@inproceedings{tran-etal-2024-z,
title = "{Z}-{GMOT}: Zero-shot Generic Multiple Object Tracking",
author = "Tran, Kim and
Le Dinh, Anh Duy and
Nguyen, Tien-Phat and
Phan, Thinh and
Nguyen, Pha and
Luu, Khoa and
Adjeroh, Donald and
Doretto, Gianfranco and
Le, Ngan",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.220",
doi = "10.18653/v1/2024.findings-naacl.220",
pages = "3468--3479",
abstract = "Despite recent significant progress, Multi-Object Tracking (MOT) faces limitations such as reliance on prior knowledge and predefined categories and struggles with unseen objects. To address these issues, Generic Multiple Object Tracking (GMOT) has emerged as an alternative approach, requiring less prior information. However, current GMOT methods often rely on initial bounding boxes and struggle to handle variations in factors such as viewpoint, lighting, occlusion, and scale, among others. Our contributions commence with the introduction of the Referring GMOT dataset a collection of videos, each accompanied by detailed textual descriptions of their attributes. Subsequently, we propose Z-GMOT, a cutting-edge tracking solution capable of tracking objects from never-seen categories without the need of initial bounding boxes or predefined categories. Within our Z-GMOT framework, we introduce two novel components: (i) iGLIP, an improved Grounded language-image pretraining, for accurately detecting unseen objects with specific characteristics. (ii) MA-SORT, a novel object association approach that adeptly integrates motion and appearance-based matching strategies to tackle the complex task of tracking objects with high similarity. Our contributions are benchmarked through extensive experiments conducted on the Referring GMOT dataset for GMOT task. Additionally, to assess the generalizability of the proposed Z-GMOT, we conduct ablation studies on the DanceTrack and MOT20 datasets for the MOT task. Our dataset, code, and models are released at: https://fsoft-aic.github.io/Z-GMOT",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-etal-2024-z">
<titleInfo>
<title>Z-GMOT: Zero-shot Generic Multiple Object Tracking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kim</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="given">Duy</namePart>
<namePart type="family">Le Dinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tien-Phat</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thinh</namePart>
<namePart type="family">Phan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pha</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khoa</namePart>
<namePart type="family">Luu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donald</namePart>
<namePart type="family">Adjeroh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gianfranco</namePart>
<namePart type="family">Doretto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngan</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite recent significant progress, Multi-Object Tracking (MOT) faces limitations such as reliance on prior knowledge and predefined categories and struggles with unseen objects. To address these issues, Generic Multiple Object Tracking (GMOT) has emerged as an alternative approach, requiring less prior information. However, current GMOT methods often rely on initial bounding boxes and struggle to handle variations in factors such as viewpoint, lighting, occlusion, and scale, among others. Our contributions commence with the introduction of the Referring GMOT dataset a collection of videos, each accompanied by detailed textual descriptions of their attributes. Subsequently, we propose Z-GMOT, a cutting-edge tracking solution capable of tracking objects from never-seen categories without the need of initial bounding boxes or predefined categories. Within our Z-GMOT framework, we introduce two novel components: (i) iGLIP, an improved Grounded language-image pretraining, for accurately detecting unseen objects with specific characteristics. (ii) MA-SORT, a novel object association approach that adeptly integrates motion and appearance-based matching strategies to tackle the complex task of tracking objects with high similarity. Our contributions are benchmarked through extensive experiments conducted on the Referring GMOT dataset for GMOT task. Additionally, to assess the generalizability of the proposed Z-GMOT, we conduct ablation studies on the DanceTrack and MOT20 datasets for the MOT task. Our dataset, code, and models are released at: https://fsoft-aic.github.io/Z-GMOT</abstract>
<identifier type="citekey">tran-etal-2024-z</identifier>
<identifier type="doi">10.18653/v1/2024.findings-naacl.220</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.220</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>3468</start>
<end>3479</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Z-GMOT: Zero-shot Generic Multiple Object Tracking
%A Tran, Kim
%A Le Dinh, Anh Duy
%A Nguyen, Tien-Phat
%A Phan, Thinh
%A Nguyen, Pha
%A Luu, Khoa
%A Adjeroh, Donald
%A Doretto, Gianfranco
%A Le, Ngan
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F tran-etal-2024-z
%X Despite recent significant progress, Multi-Object Tracking (MOT) faces limitations such as reliance on prior knowledge and predefined categories and struggles with unseen objects. To address these issues, Generic Multiple Object Tracking (GMOT) has emerged as an alternative approach, requiring less prior information. However, current GMOT methods often rely on initial bounding boxes and struggle to handle variations in factors such as viewpoint, lighting, occlusion, and scale, among others. Our contributions commence with the introduction of the Referring GMOT dataset a collection of videos, each accompanied by detailed textual descriptions of their attributes. Subsequently, we propose Z-GMOT, a cutting-edge tracking solution capable of tracking objects from never-seen categories without the need of initial bounding boxes or predefined categories. Within our Z-GMOT framework, we introduce two novel components: (i) iGLIP, an improved Grounded language-image pretraining, for accurately detecting unseen objects with specific characteristics. (ii) MA-SORT, a novel object association approach that adeptly integrates motion and appearance-based matching strategies to tackle the complex task of tracking objects with high similarity. Our contributions are benchmarked through extensive experiments conducted on the Referring GMOT dataset for GMOT task. Additionally, to assess the generalizability of the proposed Z-GMOT, we conduct ablation studies on the DanceTrack and MOT20 datasets for the MOT task. Our dataset, code, and models are released at: https://fsoft-aic.github.io/Z-GMOT
%R 10.18653/v1/2024.findings-naacl.220
%U https://aclanthology.org/2024.findings-naacl.220
%U https://doi.org/10.18653/v1/2024.findings-naacl.220
%P 3468-3479
Markdown (Informal)
[Z-GMOT: Zero-shot Generic Multiple Object Tracking](https://aclanthology.org/2024.findings-naacl.220) (Tran et al., Findings 2024)
ACL
- Kim Tran, Anh Duy Le Dinh, Tien-Phat Nguyen, Thinh Phan, Pha Nguyen, Khoa Luu, Donald Adjeroh, Gianfranco Doretto, and Ngan Le. 2024. Z-GMOT: Zero-shot Generic Multiple Object Tracking. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 3468–3479, Mexico City, Mexico. Association for Computational Linguistics.