Computer Vision

Video Object Segmentation

Fast Video Object Segmentation with Temporal Aggregation Network and Dynamic Template Matching

Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories

+ Co-author of this work. + Formulation of zero-shot part discovery on a large-scale fine-grained shape segmentation benchmark. + A learning-based agglomerative clustering framework that learns to do part proposal and grouping from training categories and generalizes to unseen novel categories

GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond

+ Re-interpretation and connection of two top popular techniques proposed in CVPR 2018 (Non-local neural networks and SE-Net). + Unification of these the two techniques into a general framework. + Better instantiation of the general framework, which is about 50x faster than the non-local neural block, while achieving better accuracy than both techniques (non-local and SE-Net) on several recognition tasks such as ImageNet classification, COCO object detection and Kinetics action recognition.

Spatial-Temporal Relation Networks for Multi-Object Tracking

+ The first coherent and end-to-end framework for similarity measure which combines all of the appearance, motion and interaction cues. + Properly redesign of feature representation for the tracklet-object pair. + Achieve the state-of-the-art multi-object tracking (MOT) results on all of the MOT15-17 leaderboards using few bells and whistles.

End-to-End Deep HDR Imaging with Large Foreground Motions

This paper proposes the first end-to-end deep framework for high dynamic range (HDR) imaging of dynamic scenes with _**large-scale foreground motions**_.


Champion in International Wildcard Game