17 citations · 41 across the 14 of their papers we have counts for
15 papers
Towards Automated Machine Learning Research
Shervin Ardeshir
This paper explores a top-down approach to automating incremental advances in machine learning research through component-level innovation, facilitated by Large Language Models (LL…
Training-Free Uncertainty Estimation for Embedding Models
Young-Jin Park, Hao Wang, Addison Kristanto Julistiono +2
Embedding models, often obtained via self-supervised learning, extract general-purpose representations from data. Quantifying the reliability of these representations is crucial, a…
LLM2Loss: Leveraging Language Models for Explainable Model Diagnostics
Shervin Ardeshir
Trained on a vast amount of data, Large Language models (LLMs) have achieved unprecedented success and generalization in modeling fairly complex textual inputs in the abstract spac…
Improving Identity-Robustness for Face Models
Qi Qi, Shervin Ardeshir
Despite the success of deep-learning models in many tasks, there have been concerns about such models learning shortcuts, and their lack of robustness to irrelevant confounders. Wh…
Fairness via Adversarial Attribute Neighbourhood Robust Learning
Qi Qi, Shervin Ardeshir, Yi Xu +1
Improving fairness between privileged and less-privileged sensitive attribute groups (e.g, {race, gender}) has attracted lots of attention. To enhance the model performs uniformly…
Uncertainty in Contrastive Learning: On the Predictability of Downstream Performance
Shervin Ardeshir, Navid Azizan
The superior performance of some of today's state-of-the-art deep learning models is to some extent owed to extensive (self-)supervised contrastive pretraining on large-scale datas…
On Negative Sampling for Audio-Visual Contrastive Learning from Movies
Mahdi M. Kalayeh, Shervin Ardeshir, Lingyi Liu +2
The abundance and ease of utilizing sound, along with the fact that auditory clues reveal a plethora of information about what happens in a scene, make the audio-visual space an in…
Character-focused Video Thumbnail Retrieval
Shervin Ardeshir, Nagendra Kamath, Hossein Taghavi
We explore retrieving character-focused video frames as candidates for being video thumbnails. To evaluate each frame of the video based on the character(s) present in it, characte…
Estimating Structural Disparities for Face Models
Shervin Ardeshir, Cristina Segalin, Nathan Kallus
In machine learning, disparity metrics are often defined by measuring the difference in the performance or outcome of a model, across different sub-populations (groups) of datapoin…
On Attention Modules for Audio-Visual Synchronization
Naji Khosravan, Shervin Ardeshir, Rohit Puri
With the development of media and networking technologies, multimedia applications ranging from feature presentation in a cinema setting to video on demand to interactive video con…
From Third Person to First Person: Dataset and Baselines for Synthesis and Retrieval
Mohamed Elfeki, Krishna Regmi, Shervin Ardeshir +1
First-person (egocentric) and third person (exocentric) videos are drastically different in nature. The relationship between these two views have been studied in recent years, howe…
EgoReID: Cross-view Self-Identification and Human Re-identification in Egocentric and Surveillance Videos
Shervin Ardeshir, Sandesh Sharma, Ali Broji
Human identification remains to be one of the challenging tasks in computer vision community due to drastic changes in visual features across different viewpoints, lighting conditi…
EgoTransfer: Transferring Motion Across Egocentric and Exocentric Domains using Deep Neural Networks
Shervin Ardeshir, Krishna Regmi, Ali Borji
Mirror neurons have been observed in the primary motor cortex of primate species, in particular in humans and monkeys. A mirror neuron fires when a person performs a certain action…
Egocentric Meets Top-view
Shervin Ardeshir, Ali Borji
Thanks to the availability and increasing popularity of Egocentric cameras such as GoPro cameras, glasses, and etc. we have been provided with a plethora of videos captured from th…
Ego2Top: Matching Viewers in Egocentric and Top-view Videos
Shervin Ardeshir, Ali Borji
Egocentric cameras are becoming increasingly popular and provide us with large amounts of videos, captured from the first person perspective. At the same time, surveillance cameras…