AI Paper Atlas

Research map / Video / Video-language understanding

VideoOrion: Tokenizing Object Dynamics in Videos

Yicheng Feng, Yijiang Li, Wanpeng Zhang, Sipeng Zheng, Hao Luo, Zihao Yue, Zongqing Lu

ICCV 2025 · Video › Video-language understanding · approach: Long video understanding · 8 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 object-centric branch with object tokens (ablation)VideoLLaMA2 · MVBench (ablation subset data)accuracy: 41.9 -> 44.2Improved
add object-centric branch with object tokens (ablation)VideoLLaMA2 · EgoSchema (ablation subset data)accuracy: 41.3 -> 44.5Improved
add object-centric branch with object tokens (ablation)VideoLLaMA2 · Perception-Test (ablation subset data)accuracy: 43.6 -> 46.3Improved
add object-centric branch with object tokens (ablation)VideoLLaMA2 · ActivityNet-QA (ablation subset data)accuracy: 43.0 -> 43.3No clear effect
split video into clips with RAM++ tag changes instead of no split (ablation)VideoOrion · Average over 5 benchmarks (ablation subset data)average accuracy: 43.9 -> 44.9Improved
split with RAM++ instead of uniform segmentation (ablation)VideoOrion · Average over 5 benchmarks (ablation subset data)average accuracy: 44.7 -> 44.9No clear effect
use GroundingDINO instead of Mask2Former for object proposals (ablation)VideoOrion · Average over 5 benchmarks (ablation subset data)average accuracy: 43.4 -> 44.9Improved
use XMem instead of SAM2 for tracking (ablation)VideoOrion · Average over 5 benchmarks (ablation subset data)average accuracy: 44.4 -> 44.9No clear effect
use MLP instead of linear object projector (ablation)VideoOrion · Average over 5 benchmarks (Table 6 subset)average accuracy: 45.52 -> 46.73No clear effect
use MLP instead of attention object projector (ablation)VideoOrion · Average over 5 benchmarks (Table 6 subset)average accuracy: 45.51 -> 46.73Improved
use MLP instead of LSTM object projector (ablation)VideoOrion · Average over 5 benchmarks (Table 6 subset)average accuracy: 46.45 -> 46.73No clear effect
use CLIP instead of DINOv2-L for object features (ablation)VideoOrion · Average over 5 benchmarks (Table 6 subset)average accuracy: 43.6 -> 46.73Improved

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