MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding

TL;DR

MammalNet is a comprehensive large-scale video dataset designed for mammal recognition and behavior understanding, enabling advanced research in wildlife monitoring and conservation through extensive annotated videos.

Contribution

The paper introduces MammalNet, the largest annotated mammal behavior dataset with taxonomy-guided labels, facilitating large-scale recognition and behavior detection tasks.

Findings

MammalNet contains over 18,000 videos and 539 hours of footage.

It covers 17 orders, 69 families, and 173 mammal categories.

Three benchmarks are established for recognition and behavior detection.

Abstract

Monitoring animal behavior can facilitate conservation efforts by providing key insights into wildlife health, population status, and ecosystem function. Automatic recognition of animals and their behaviors is critical for capitalizing on the large unlabeled datasets generated by modern video devices and for accelerating monitoring efforts at scale. However, the development of automated recognition systems is currently hindered by a lack of appropriately labeled datasets. Existing video datasets 1) do not classify animals according to established biological taxonomies; 2) are too small to facilitate large-scale behavioral studies and are often limited to a single species; and 3) do not feature temporally localized annotations and therefore do not facilitate localization of targeted behaviors within longer video sequences. Thus, we propose MammalNet, a new large-scale animal behavior dataset with taxonomy-guided annotations of mammals and their common behaviors. MammalNet contains over 18K videos totaling 539 hours, which is ~10 times larger than the largest existing animal behavior dataset. It covers 17 orders, 69 families, and 173 mammal categories for animal categorization and captures 12 high-level animal behaviors that received focus in previous animal behavior studies. We establish three benchmarks on MammalNet: standard animal and behavior recognition, compositional low-shot animal and behavior recognition, and behavior detection. Our dataset and code have been made available at: https://mammal-net.github.io.