4 citations · 4 across the 7 of their papers we have counts for
7 papers · 1 filter
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…
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…