Concept Retrieval -- What and How?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917079955800064 |
|---|---|
| author | Nizan, Ori Shrout, Oren Tal, Ayellet |
| author_facet | Nizan, Ori Shrout, Oren Tal, Ayellet |
| contents | A concept may reflect either a concrete or abstract idea. Given an input image, this paper seeks to retrieve other images that share its central concepts, capturing aspects of the underlying narrative. This goes beyond conventional retrieval or clustering methods, which emphasize visual or semantic similarity. We formally define the problem, outline key requirements, and introduce appropriate evaluation metrics. We propose a novel approach grounded in two key observations: (1) While each neighbor in the embedding space typically shares at least one concept with the query, not all neighbors necessarily share the same concept with one another. (2) Modeling this neighborhood with a bimodal Gaussian distribution uncovers meaningful structure that facilitates concept identification. Qualitative, quantitative, and human evaluations confirm the effectiveness of our approach. See the package on PyPI: https://pypi.org/project/coret/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07058 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Concept Retrieval -- What and How? Nizan, Ori Shrout, Oren Tal, Ayellet Computer Vision and Pattern Recognition A concept may reflect either a concrete or abstract idea. Given an input image, this paper seeks to retrieve other images that share its central concepts, capturing aspects of the underlying narrative. This goes beyond conventional retrieval or clustering methods, which emphasize visual or semantic similarity. We formally define the problem, outline key requirements, and introduce appropriate evaluation metrics. We propose a novel approach grounded in two key observations: (1) While each neighbor in the embedding space typically shares at least one concept with the query, not all neighbors necessarily share the same concept with one another. (2) Modeling this neighborhood with a bimodal Gaussian distribution uncovers meaningful structure that facilitates concept identification. Qualitative, quantitative, and human evaluations confirm the effectiveness of our approach. See the package on PyPI: https://pypi.org/project/coret/ |
| title | Concept Retrieval -- What and How? |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.07058 |