@inproceedings{bilen-etal-2026-visaffect,
    title = "{V}is{A}ffect at {MWE}-2026 {A}d{MIR}e 2: {IMMCAN} Idiom Multimodal Cross-Attention Network",
    author = "Bilen, Bar{\i}{\c{s}}  and
      Azmoudeh, Ali  and
      Ekenel, Haz{\i}m Kemal  and
      Kose, Hatice",
    editor = {Ojha, Atul Kr.  and
      Mititelu, Verginica Barbu  and
      Constant, Mathieu  and
      Stoyanova, Ivelina  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Rademaker, Alexandre},
    booktitle = "Proceedings of the 22nd Workshop on Multiword Expressions ({MWE} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Marocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.mwe-1.19/",
    pages = "149--153",
    ISBN = "979-8-89176-363-0",
    abstract = "We address AdMIRe 2.0, a static image ranking task where a sentence containing a potentially idiomatic expression is paired with five image{--}caption candidates, and the goal is to rank the candidates by semantic compatibility with the intended idiomatic or literal meaning. We propose IMMCAN, which keeps XLM-R and Jina-CLIP-v2 frozen and learns a lightweight two-stage cross-attention fusion, caption{--}image grounding followed by idiom-to-multimodal conditioning, to predict a compatibility score per candidate. We also evaluate caption-only augmentation via back-translation and synonym substitution, and compare regression and rank-class formulations. On AdMIRe 1.0, text-only achieves higher test top-image accuracy than VLM-grounded modeling. In contrast, on AdMIRe 2.0 zero-shot, adding visual patch grounding improves both accuracy and NDCG indicating better cross-lingual ranking transfer."
}