Chunluan Zhou

8

Papers

11

Total Citations

Papers (8)

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians

Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking

Generalized Relation Modeling for Transformer Tracking

Multi-Label Learning of Part Detectors for Heavily Occluded Pedestrian Detection

Discriminative Feature Transformation for Occluded Pedestrian Detection

SOAR: Scene-debiasing Open-set Action Recognition

AiATrack: Attention in Attention for Transformer Visual Tracking