Multiple People Tracking by Lifted Multicut and Person Re-identification

By Siyu Tang, Mykhaylo Andriluka, Bjoern Andres, Bernt Schiele. Computer Vision and Pattern Recognition, 2017

555 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/73530b7ece291cd77e409bf03001dfc6983f602d

How researchers see this paper

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

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

TrackFormer: Multi-Object Tracking with Transformers (2021, methodology): “Other methods use association graphs [45], learned models [22], and motion information [21], general-purpose solvers [61], multicuts [48], weighted graph labeling [18], edge lifting [19], or trainable graph neural networks [6,54].”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, background): “A graph-based formulation to link person hypotheses is proposed for multi-person tracking [203], where the holistic features of the full human body and body pose layout are combined as the representation for each person.”
Learning Target Candidate Association to Keep Track of What Not to Track (2021, background): “The dominant paradigm in MOT is tracking-bydetection [5, 1, 49, 40, 52], where tracking is posed as the problem of associating object detections over time.”
Learning a Neural Solver for Multiple Object Tracking (2019, background): “non-maxima suppressed) detections to approach this challenge [9, 25, 24, 26, 12].”
An Empirical Study of Detection-Based Video Instance Segmentation (2019, background): “The top-performing class of tracking-bydetection methods [21, 28] link individual detections from each frame into object tracks via association.”
Real-Time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification (2018, methodology): “Some studies proposed to handle unreliable detection in a batch mode [2, 5, 6].”
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking (2020, methodology): “Interestingly, the ﬁrst methods outperforming NOMT on MOT16 were published only in 2017 (AMIR (Sadeghian et al. 2017) and NLLMP (Levinkov et al. 2017)).”
High Performance Visual Tracking with Siamese Region Proposal Network (2018, background): “Visual object tracking is a basic building block in various tasks of computer vision, such as automatic driving [19] and video surveillance [32].”
Deep learning in video multi-object tracking: A survey (2019, methodology): “For example, the minimum cost lifted multicut problem has reached top performance on MOT16, helped by CNN-computed affinities [148, 51], while heterogeneous association graph fusion and correlation clustering are used on the two top MOT17 methods [103, 155].”
Tracking Objects as Points (2020, methodology): “We believe that there is an exciting avenue for future work in combining local trackers (such as our work) with stronger offline long-range models (such as SORT [2], LMP [41], and other ReID-based trackers [50, 52]).”
SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation (2021, background): “Others learn tracking representations by exploiting the appearance similarity [33, 42, 35] or re-identify vanished objects [17, 36, 37].”
Track to Detect and Segment: An Online Multi-Object Tracker (2021, methodology): “MOT was dominated by the tracking-by-detection (TBD) paradigm over the past years [58, 6, 66, 52, 33, 5, 38, 48, 54].”
TransTrack: Multiple-Object Tracking with Transformer (2020, methodology): “Lifted-Multicut[34] leverage person-re identification features and human pose features.”
Online Multi-Object Tracking with Dual Matching Attention Networks (2018, methodology): “Typically, these methods model the MOT task as a global optimization problem in various forms such as network flow [58,51,14], and multi-cut [47,48,46].”