Temporal Image Caption Retrieval Competition -- Description and Results
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913538498363392 |
|---|---|
| author | Pokrywka, Jakub Wierzchoń, Piotr Weryszko, Kornel Jassem, Krzysztof |
| author_facet | Pokrywka, Jakub Wierzchoń, Piotr Weryszko, Kornel Jassem, Krzysztof |
| contents | Multimodal models, which combine visual and textual information, have recently gained significant recognition. This paper addresses the multimodal challenge of Text-Image retrieval and introduces a novel task that extends the modalities to include temporal data. The Temporal Image Caption Retrieval Competition (TICRC) presented in this paper is based on the Chronicling America and Challenging America projects, which offer access to an extensive collection of digitized historic American newspapers spanning 274 years. In addition to the competition results, we provide an analysis of the delivered dataset and the process of its creation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_06314 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Temporal Image Caption Retrieval Competition -- Description and Results Pokrywka, Jakub Wierzchoń, Piotr Weryszko, Kornel Jassem, Krzysztof Computer Vision and Pattern Recognition Computation and Language Multimodal models, which combine visual and textual information, have recently gained significant recognition. This paper addresses the multimodal challenge of Text-Image retrieval and introduces a novel task that extends the modalities to include temporal data. The Temporal Image Caption Retrieval Competition (TICRC) presented in this paper is based on the Chronicling America and Challenging America projects, which offer access to an extensive collection of digitized historic American newspapers spanning 274 years. In addition to the competition results, we provide an analysis of the delivered dataset and the process of its creation. |
| title | Temporal Image Caption Retrieval Competition -- Description and Results |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2410.06314 |