Search Results for author: Ba-Ngu Vo

Found 13 papers, 3 papers with code

The Mean of Multi-Object Trajectories

no code implementations29 Apr 2025 Tran Thien Dat Nguyen, Ba Tuong Vo, Ba-Ngu Vo, Hoa Van Nguyen, Changbeom Shim

This paper introduces the concept of a mean for trajectories and multi-object trajectories--sets or multi-sets of trajectories--along with algorithms for computing them.

Multi-Object Tracking Object

An Overview of Multi-Object Estimation via Labeled Random Finite Set

no code implementations27 Sep 2024 Ba-Ngu Vo, Ba-Tuong Vo, Tran Thien Dat Nguyen, Changbeom Shim

Building on this, we outline the fundamentals of multi-object state space modeling and estimation using LRFS, which formally address object identities/trajectories, ancestries for spawning objects, and characterization of the uncertainty on the ensemble of objects (and their trajectories).

Multi-Object Tracking Object

Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking

3 code implementations28 May 2024 Linh Van Ma, Tran Thien Dat Nguyen, Ba-Ngu Vo, Hyunsung Jang, Moongu Jeon

Specifically, we exploit the 2D detections and extracted features from multiple cameras to provide a better approximation of the multi-object filtering density to realize the track initiation/termination and re-identification functionalities.

3D Multi-Object Tracking Object +1

Linear Complexity Gibbs Sampling for Generalized Labeled Multi-Bernoulli Filtering

no code implementations29 Nov 2022 Changbeom Shim, Ba-Tuong Vo, Ba-Ngu Vo, Jonah Ong, Diluka Moratuwage

Specifically, we propose a tempered Gibbs sampler that exploits the structure of the GLMB filtering density to achieve an $\mathcal{O}(T(P+M))$ complexity, where $T$ is the number of iterations of the algorithm, $P$ and $M$ are the number hypothesized objects and measurements.

Tracking Cells and their Lineages via Labeled Random Finite Sets

1 code implementation22 Apr 2021 Tran Thien Dat Nguyen, Ba-Ngu Vo, Ba-Tuong Vo, Du Yong Kim, Yu Suk Choi

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.

How Trustworthy are Performance Evaluations for Basic Vision Tasks?

1 code implementation8 Aug 2020 Tran Thien Dat Nguyen, Hamid Rezatofighi, Ba-Ngu Vo, Ba-Tuong Vo, Silvio Savarese, Ian Reid

This paper examines performance evaluation criteria for basic vision tasks involving sets of objects namely, object detection, instance-level segmentation and multi-object tracking.

Multi-Object Tracking object-detection +1

Model-Based Multiple Instance Learning

no code implementations7 Mar 2017 Ba-Ngu Vo, Dinh Phung, Quang N. Tran, Ba-Tuong Vo

While Multiple Instance (MI) data are point patterns -- sets or multi-sets of unordered points -- appropriate statistical point pattern models have not been used in MI learning.

Clustering Decision Making +4

Clustering For Point Pattern Data

no code implementations8 Feb 2017 Quang N. Tran, Ba-Ngu Vo, Dinh Phung, Ba-Tuong Vo

However, there has been limited research in the clustering of point patterns - sets or multi-sets of unordered elements - that are found in numerous applications and data sources.

Clustering

Online Visual Multi-Object Tracking via Labeled Random Finite Set Filtering

no code implementations18 Nov 2016 Du Yong Kim, Ba-Ngu Vo, Ba-Tuong Vo

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.

Management Multi-Object Tracking +3

A Generalized Labeled Multi-Bernoulli Filter Implementation using Gibbs Sampling

no code implementations2 Jun 2015 Hung Gia Hoang, Ba-Tuong Vo, Ba-Ngu Vo

This paper proposes an efficient implementation of the generalized labeled multi-Bernoulli (GLMB) filter by combining the prediction and update into a single step.

Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.