AI Paper Atlas

Research map / Video / Video segmentation and tracking

Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensing

Weitong Cai, Hang Zhang, Yukai Huang, Shitong Sun, Jiankang Deng, Songcen Xu, Jifei Song, Zhensong Zhang

CVPR 2026 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 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
keep continuous grayscale stream alongside triggered RGB (vs Only TrigRGB, 8.1% RGB) (ablation)ColorTrigger · StreamingBench (real-time visual understanding)overall accuracy: 68.76 -> 70.72Improved
use triggered instead of uniform RGB frames (8.1% RGB) (ablation)ColorTrigger + grayscale · StreamingBench (real-time visual understanding)overall accuracy: 69.00 -> 70.72Improved
keep grayscale stream alongside triggered RGB (34.3% RGB) (ablation)ColorTrigger · StreamingBench (real-time visual understanding)overall accuracy: 73.48 -> 75.24Improved
use triggered instead of uniform RGB frames (34.3% RGB) (ablation)ColorTrigger + grayscale · StreamingBench (real-time visual understanding)overall accuracy: 72.64 -> 75.24Improved
add grayscale stream to uniform RGB sampling (8.1% RGB) (ablation)Uniform RGB · StreamingBench (real-time visual understanding)overall accuracy: 65.52 -> 69.00Improved
add dynamic token router (64 gray tokens) at 8.1% RGB (ablation)Gray + TrigRGB · StreamingBench (real-time visual understanding)overall accuracy: 67.08 -> 70.72Improved
add dynamic token router (64 gray tokens) at 34.3% RGB (ablation)Gray + TrigRGB · StreamingBench (real-time visual understanding)overall accuracy: 68.96 -> 75.24Improved
use 256 gray tokens instead of dynamic router at 34.3% RGB (ablation)Gray + TrigRGB · StreamingBench (real-time visual understanding)overall accuracy: 75.24 -> 76.32Mixed
insert 8.1% triggered RGB frames into grayscale video (ablation)InternVL-3.5-8B grayscale · StreamingBench (real-time visual understanding)overall accuracy: 62.08 -> 70.72Improved
insert 33.1% triggered RGB frames into grayscale videoInternVL-3.5-8B grayscale · OVO-Benchoverall average: 47.9 -> 52.5Improved
use 37.6% triggered RGB instead of full RGBInternVL-3.5-8B · Video-MMEoverall accuracy: 65.6 -> 66.1Improved
replace full RGB by 34.3% triggered RGBInternVL-3.5-8B · StreamingBench (real-time visual understanding)overall accuracy: 77.20 -> 75.24Hurt

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