Manoj Acharya

Manoj Acharya

Machine Learning Researcher at SRI International

Email: manoj.acharya@sri.com, ma7583@rit.edu
CV
Twitter
Github
Linkedin

Research Interests

I received my PhD from the Rochester Institute of Technology in 2022 where I worked with my adviser Dr. Christopher Kanan . I enjoy doing research on Deep Learning especially on topics such as multimodal learning with language and vision(V&L), Object detection, Large Language Models, and Continual Learning. Ideally, I would want to develop multimodal systems that can learn from large uncurated data and are robust enough to operate in an Open-World via continual knowledge exploration and adaptation just like humans.

Timeline Events

June 2023: I joined SRI International as an Advanced Computer Scientist in the Neuro-symbolic Computing and Intelligence (NuSCI) research group.
July 2022: I joined Amazon as an Applied Scientist in the Search team to help Amazon build foundation models.
June 2022: Defended my dissertaion titled "Towards Multimodal Open-World Learning in Deep Neural Networks". Online link
April 2022:Our paper "Detecting out-of-context objects using graph contextual reasoning network" is accepted to IJCAI-ECAI 2022 !!
Oct 2021: Secured second position in the SODA10M Continual Object Detection Challenge at ICCV 2021 !!
Sep 2021: Spent three months working as a Summer Research Intern at SRI International.
April 2021: I successfully defended my dissertation proposal and advanced to candidacy.
Jul 2020: Our paper "RODEO: Replay for Online Object Detection" is accepted to BMVC 2020!!
Jul 2020: Our paper "REMIND Your Neural Network to Prevent Catastrophic Forgetting" is accepted to ECCV 2020! (27.1% acceptance rate)
Oct 2019: Our work got featured in RIT news!!
Sep 2019: We won the Facebook Eye Tracking Semantic Segmentation Challenge!!
Feb 2019: Our short paper is accepted to NAACL 2019!!
Nov 2018: TallyQA won the best poster award in the annual RIT Graduate Showcase!!
Nov 2018: Our paper is accepted to AAAI 2019. (acceptance rate ~16%)
July 2017: Started working at Klab under Dr. Christopher Kanan.
July 2017: Passed the Imaging science PhD qualifying exam.

Publications

For a complete and the most current list please refer to my Google Scholar profile.
Detecting out-of-context objects using graph contextual reasoning network.
Manoj Acharya, Anirban Roy, Kaushik Koneripalli, Susmit Jha, Christopher Kanan, Ajay Divakaran
IJCAI-ECAI 2022
abstract / bibtex / code video

2nd Place Solution for SODA10M Challenge 2021 -- Continual Detection Track.
Manoj Acharya, and Christopher Kanan
ICCVW 2021
abstract / bibtex /

RODEO: Replay for Online Object Detection.
Manoj Acharya, Tyler L. Hayes, and Christopher Kanan
BMVC 2020
abstract / bibtex / code / video

REMIND Your Neural Network to Prevent Catastrophic Forgetting.
Tyler L. Hayes*, Kushal Kafle*, Robik Shrestha*, Manoj Acharya, and Christopher Kanan
ECCV 2020
abstract / bibtex / code

RITnet: Real-time Semantic Segmentation of the Eye for Gaze Tracking.
Aayush Chaudhary*, Rakshit Kothari*,Manoj Acharya*, Shusil Dangi, Nitinraj Nair, Reynold Bailey, Christopher Kanan ,Gabriel Diaz, Jeff Pelz
ICCVW 2019 (Competition Winner)
abstract / bibtex / code

VQD: Visual Query Detection in Natural Scenes.
Manoj Acharya , Karan Jariwala, Christopher Kanan
NAACL 2019
abstract / bibtex / website

TallyQA: Answering Complex Counting Questions.
Manoj Acharya , Kushal Kafle, Christopher Kanan
AAAI 2019 (Spotlight Presentation)
abstract / bibtex / website / code