Universal Object Detection Under Unconstrained Environments

Nancy Kaur; K. M. Swaroopa; Girija Chetty

doi:10.1007/978-981-99-5088-1_34

Universal Object Detection Under Unconstrained Environments

Nancy Kaur, K. M. Swaroopa, Girija Chetty

Information Systems

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

Abstract

This paper presents a universal object detection framework for unconstrained environment settings where machines can only learn from massive unlabeled multimodal data and a few labeled data. This research aims to tackle key challenges in computer vision and expects to produce next-generation object detection techniques that can effectively detect objects of diversified categories in complex application settings. The proposed universal object detection framework is based on a novel formulation to solve anomaly detection problem leveraging multimodal heterogeneous data sources and denoising diffusion models and application to a wide set of complex application settings.

Original language	English
Title of host publication	Advances in IoT and Security with Computational Intelligence
Subtitle of host publication	Proceedings of ICAISA 2023, Volume 2
Editors	Anurag Mishra, Deepak Gupta, Girija Chetty
Place of Publication	Singapore
Publisher	Springer
Pages	395-404
Number of pages	10
Volume	2
Edition	1
ISBN (Electronic)	9789819950881
ISBN (Print)	9789819950874
DOIs	https://doi.org/10.1007/978-981-99-5088-1_34
Publication status	Published - Sept 2023
Event	International Conference on Advances in IoT, Security with AI, ICAISA 2023 - New Delhi, India Duration: 24 Mar 2023 → 25 Mar 2023

Publication series

Name	Lecture Notes in Networks and Systems
Volume	756 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	International Conference on Advances in IoT, Security with AI, ICAISA 2023
Country/Territory	India
City	New Delhi
Period	24/03/23 → 25/03/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-981-99-5088-1_34

Cite this

Kaur, N., Swaroopa, K. M., & Chetty, G. (2023). Universal Object Detection Under Unconstrained Environments. In A. Mishra, D. Gupta, & G. Chetty (Eds.), Advances in IoT and Security with Computational Intelligence : Proceedings of ICAISA 2023, Volume 2 (1 ed., Vol. 2, pp. 395-404). (Lecture Notes in Networks and Systems; Vol. 756 LNNS). Springer. https://doi.org/10.1007/978-981-99-5088-1_34

@inproceedings{98dc3bbb0c07415c81aea6a459df6b66,

title = "Universal Object Detection Under Unconstrained Environments",

abstract = "This paper presents a universal object detection framework for unconstrained environment settings where machines can only learn from massive unlabeled multimodal data and a few labeled data. This research aims to tackle key challenges in computer vision and expects to produce next-generation object detection techniques that can effectively detect objects of diversified categories in complex application settings. The proposed universal object detection framework is based on a novel formulation to solve anomaly detection problem leveraging multimodal heterogeneous data sources and denoising diffusion models and application to a wide set of complex application settings.",

keywords = "Anomaly detection, Diffusion models, Multimodal, Object detection",

author = "Nancy Kaur and Swaroopa, {K. M.} and Girija Chetty",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; International Conference on Advances in IoT, Security with AI, ICAISA 2023 ; Conference date: 24-03-2023 Through 25-03-2023",

year = "2023",

month = sep,

doi = "10.1007/978-981-99-5088-1_34",

language = "English",

isbn = "9789819950874",

volume = "2",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer",

pages = "395--404",

editor = "Anurag Mishra and Deepak Gupta and Girija Chetty",

booktitle = "Advances in IoT and Security with Computational Intelligence",

address = "Netherlands",

edition = "1",

}

Kaur, N, Swaroopa, KM & Chetty, G 2023, Universal Object Detection Under Unconstrained Environments. in A Mishra, D Gupta & G Chetty (eds), Advances in IoT and Security with Computational Intelligence : Proceedings of ICAISA 2023, Volume 2. 1 edn, vol. 2, Lecture Notes in Networks and Systems, vol. 756 LNNS, Springer, Singapore, pp. 395-404, International Conference on Advances in IoT, Security with AI, ICAISA 2023, New Delhi, India, 24/03/23. https://doi.org/10.1007/978-981-99-5088-1_34

Universal Object Detection Under Unconstrained Environments. / Kaur, Nancy; Swaroopa, K. M.; Chetty, Girija.
Advances in IoT and Security with Computational Intelligence : Proceedings of ICAISA 2023, Volume 2. ed. / Anurag Mishra; Deepak Gupta; Girija Chetty. Vol. 2 1. ed. Singapore: Springer, 2023. p. 395-404 (Lecture Notes in Networks and Systems; Vol. 756 LNNS).

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - Universal Object Detection Under Unconstrained Environments

AU - Kaur, Nancy

AU - Swaroopa, K. M.

AU - Chetty, Girija

PY - 2023/9

Y1 - 2023/9

N2 - This paper presents a universal object detection framework for unconstrained environment settings where machines can only learn from massive unlabeled multimodal data and a few labeled data. This research aims to tackle key challenges in computer vision and expects to produce next-generation object detection techniques that can effectively detect objects of diversified categories in complex application settings. The proposed universal object detection framework is based on a novel formulation to solve anomaly detection problem leveraging multimodal heterogeneous data sources and denoising diffusion models and application to a wide set of complex application settings.

AB - This paper presents a universal object detection framework for unconstrained environment settings where machines can only learn from massive unlabeled multimodal data and a few labeled data. This research aims to tackle key challenges in computer vision and expects to produce next-generation object detection techniques that can effectively detect objects of diversified categories in complex application settings. The proposed universal object detection framework is based on a novel formulation to solve anomaly detection problem leveraging multimodal heterogeneous data sources and denoising diffusion models and application to a wide set of complex application settings.

KW - Anomaly detection

KW - Diffusion models

KW - Multimodal

KW - Object detection

UR - http://www.scopus.com/inward/record.url?scp=85174617327&partnerID=8YFLogxK

UR - https://icaisa2023.com/commitee/

U2 - 10.1007/978-981-99-5088-1_34

DO - 10.1007/978-981-99-5088-1_34

M3 - Conference contribution

AN - SCOPUS:85174617327

SN - 9789819950874

VL - 2

T3 - Lecture Notes in Networks and Systems

SP - 395

EP - 404

BT - Advances in IoT and Security with Computational Intelligence

A2 - Mishra, Anurag

A2 - Gupta, Deepak

A2 - Chetty, Girija

PB - Springer

CY - Singapore

T2 - International Conference on Advances in IoT, Security with AI, ICAISA 2023

Y2 - 24 March 2023 through 25 March 2023

ER -

Universal Object Detection Under Unconstrained Environments

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this