3 papers
cs.CV2026
ProCap: Prominence-guided Object Rectification for Faithful and Comprehensive Video Captioning
Debjyoti Das Adhikary, Aritra Hazra, Partha Pratim Chakrabarti
Improving video captioning quality typically demands retraining large vision-language models, an expensive and often impractical requirement. Existing training-free alternatives in…
cs.CV2025
ReFrame: Rectification Framework for Image Explaining Architectures
Debjyoti Das Adhikary, Aritra Hazra, Partha Pratim Chakrabarti
Image explanation has been one of the key research interests in the Deep Learning field. Throughout the years, several approaches have been adopted to explain an input image fed by…
cs.LG2024
Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles
Shubhi Shukla, Subhadeep Dalui, Manaar Alam +4
Adversarial attacks rely on transferability, where an adversarial example (AE) crafted on a surrogate classifier tends to mislead a target classifier. Recent ensemble methods demon…