AI Paper Atlas

Research map / Video / Video segmentation and tracking

DetectSCI: Toward Object-Guided ROI Reconstruction for High-Resolution Video Snapshot Compressive Imaging

Xingjian Jiang, Lishun Wang, Ping Wang, Xin Yuan

CVPR 2026 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors

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 INR block to RT-DETR baseline (ablation)RT-DETR · SportsMOT SCIAP: 76.8 -> 79.5Improved
add multi-scale spatial Mamba block to RT-DETR baseline (ablation)RT-DETR · SportsMOT SCIAP: 76.8 -> 79.6Improved
combine single-scale MSM with INR (ablation)MSM only · SportsMOT SCIAP: 79.6 -> 79.9Improved
use independent multi-scale MSM (ablation)single-scale MIM · SportsMOT SCIAP: 79.9 -> 82.5Improved
share weights across scales in MIM (ablation)independent MIM · SportsMOT SCIAP: 82.5 -> 80.9; params 61.2M -> 53.1MMixed
add Frequency Mamba (all bands fused) (ablation)DetectSCI without FM · SportsMOT SCIAP: 78.4 -> 80.9Improved
add low-frequency branch only (ablation)DetectSCI without FM · SportsMOT SCIAP: 78.4 -> 78.8Improved
add high-frequency branch only (ablation)DetectSCI without FM · SportsMOT SCIAP: 78.4 -> 80.1Improved
fuse all three bands vs best single band (ablation)high-frequency only FM · SportsMOT SCIAP: 80.1 -> 80.9Improved

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