A Hybrid Approach for Visual Recognition of Object States
Abstract
The basic objective of my research work is to address the challenging problem of recognizing object states in a visual context by integrating data-driven and symbolic approaches. In particular, I focus on the Zero-shot variation of this task. The contributions made so far include the development of novel methods that exhibit state-of-the-art (SOTA) performance, the creation of a new object states dataset, the formulation of novel problems, the successful integration of low-level and high-level approaches, and comprehensive analyses that highlight the specific challenges posed by the problem.
Cite
Text
Gouidis. "A Hybrid Approach for Visual Recognition of Object States." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I28.35207Markdown
[Gouidis. "A Hybrid Approach for Visual Recognition of Object States." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/gouidis2025aaai-hybrid/) doi:10.1609/AAAI.V39I28.35207BibTeX
@inproceedings{gouidis2025aaai-hybrid,
title = {{A Hybrid Approach for Visual Recognition of Object States}},
author = {Gouidis, Filippos},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {29259-29260},
doi = {10.1609/AAAI.V39I28.35207},
url = {https://mlanthology.org/aaai/2025/gouidis2025aaai-hybrid/}
}