Search Results for author:
Found 11 papers, 4 papers with code
GCCN: Global Context Convolutional Network
These global contextual features are defined as local maxima pixels with high visual sharpness in each patch.
Signature-Graph Networks
SGN constructs unique undirected graphs for each image based on the CNN feature maps.
Tracking Cells and their Lineages via Labeled Random Finite Sets
Determining the trajectories of cells and their lineages or ancestries in live-cell experiments are fundamental to the understanding of how cells behave and divide.
Drone-as-a-Service Composition Under Uncertainty
Specifically, we propose a service model of DaaS based on the dynamic spatiotemporal features of drones and their in-flight contexts.
flexgrid2vec: Learning Efficient Visual Representations Vectors
We compare the performance of flexgrid2vec with a set of state-of-the-art visual representation learning models on binary and multi-class image classification tasks.
DroTrack: High-speed Drone-based Object Tracking Under Uncertainty
The combination of the FCM segmentation and the angular scaling increased DroTrack precision by up to $9\%$ and decreased the centre location error by $162$ pixels on average.
A Bayesian Filter for Multi-view 3D Multi-object Tracking with Occlusion Handling
This paper proposes an online multi-camera multi-object tracker that only requires monocular detector training, independent of the multi-camera configurations, allowing seamless extension/deletion of cameras without retraining effort.
Ranked #7 on
Multi-Object Tracking
on Wildtrack
GLMB Tracker with Partial Smoothing
In the forward filtering stage, we use the GLMB filter to generate a set of labels and the association history between labels and the measurements.
Online Multiple Pedestrians Tracking using Deep Temporal Appearance Matching Association
The higher dimension of inherent information in the appearance model compared to the geometric model is problematic in many ways.
Visual Multiple-Object Tracking for Unknown Clutter Rate
In multi-object tracking applications, model parameter tuning is a prerequisite for reliable performance.
Online Visual Multi-Object Tracking via Labeled Random Finite Set Filtering
Furthermore the labeled random finite set framework enables the incorporation of prior knowledge that mis-detections of long tracks which occur in the middle of the scene are likely to be due to occlusions.
