ORCA: Object Recognition and Comprehension for Archiving Marine Species
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911337495396352 |
|---|---|
| author | Wong, Yuk-Kwan Liang, Haixin Ma, Zeyu Chen, Yiwei Zheng, Ziqiang Gotama, Rinaldi Sebastian, Pascal Sparks, Lauren D. Yeung, Sai-Kit |
| author_facet | Wong, Yuk-Kwan Liang, Haixin Ma, Zeyu Chen, Yiwei Zheng, Ziqiang Gotama, Rinaldi Sebastian, Pascal Sparks, Lauren D. Yeung, Sai-Kit |
| contents | Marine visual understanding is essential for monitoring and protecting marine ecosystems, enabling automatic and scalable biological surveys. However, progress is hindered by limited training data and the lack of a systematic task formulation that aligns domain-specific marine challenges with well-defined computer vision tasks, thereby limiting effective model application. To address this gap, we present ORCA, a multi-modal benchmark for marine research comprising 14,647 images from 478 species, with 42,217 bounding box annotations and 22,321 expert-verified instance captions. The dataset provides fine-grained visual and textual annotations that capture morphology-oriented attributes across diverse marine species. To catalyze methodological advances, we evaluate 18 state-of-the-art models on three tasks: object detection (closed-set and open-vocabulary), instance captioning, and visual grounding. Results highlight key challenges, including species diversity, morphological overlap, and specialized domain demands, underscoring the difficulty of marine understanding. ORCA thus establishes a comprehensive benchmark to advance research in marine domain. Project Page: http://orca.hkustvgd.com/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_21150 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ORCA: Object Recognition and Comprehension for Archiving Marine Species Wong, Yuk-Kwan Liang, Haixin Ma, Zeyu Chen, Yiwei Zheng, Ziqiang Gotama, Rinaldi Sebastian, Pascal Sparks, Lauren D. Yeung, Sai-Kit Computer Vision and Pattern Recognition Marine visual understanding is essential for monitoring and protecting marine ecosystems, enabling automatic and scalable biological surveys. However, progress is hindered by limited training data and the lack of a systematic task formulation that aligns domain-specific marine challenges with well-defined computer vision tasks, thereby limiting effective model application. To address this gap, we present ORCA, a multi-modal benchmark for marine research comprising 14,647 images from 478 species, with 42,217 bounding box annotations and 22,321 expert-verified instance captions. The dataset provides fine-grained visual and textual annotations that capture morphology-oriented attributes across diverse marine species. To catalyze methodological advances, we evaluate 18 state-of-the-art models on three tasks: object detection (closed-set and open-vocabulary), instance captioning, and visual grounding. Results highlight key challenges, including species diversity, morphological overlap, and specialized domain demands, underscoring the difficulty of marine understanding. ORCA thus establishes a comprehensive benchmark to advance research in marine domain. Project Page: http://orca.hkustvgd.com/. |
| title | ORCA: Object Recognition and Comprehension for Archiving Marine Species |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.21150 |