@inproceedings{shanmugavadivel-etal-2025-innovationengineers,
    title = "{I}nnovation{E}ngineers@{D}ravidian{L}ang{T}ech 2025: Enhanced {CNN} Models for Detecting Misogyny in {T}amil Memes Using Image and Text Classification",
    author = "Shanmugavadivel, Kogilavani  and
      Subramanian, Malliga  and
      M, Pooja Sree  and
      V, Palanimurugan  and
      K, Roshini Priya",
    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-1.27/",
    pages = "162--166",
    ISBN = "979-8-89176-228-2",
    abstract = "The rise of misogynistic memes on social media posed challenges to civil discourse. This paper aimed to detect misogyny in Dravidian language memes using a multimodal deep learning approach. We integrated Bidirectional Encoder Representations from Transformers (BERT), Long Short-Term Memory (LSTM), EfficientNet, and a Vision Language Model (VLM) to analyze textual and visual informa tion. EfficientNet extracted image features, LSTM captured sequential text patterns, and BERT learned language-specific embeddings. Among these, VLM achieved the highest accuracy of 85.0{\%} and an F1-score of 70.8, effectively capturing visual-textual relationships. Validated on a curated dataset, our method outperformed baselines in precision, recall, and F1-score. Our approach ranked 12th out of 118 participants for the Tamil language, highlighting its competitive performance. This research emphasizes the importance of multimodal models in detecting harmful content. Future work can explore improved feature fusion techniques to enhance classification accuracy."
}