June 6, 2024, 4:50 a.m. | Jingbiao Mei, Jinghong Chen, Weizhe Lin, Bill Byrne, Marcus Tomalin

cs.CV updates on arXiv.org arxiv.org

arXiv:2311.08110v2 Announce Type: replace-cross
Abstract: Hateful memes have emerged as a significant concern on the Internet. Detecting hateful memes requires the system to jointly understand the visual and textual modalities. Our investigation reveals that the embedding space of existing CLIP-based systems lacks sensitivity to subtle differences in memes that are vital for correct hatefulness classification. We propose constructing a hatefulness-aware embedding space through retrieval-guided contrastive training. Our approach achieves state-of-the-art performance on the HatefulMemes dataset with an AUROC of 87.0, …

abstract arxiv clip cs.cl cs.cv detection differences embedding improving internet investigation meme memes replace retrieval sensitivity space systems textual through type visual vital

Senior Data Engineer

@ Displate | Warsaw

Professor/Associate Professor of Health Informatics [LKCMedicine]

@ Nanyang Technological University | NTU Novena Campus, Singapore

Research Fellow (Computer Science (and Engineering)/Electronic Engineering/Applied Mathematics/Perception Sciences)

@ Nanyang Technological University | NTU Main Campus, Singapore

Java Developer - Assistant Manager

@ State Street | Bengaluru, India

Senior Java/Python Developer

@ General Motors | Austin IT Innovation Center North - Austin IT Innovation Center North

Research Associate (Computer Engineering/Computer Science/Electronics Engineering)

@ Nanyang Technological University | NTU Main Campus, Singapore