AI Paper Atlas

Research map / Video / Video segmentation and tracking

DualScope: Capturing Critical Spatial and Temporal Cues for Distracted Driving Activity Recognition

Zhijie Qiu, Shuaibo Li, Laixin Zhang, Xuming Hu, Wei Ma

AAAI 2026 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 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
replace pretrained ViT-L/14 with behavior-centric encoder BCVE (ablation)DualScope · 5 video datasets avgtop-1 accuracy (%): 87.23 -> 90.84Improved
add Dynamic Difference Extractor (ablation)DualScope · 5 video datasets avgtop-1 accuracy (%): 87.49 -> 90.84Improved
add Fine-Grained Motion Encoder (ablation)DualScope · 5 video datasets avgtop-1 accuracy (%): 89.76 -> 90.84Improved
add SATPM temporal pyramid on top of FGME (ablation)DualScope · 5 video datasets avgtop-1 accuracy (%): 79.34 -> 90.84Improved
increase SATPM blocks from 1 to 3 (ablation)DualScope · 5 video datasets avgtop-1 accuracy (%): 87.53 -> 90.84Improved
increase SATPM blocks from 3 to 4 (ablation)DualScope · 5 video datasets avgtop-1 accuracy (%): 90.84 -> 86.42Hurt
add Gradient Surgery to joint CRCD+IRDD training (ablation)BCVE · StateFarm+AUC avgtop-1 accuracy (%): 89.31 -> 91.86Improved
use task-specific adapters instead of full fine-tuning (ablation)BCVE · StateFarm+AUC avgtop-1 accuracy (%): 90.33 -> 91.86Improved
use TA+SI adapters instead of LoRA (ablation)BCVE · StateFarm+AUC avgtop-1 accuracy (%): 90.76 -> 91.86Improved
add SI-Adapter to TA-Adapter (ablation)BCVE · StateFarm+AUC avgtop-1 accuracy (%): 90.67 -> 91.86Improved
apply behavior-centric pretraining (BCVE) in zero-shotDualScope vs DriveCLIP · SynDD1/StateFarm/DMD/SAM-DD zero-shottop-1 accuracy (%): 54.00 -> 54.52 (SynDD1); 66.52 -> 66.87 (SAM-DD)No clear effect

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