Predict Unmatching Compositions for Compositional Zero-Shot Learning

Compositional Zero-Shot Learning (CZSL) poses the challenge of predicting unseen attribute-object combinations in images. In this study, we focus on the open-world CZSL task, which presents a more realistic and comprehensive challenge by expanding the search space to include unmatching pairs. Throug...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Soohyeong Kim, Yong Suk Choi
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2025-01-01
Serija:	IEEE Access
Teme:	Compositional zero-shot learning representation learning image recognition zero-shot learning
Online dostop:	https://ieeexplore.ieee.org/document/11115043/
Oznake:	Označite Brez oznak, prvi označite!