AI Paper Atlas

Research map / Video / Video-language understanding

Streaming VideoLLMs for Real-Time Procedural Video Understanding

Dibyadip Chatterjee, Edoardo Remelli, Yale Song, Bugra Tekin, Abhay Mittal, Bharat Bhatnagar, Necati Cihan Camgoz, Shreyas Hampali, Eric Sauser, Shugao Ma, Angela Yao, Fadime Sener

ICCV 2025 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 5 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 long-term verbalization and interleaving (ablation)ProVideLLM-1B/5 · Ego4D GoalStep valper-frame mAP: 12.1 -> 13.0Improved
add long-term verbalization and interleaving (ablation)ProVideLLM-1B/5 · Ego4D GoalStep testper-frame mAP: 12.2 -> 12.9Improved
add long-term verbalization (ablation)ProVideLLM-8B/11+ · COIN next step forecastingTop-1 accuracy: 52.1 -> 53.6Improved
use single-view ProVideLLM with verbalization vs TempAgg + Goal with 12 viewsTempAgg + Goal · Assembly101 action anticipationTop-5 recall: 12.0 -> 13.8Improved
replace 2-layer MLP with QFormer on DINOv2 (5 tokens) (ablation)DINOv2 connector · EgoExo4D keystep valaccuracy: 32.4 -> 33.6Improved
replace QFormer with DETR-QFormer on DINOv2 (5 tokens) (ablation)DINOv2 connector · EgoExo4D keystep valaccuracy: 33.6 -> 34.7Improved
replace QFormer with DETR-QFormer on DINOv2 (17 tokens) (ablation)DINOv2 connector · EgoExo4D keystep valaccuracy: 38.1 -> 40.7Improved
replace QFormer with DETR-QFormer on SigLIP (5 tokens) (ablation)SigLIP connector · EgoExo4D keystep valaccuracy: 32.9 -> 30.9Hurt
replace SigLIP with DINOv2 using DETR-QFormer (17 tokens) (ablation)DETR-QFormer · EgoExo4D keystep valaccuracy: 33.6 -> 40.7Improved
use SigLIP CLS token instead of DINOv2 with 1 token MLP (ablation)MLP connector · EgoExo4D keystep valaccuracy: 28.7 -> 31.8Improved
add interleaving to verbalization in the multimodal cache (ablation)ProVideLLM-1B/5 · Ego4D GoalStep long videoruntime stabilityImproved
add verbalization of long-term past instead of visual tokens only (ablation)ProVideLLM-1B/5 · Ego4D GoalStep long videomemory: 40K -> 2.5K tokensImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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