AI Paper Atlas

Research map / Video / Video-language understanding

Open-ended Hierarchical Streaming Video Understanding with Vision Language Models

Hyolim Kang, Yunsu Park, Youngbeom Yoo, Yeeun Choi, Seon Joo Kim

ICCV 2025 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 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 progress-drop based action end detection (hybrid boundary detection) (ablation)OpenHOUSE streaming module · EgoGS step (GT labels)F1 (loc.): 16.78 -> 39.35Improved
add hybrid boundary detection (ablation)OpenHOUSE streaming module · EgEx substep (GT labels)F1 (loc.): 8.42 -> 52.2Improved
add hybrid boundary detection (ablation)OpenHOUSE streaming module · EK100 substep (GT labels)F1 (loc.): 31.46 -> 48.95Improved
train on LLM pseudo step labels instead of ground-truth (ablation)OpenHOUSE streaming module · EgoGS stepF1 (loc.) @tIoU 0.3: 51.58 -> 50.65No clear effect
sample frames by hierarchy and add previous predictions to context memory (ablation)OpenHOUSE VLM captioning · EgoGS step captionsF1 (loc.+desc.): 13.08 -> 13.05 with 22770 instead of 59385 framesNo clear effect
add previous text predictions as context given hierarchical frames (ablation)OpenHOUSE VLM captioning · EgoGS step captionsGPT Score: 2.42 -> 2.76Improved
use lightweight streaming module as VLM caller rather than a VLM on every frameOpenHOUSE · 46-minute video inferenceinference speed: 24 fps, 16 times fasterImproved
merge EgoGS and EgEx training data (ablation)OpenHOUSE · EK100 validation (cross-dataset)F1 (loc.) @tIoU 0.3, step: 42.49 -> 51.64 (vs EgoGS only)Improved
use OAD-based streaming instead of SDVC fixed decoding pointsHierarchical streaming understanding · EgoGS stepAEDT (s): 36.36 -> 4.94Improved
use frozen powerful VLM with SDVC proposals instead of fine-tuning SDVC (ablation)SDVC · EgoGS stepF1 (loc.+desc.) @tIoU 0.3: 2.61 -> 6.20Improved
use a smaller VLM (InternVL2-8B instead of InternVL2-40B-AWQ) (ablation)OpenHOUSE captioning · EgoGS stepF1 (loc.+desc.) @tIoU 0.3: 15.23 -> 10.01Hurt
use GPT-4o instead of InternVL2-40B-AWQ (ablation)OpenHOUSE captioning · EgoGS stepF1 (loc.+desc.) @tIoU 0.3: 15.23 -> 15.53No clear effect

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