Jungong Han

Continuity-Driven Pose Estimation for Videos

Hierarchical divide-and-conquer grouping for Zero shot learning

Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability

ShuffleNorm: A Better Normalization for Semi-supervised Learning

FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation

YOLOv10: Real-Time End-to-End Object Detection

Revisiting motion information for RGB-Event tracking with MOT philosophy

Motion PointNet: Solving Dynamic Capture in Point Cloud Video Human Action

Reconstruction as Sequence for Efficient Unified Unsupervised Anomaly Detection