Universal Object Detection Under Unconstrained Environments

Nancy Kaur, K. M. Swaroopa, Girija Chetty

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review


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 languageEnglish
Title of host publicationAdvances in IoT and Security with Computational Intelligence
Subtitle of host publicationProceedings of ICAISA 2023, Volume 2
EditorsAnurag Mishra, Deepak Gupta, Girija Chetty
Place of PublicationSingapore
Number of pages10
ISBN (Electronic)9789819950881
ISBN (Print)9789819950874
Publication statusPublished - Sept 2023
EventInternational Conference on Advances in IoT, Security with AI, ICAISA 2023 - New Delhi, India
Duration: 24 Mar 202325 Mar 2023

Publication series

NameLecture Notes in Networks and Systems
Volume756 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389


ConferenceInternational Conference on Advances in IoT, Security with AI, ICAISA 2023
CityNew Delhi


Dive into the research topics of 'Universal Object Detection Under Unconstrained Environments'. Together they form a unique fingerprint.

Cite this