activity
20182022
most citedLooking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attention

24 citations · 48 across the 16 of their papers we have counts for

collaborators

19 papers

cs.CL20221 cited

Time-Aware Datasets are Adaptive Knowledgebases for the New Normal

Abhijit Suprem, Sanjyot Vaidya, Joao Eduardo Ferreira +1

Recent advances in text classification and knowledge capture in language models have relied on availability of large-scale text datasets. However, language models are trained on st…

cs.CV2022

Targeted Attention for Generalized- and Zero-Shot Learning

Abhijit Suprem

The Zero-Shot Learning (ZSL) task attempts to learn concepts without any labeled data. Unlike traditional classification/detection tasks, the evaluation environment is provided uns…

cs.CV2022

ATEAM: Knowledge Integration from Federated Datasets for Vehicle Feature Extraction using Annotation Team of Experts

Abhijit Suprem, Purva Singh, Suma Cherkadi +3

The vehicle recognition area, including vehicle make-model recognition (VMMR), re-id, tracking, and parts-detection, has made significant progress in recent years, driven by severa…

cs.LG2022

EdnaML: A Declarative API and Framework for Reproducible Deep Learning

Abhijit Suprem, Sanjyot Vaidya, Avinash Venugopal +2

Machine Learning has become the bedrock of recent advances in text, image, video, and audio processing and generation. Most production systems deal with several models during deplo…

cs.LG20222 cited

Evaluating Generalizability of Fine-Tuned Models for Fake News Detection

Abhijit Suprem, Calton Pu

The Covid-19 pandemic has caused a dramatic and parallel rise in dangerous misinformation, denoted an `infodemic' by the CDC and WHO. Misinformation tied to the Covid-19 infodemic…

cs.CV20221 cited

Constructive Interpretability with CoLabel: Corroborative Integration, Complementary Features, and Collaborative Learning

Abhijit Suprem, Sanjyot Vaidya, Suma Cherkadi +3

Machine learning models with explainable predictions are increasingly sought after, especially for real-world, mission-critical applications that require bias detection and risk mi…