SA-FARI 数据集：面向识别与鉴定的动物视频分割一切
The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification
SA-FARI 提供了大规模、多物种、跨地域的相机陷阱视频密集标注（掩码、边界框、身份），可直接用于训练和评测多动物跟踪与重识别模型；其基准测试还系统比较了 SAM 3 等视觉语言模型在物种特定与通用提示下的表现，为视觉-语言模型在细粒度动物跟踪中的适用性提供了参考。
原文依据 we present comprehensive benchmarks on SA-FARI using state-of-the-art vision-language models for detection and tracking, including SAM 3
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自动化视频分析对野生动物保护至关重要。该领域的一项基础任务是多动物跟踪（MAT），它支撑着个体重识别和行为识别等应用。然而，现有数据集在规模上有限、局限于少数物种，或缺乏足够的时序和地理多样性——导致没有合适的基准来训练适用于野生动物的通用 MAT 模型。为此，我们推出了 SA-FARI，这是最大的开源野生动物 MAT 数据集。它包含 11,609 段相机陷阱视频，采集自 2014 至 2024 年的 10 年间，覆盖 4 大洲的 741 个地点，涵盖 99 个物种类别。每段视频都经过详尽标注，最终形成 46 小时的密集标注视频，包含 16,224 个掩码身份和 942,702 个个体边界框、分割掩码及物种标签。除任务特定标注外，我们还发布了每段视频的匿名化相机陷阱位置。最后，我们使用最优的视觉语言模型在 SA-FARI 上进行了全面的基准测试，用于检测和跟踪，包括 SAM 3，并分别以物种特定和通用动物提示进行评估。我们还与专为野生动物分析开发的纯视觉方法进行了比较。SA-FARI 是首个结合高物种多样性、多区域覆盖和高质量时空标注的大规模数据集，为推进野外多动物跟踪提供了新基础。数据集可在 conservationxlabs.com/SA-FARI 获取。
英文原文摘要 1584 字符
Automated video analysis is critical for wildlife conservation. A foundational task in this domain is multi-animal tracking (MAT), which underpins applications such as individual re-identification and behavior recognition. However, existing datasets are limited in scale, constrained to a few species, or lack sufficient temporal and geographical diversity - leaving no suitable benchmark for training general-purpose MAT models applicable to wild animals. To address this, we introduce SA-FARI, the largest open-source MAT dataset for wild animals. It comprises 11,609 camera trap videos collected over 10 years (2014-2024) from 741 locations across 4 continents, spanning 99 species categories. Each video is exhaustively annotated culminating in 46 hours of densely annotated footage containing 16,224 masklet identities and 942,702 individual bounding boxes, segmentation masks, and species labels. Alongside the task-specific annotations, we publish anonymized camera trap locations for each video. Finally, we present comprehensive benchmarks on SA-FARI using state-of-the-art vision-language models for detection and tracking, including SAM 3, evaluated with both species-specific and generic animal prompts. We also compare against vision only methods developed specifically for wildlife analysis. SA-FARI is the first large-scale dataset to combine high species diversity, multi-region coverage, and high-quality spatio-temporal annotations, offering a new foundation for advancing multi-animal tracking in the wild. The dataset is available at conservationxlabs.com/SA-FARI.