← Back to home

Research output

Publications

Work on multimodal understanding, misinformation analysis, adversarial learning and biomedical computer vision.

01

What Improves Multimodal Misinformation Detection? Answers from a Large-Scale Empirical Study

Akshit Sharma, Prashant W. Patil

Accepted to the 10th Widening NLP Workshop (WiNLP) at EMNLP 2026

02

Small Cues, Big Consequences: Learning Pivotal Cues for Multimodal Meme Classification

Akshit Sharma, Prashant W. Patil

Accepted at The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026, Findings)

03

What Makes Multimodal Meme Classification Reliable? A Large-Scale Controlled Study of Fusion, Encoders, and Modality Reliance

Akshit Sharma, Prashant W. Patil

Accepted at IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026

04

MemeTAG: Keyword-Driven Meme Classification through Tag Embedding Reconstruction

Akshit Sharma, Prashant W. Patil

Accepted at IEEE/CVF Winter Conference on Applications of Computer Vision 2026 (WACV 26)

05

Robust Fake News Detection via Adversarial Contrastive Learning over Vision–Language Representations

Akshit Sharma, Manas Kamal Bhuyan

Accepted at 10th International Conference on Computer Vision and Image Processing 2025 (CVIP 25)

06

HDL-SAM: A Hybrid Deep Learning Framework for High-Resolution Imaging in Scanning Acoustic Microscopy

Akshit Sharma, Ayush Somani, Pragyan Banerjee, Frank Melandsø, Anowarul Habib

Accepted at IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024

For preprints, supplementary material, or collaboration enquiries, please contact me.