1

Enhancing Novel Object Detection via Cooperative Foundational Models

Utilised complementary strengths of foundational models to achieve state-of-the-art performance in novel object detection.

VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs

VANE-Bench is a benchmark designed to assess Video-LMMs’ ability to detect and localize anomalies in videos, revealing their limitations in subtle anomaly detection through a visual question-answering challenge.

Mobile based Human Identification using Forehead Creases: Application and Assessment under COVID-19 Masked Face Scenarios

Developed an complete end-to-end system for using forehead creases as a biometric modality for human authentication. Code and Database have also been made public.

Is this URL Safe: Detection of Malicious URLs Using Global Vector for Word Representation

Machine Learning models were developed and trained to classify and detect malicious URLs.