect
use factorized attention rather than standard causal attention (ablation)parallel decoding · ChronusAV DVCF1: 38.7 -> 61.8Improved
give each branch access to all global event tokens (ablation)factorized attention · ChronusAV DVCF1: 59.8 -> 61.8Improved
add audio-visual semantic aggregation into event tokens (ablation)global event tokens · ChronusAV DVCF1: 47.7 -> 61.8Improved
attention-guided instead of mean-pooling aggregation (ablation)global event tokens · ChronusAV DVCF1: 58.5 -> 61.8Improved
attention-guided instead of learned scoring head (ablation)global event tokens · ChronusAV DVCF1: 61.4 -> 61.8No clear effect
apply method to LongVALE-LLM base modelLongVALE-LLM · ChronusAV DVC (12K)F1 / Sim: F1 24.5 -> 36.5; Sim 21.0 -> 25.8Improved
PadCaptioner vs ChronusOmni 7Bdense video captioning · LongVALE DVCT/video: 16162.1 -> 4283.8 msImproved

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