Akshita Guptaअक्षिता गुप्ता
I am an ELLIS PhD student at TU Darmstadt, co-supervised
by Prof. Marcus Rohrbach and Dr. Federico Tombari at Google Zurich. I completed my MASc at the University of Guelph, where I was advised by Prof. Graham Taylor. During that time, I was also a
student researcher at the Vector Institute.
I was fortunate to spend time as a research intern at Apple under Dr. Tatiana
Likhomanenko, Microsoft under Gaurav Mittal and Mei Chen, Vector Institute under Dr. David Emerson, and as a scientist
in residence at NextAI with Prof. Graham Taylor.
Before coming to academia, I worked as a Data Scientist at Bayanat, where I
focused on projects related to detection and segmentation. Prior to that, I was a Research
Engineer at the Inception Institute of Artificial Intelligence (IIAI),
working with Dr. Sanath Narayan,
Dr. Salman Khan, and Dr. Fahad Shahbaz Khan.
Email  / 
Google Scholar
 / 
Twitter  / 
Github  / 
Resume/CV
|
|
What's New
Research Interest
I'm interested in developing models which can learn with limited data and few, zero or one training sample(s).
|
|
LoSA: Long-Short-range Adapter for Scaling End-to-End Temporal Action
Localization
Akshita Gupta*,
Akshita Gupta*,
Salman ,
Shahbaz Khan,
Cees G. M. Snoek,
Ling Shao,
WACV 2025
paper /
code
-
Description: Developed a generative feature synthesizing framework for zero-shot
learning.
-
Outcome: Improved state-of-the-art performances on CUB, FLO, SUN, and AWA by
4.6%, 7.1%, 1.7%, and 3.1% harmonic mean by enforcing semantic consistency at all stages
of zero-shot learning.
|
|
Open-Vocabulary Temporal Action
Localization using Multimodal Guidance
Akshita Gupta*,
Akshita Gupta*,
Salman ,
Shahbaz Khan,
Cees G. M. Snoek,
Ling Shao,
BMVC 2024
paper /
code
-
Description: Developed a generative feature synthesizing framework for zero-shot
learning.
-
Outcome: Improved state-of-the-art performances on CUB, FLO, SUN, and AWA by
4.6%, 7.1%, 1.7%, and 3.1% harmonic mean by enforcing semantic consistency at all stages
of zero-shot learning.
|
|
Generative Multi-Label Zero-Shot Learning
Akshita Gupta*,
Akshita Gupta*,
Salman ,
Shahbaz Khan,
Cees G. M. Snoek,
Ling Shao,
TPAMI 2023
paper /
code
-
Description: Developed a generative feature synthesizing framework for zero-shot
learning.
-
Outcome: Improved state-of-the-art performances on CUB, FLO, SUN, and AWA by
4.6%, 7.1%, 1.7%, and 3.1% harmonic mean by enforcing semantic consistency at all stages
of zero-shot learning.
|
|
OW-DETR: Open-world Detection Transformer
Akshita Gupta*,
Sanath Narayan*,
Joseph KJ,
Salman Khan,
Fahad Shahbaz Khan,
Mubarak Shah
CVPR 2022
paper /
code
-
Description: Developed multi-scale context aware detection framework with
attention-driven psuedo-labelling.
-
Outcome: Improved state-of-the-art performances on MS-COCO dataset with absolute
gains ranging from 1.8% to 3.3% in terms of unknown recall.
|
|
Latent Embedding Feedback and Discriminative Features for Zero-Shot
Classification
Sanath Narayan*,
Akshita Gupta*,
Salman Khan,
Fahad Shahbaz Khan,
Cees G. M. Snoek,
Ling Shao,
ECCV 2020
paper /
code
-
Description: Developed a generative feature synthesizing framework for
zero-shot learning.
-
Outcome: Improved state-of-the-art performances on CUB, FLO, SUN, and AWA by
4.6%, 7.1%, 1.7%, and 3.1% harmonic mean by enforcing semantic consistency at all
stages of zero-shot learning.
|
I borrowed this website layout from here!
|
|