no code implementations • 24 May 2024 • Yiran Luo, Joshua Feinglass, Tejas Gokhale, Kuan-Cheng Lee, Chitta Baral, Yezhou Yang
We first introduce two new quantitative measures ICV and IDD to describe domain shifts in terms of consistency of classes within one domain and similarity between two stylistic domains.
no code implementations • 12 Apr 2024 • Joshua Feinglass, Jayaraman J. Thiagarajan, Rushil Anirudh, T. S. Jayram, Yezhou Yang
Current approaches in Generalized Zero-Shot Learning (GZSL) are built upon base models which consider only a single class attribute vector representation over the entire image.
1 code implementation • 1 Sep 2023 • Joshua Feinglass, Yezhou Yang
Object proposal generation serves as a standard pre-processing step in Vision-Language (VL) tasks (image captioning, visual question answering, etc.).
1 code implementation • ACL 2021 • Joshua Feinglass, Yezhou Yang
The open-ended nature of visual captioning makes it a challenging area for evaluation.