BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shinoda, Risa, Shiohara, Kaede, Inoue, Nakamasa, Saito, Kuniaki, Santo, Hiroaki, Okura, Fumio
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917360965779456
author Shinoda, Risa
Shiohara, Kaede
Inoue, Nakamasa
Saito, Kuniaki
Santo, Hiroaki
Okura, Fumio
author_facet Shinoda, Risa
Shiohara, Kaede
Inoue, Nakamasa
Saito, Kuniaki
Santo, Hiroaki
Okura, Fumio
contents Understanding animal species from multimodal data poses an emerging challenge at the intersection of computer vision and ecology. While recent biological models, such as BioCLIP, have demonstrated strong alignment between images and textual taxonomic information for species identification, the integration of the audio modality remains an open problem. We propose BioVITA, a novel visual-textual-acoustic alignment framework for biological applications. BioVITA involves (i) a training dataset, (ii) a representation model, and (iii) a retrieval benchmark. First, we construct a large-scale training dataset comprising 1.3 million audio clips and 2.3 million images, covering 14,133 species annotated with 34 ecological trait labels. Second, building upon BioCLIP2, we introduce a two-stage training framework to effectively align audio representations with visual and textual representations. Third, we develop a cross-modal retrieval benchmark that covers all possible directional retrieval across the three modalities (i.e., image-to-audio, audio-to-text, text-to-image, and their reverse directions), with three taxonomic levels: Family, Genus, and Species. Extensive experiments demonstrate that our model learns a unified representation space that captures species-level semantics beyond taxonomy, advancing multimodal biodiversity understanding. The project page is available at: https://dahlian00.github.io/BioVITA_Page/
format Preprint
id arxiv_https___arxiv_org_abs_2603_23883
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment
Shinoda, Risa
Shiohara, Kaede
Inoue, Nakamasa
Saito, Kuniaki
Santo, Hiroaki
Okura, Fumio
Computer Vision and Pattern Recognition
Understanding animal species from multimodal data poses an emerging challenge at the intersection of computer vision and ecology. While recent biological models, such as BioCLIP, have demonstrated strong alignment between images and textual taxonomic information for species identification, the integration of the audio modality remains an open problem. We propose BioVITA, a novel visual-textual-acoustic alignment framework for biological applications. BioVITA involves (i) a training dataset, (ii) a representation model, and (iii) a retrieval benchmark. First, we construct a large-scale training dataset comprising 1.3 million audio clips and 2.3 million images, covering 14,133 species annotated with 34 ecological trait labels. Second, building upon BioCLIP2, we introduce a two-stage training framework to effectively align audio representations with visual and textual representations. Third, we develop a cross-modal retrieval benchmark that covers all possible directional retrieval across the three modalities (i.e., image-to-audio, audio-to-text, text-to-image, and their reverse directions), with three taxonomic levels: Family, Genus, and Species. Extensive experiments demonstrate that our model learns a unified representation space that captures species-level semantics beyond taxonomy, advancing multimodal biodiversity understanding. The project page is available at: https://dahlian00.github.io/BioVITA_Page/
title BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.23883