Joint Probabilistic Data Association Revisited

By Seyed Hamid Rezatofighi, Anton Milan, Zhen Zhang, Javen Qinfeng Shi, Anthony R. Dick, Ian David Reid. IEEE International Conference on Computer Vision, 2015

365 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Epidemiology

View Paper: https://www.semanticscholar.org/paper/b035e377fcdd5c4b3c9e4fabb2e6ea12982c680b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Simple online and realtime tracking (2016, methodology): “Firstly, there is a resurgence of mature data association techniques including Multiple Hypothesis Tracking (MHT) [7, 3] and Joint Probabilistic Data Association (JPDA) [2] which occupy many of the top positions of the MOT benchmark.”
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking (2020, methodology): “3 CRF OF 7 7 7 JPDA m [Rezatofighi et al., 2015] Mahalanobis distance 7 LP — 7 7 7 SegTrack [Milan et al.”
MOT16: A Benchmark for Multi-Object Tracking (2016, background): “ment hypotheses to be considered. It has thus long been considered impractical for computer vision applications, especially in crowded scenes. Recently, an efﬁcient approximation to JPDA was proposed [36]. The main idea is to approximate the full joint probability distribution by mstrongest hypothes”
Simple online and realtime tracking with a deep association metric (2017, methodology): “Both methods have recently been revisited in a tracking-by-detection scenario [10, 11] and shown promising results.”
Online Multi-object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism (2017, neutral): “5% 14180 34591 813 1023 JPDA m[16] 23.”
Online Multi-Target Tracking Using Recurrent Neural Networks (2016, methodology): “Finally, JPDA m is the full joint probabilistic data association approach, recently proposed in (Rezatoﬁghi et al. 2015), including post-processing.”
Multiple object tracking: A literature review (2014, background): “[139] MATLAB Zhang & Laurens [53], [54] MATLAB/C Pirsiavash et al.”
Learning by Tracking: Siamese CNN for Robust Target Association (2016, neutral): “8 1396 7345 JPDA-m [46] 23.”
UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking (2015, methodology): “Rezatoﬁghi et al. (2015) present a computationally tractable approximation to the original JPDA algorithm based on a recent method to ﬁnd the m -best solutions of an integer linear program.”
Dynamic Label Graph Matching for Unsupervised Video Re-identification (2017, methodology): “To mine the label information across cameras, we follow [4] to formulate it as a binary linear programming with linear constraints:”