OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
Darshan Singh
Predoctoral Researcher, Foundational Research, Google DeepMind
Joined
April 2022
Names
Darshan Singh
(Preferred)
,
Darshan Singh S
Emails
****@gmail.com
(Confirmed)
,
****@research.iiit.ac.in
(Confirmed)
,
****@fastcode.ai
(Confirmed)
,
****@google.com
(Confirmed)
Personal Links
Google Scholar
DBLP
LinkedIn
Career & Education History
Predoctoral Researcher
Foundational Research,
Google DeepMind
(google.com)
2024
–
Present
ML Engineer
FastCode AI
(fastcode.ai)
2024
–
2024
MS student
Computer Science,
IIIT Hyderabad
(research.iiit.ac.in)
2022
–
2024
Research Fellow
IIIT Hyderabad
(iiit.ac.in)
2021
–
2022
Advisors, Relations & Conflicts
Coauthor
Vihari Piratla
2025
–
Present
Coauthor
Trevor Cohn
2025
–
Present
Coauthor
Purvam Jain
2025
–
Present
Coauthor
Partha Talukdar
2025
–
Present
Coauthor
Zeeshan Khan
2023
–
Present
Coauthor
Makarand Tapaswi
2021
–
Present
Coauthor
Vineet Gandhi
2024
–
2025
Coauthor
Darshana Saravanan
2024
–
2025
Coauthor
Varun Gupta
2024
–
2025
Coauthor
Manu Gaur
2024
–
2025
Coauthor
C V Jawahar
2021
–
2024
Coauthor
Anchit Gupta
2021
–
2024
Expertise
deep learning
,
computer vision
,
vision and language
,
video understanding
,
multimodal representation learning
2021
–
Present
Publications
VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment
Varun Gupta
,
Darshana Saravanan
,
Darshan Singh
,
Zeeshan Khan
,
Vineet Gandhi
,
Makarand Tapaswi
CVPR 2025
Readers:
Everyone
Rethinking Cross-Lingual Gaps From A Statistical Viewpoint
Vihari Piratla
,
Purvam Jain
,
Darshan Singh
,
Trevor Cohn
,
Partha Talukdar
Submitted to ICLR 2026
Readers:
Everyone
No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning
Manu Gaur
,
Darshan Singh S
,
Makarand Tapaswi
Accepted by TMLR
Readers:
Everyone
Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation
Manu Gaur
,
Darshan Singh S
,
Makarand Tapaswi
CoRR 2024
Readers:
Everyone
No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning
Manu Gaur
,
Darshan Singh S
,
Makarand Tapaswi
CoRR 2024
Readers:
Everyone
VELOCITI: Can Video-Language Models Bind Semantic Concepts through Time?
Darshana Saravanan
,
Darshan Singh S
,
Varun Gupta
,
Zeeshan Khan
,
Vineet Gandhi
,
Makarand Tapaswi
CoRR 2024
Readers:
Everyone
FiGCLIP: Fine-Grained CLIP Adaptation via Densely Annotated Videos
Darshan Singh S
,
Zeeshan Khan
,
Makarand Tapaswi
Published: 01 Jan 2024, Last Modified: 21 Mar 2024
CoRR 2024
Readers:
Everyone
Unsupervised Audio-Visual Lecture Segmentation
Darshan Singh S
,
Anchit Gupta
,
C. V. Jawahar
,
Makarand Tapaswi
Published: 01 Jan 2023, Last Modified: 21 Mar 2024
WACV 2023
Readers:
Everyone
Unsupervised Audio-Visual Lecture Segmentation
Darshan Singh S
,
Anchit Gupta
,
C. V. Jawahar
,
Makarand Tapaswi
Published: 01 Jan 2022, Last Modified: 21 Mar 2024
CoRR 2022
Readers:
Everyone
Co-Authors
Anchit Gupta
C. V. Jawahar
Darshana Saravanan
Makarand Tapaswi
Manu Gaur
Partha Talukdar
Purvam Jain
Trevor Cohn
Varun Gupta
Vihari Piratla
Vineet Gandhi
Zeeshan Khan