@inproceedings{rao-etal-2025-code,
    title = "{C}ode{\_}{C}onquerors@{D}ravidian{L}ang{T}ech 2025: Multimodal Misogyny Detection in {D}ravidian Languages Using Vision Transformer and {BERT}",
    author = "Rao, Pathange Omkareshwara  and
      V, Harish Vijay  and
      Srichandra, Ippatapu Venkata  and
      Mohan, Neethu  and
      S, Sachin Kumar",
    editor = "Chakravarthi, Bharathi Raja  and
      Priyadharshini, Ruba  and
      Madasamy, Anand Kumar  and
      Thavareesan, Sajeetha  and
      Sherly, Elizabeth  and
      Rajiakodi, Saranya  and
      Palani, Balasubramanian  and
      Subramanian, Malliga  and
      Cn, Subalalitha  and
      Chinnappa, Dhivya",
    booktitle = "Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages",
    month = may,
    year = "2025",
    address = "Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.dravidianlangtech-1.49/",
    pages = "283--287",
    ISBN = "979-8-89176-228-2",
    abstract = "This research focuses on misogyny detection in Dravidian languages using multimodal techniques. It leverages advanced machine learning models, including Vision Transformers (ViT) for image analysis and BERT-based transformers for text processing. The study highlights the challenges of working with regional datasets and addresses these with innovative preprocessing and model training strategies. The evaluation reveals significant improvements in detection accuracy, showcasing the potential of multimodal approaches in combating online abuse in underrepresented languages."
}