ORCA: Object Recognition and Comprehension for Archiving Marine Species
Wong, Y.-K.; Liang, H.; Ma, Z.; Cheng, Y.; Zheng, Z.; Gotama, R.; Sebastian, P.; Sparks, L.D.; Yeung, S.K. (2026). ORCA: Object Recognition and Comprehension for Archiving Marine Species, in: 2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 6-10 March 2026, Tucson, Arizona, USA. pp. 1597-1609. https://dx.doi.org/10.1109/wacv61042.2026.00161
|
| Beschikbaar in | Auteurs |
|
Documenttype: Congresbijdrage
|
| Auteurs | | Top |
- Wong, Y.-K.
- Liang, H.
- Ma, Z.
|
- Cheng, Y.
- Zheng, Z.
- Gotama, R.
|
- Sebastian, P.
- Sparks, L.D.
- Yeung, S.K.
|
| Abstract |
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. |
|
