AI Paper Atlas

Research map / Video / Video-language understanding

OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning

Zhijia Liang, Jiaming Li, Weikai Chen, Yanhao Zhang, Haonan Lu, Guanbin Li

CVPR 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 9 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 fine-reasoning retrieval (RAG stage) (ablation)OASIS (Qwen3-VL-8B) · OVO-Bench Backwardaccuracy: 55.22 -> 57.21Improved
generate retrieval cue from history instead of naive question retrieval (ablation)OASIS (Qwen3-VL-8B) · OVO-Bench Backwardaccuracy: 56.13 -> 57.21Improved
bound root nodes (hierarchical event forest) vs flatten memory (ablation)OASIS (Qwen3-VL-8B) · OVO-Bench Perceptionaccuracy: 76.70 -> 78.14Improved
bound root nodes (hierarchical event forest) vs flatten memory (ablation)OASIS (Qwen3-VL-8B) · OVO-Bench Backwardaccuracy: 55.78 -> 57.21Improved
add event forest to medium buffer and short window (ablation)OASIS (Qwen3-VL-8B) · OVO-Bench Backwardaccuracy: 54.15 -> 57.21Improved
add short window to medium buffer and event forest (ablation)OASIS (Qwen3-VL-8B) · OVO-Bench Perceptionaccuracy: 70.37 -> 78.14Improved
add medium buffer to event forest and short window (ablation)OASIS (Qwen3-VL-8B) · OVO-Bench Backwardaccuracy: 48.65 -> 57.21Improved
increase retrieved event nodes k_f from 1 to 2 (ablation)OASIS (Qwen3-VL-8B) · OVO-Bench Perceptionaccuracy: 77.12 -> 78.14Improved
increase retrieved event nodes k_f from 2 to 3 (ablation)OASIS (Qwen3-VL-8B) · OVO-Bench Backwardaccuracy: 57.21 -> 56.90No clear effect
vary merge penalty lambda from 0.0 to 1.0 (ablation)OASIS (Qwen3-VL-8B) · OVO-Bench Perceptionaccuracy: 78.26 -> 78.65No clear effect
increase retrieved QA pairs k_q from 1 to 3 (ablation)OASIS (Qwen3-VL-8B) · StreamingBench SQAaccuracy: 48.40 -> 49.20Improved
add OASIS to Qwen3-VL-8BQwen3-VL-8B · OVO-Bench Perceptionaccuracy: 66.79 -> 78.14Improved

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