-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Brookes_2025_CVPR, author = {Brookes, Otto and Kukushkin, Maksim and Mirmehdi, Majid and Stephens, Colleen and Dieguez, Paula and Hicks, Thurston C. and Jones, Sorrel and Lee, Kevin and McCarthy, Maureen S. and Meier, Amelia and Normand, Emmanuelle and Wessling, Erin G. and Wittig, Roman M. and Langergraber, Kevin and Zuberb\"uhler, Klaus and Boesch, Lukas and Schmid, Thomas and Arandjelovic, Mimi and K\"uhl, Hjalmar and Burghardt, Tilo}, title = {The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)}, month = {June}, year = {2025}, pages = {5433-5443} }
The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition
Abstract
Computer vision analysis of camera trap video footage is essential for wildlife conservation, as captured behaviours offer some of the earliest indicators of changes in population health. Recently, several high-impact animal behaviour datasets and methods have been introduced to encourage their use; however, the role of behaviour-correlated background information and its significant effect on out-of-distribution generalisation remain unexplored. In response, we present the PanAf-FGBG dataset, featuring 21 hours of wild chimpanzee behaviours, recorded at 389 individual camera locations. Uniquely, it pairs every video with a chimpanzee (referred to as a foreground video) with a corresponding background video (with no chimpanzee) from the same camera location. We present two views of the dataset: one with overlapping camera locations and one with disjoint locations. This setup enables, for the first time, direct evaluation of in-distribution and out-of-distribution conditions, and for the impact of backgrounds on behaviour recognition models to be quantified. All clips have rich behavioural annotations and metadata, including unique camera IDs. Additionally, we establish several baselines and present a highly effective latent-space normalisation technique that boosts out-of-distribution performance by +5.42% mAP for convolutional and +3.75% mAP for transformer-based models. Finally, we provide an in-depth analysis on the role of backgrounds in out-of-distribution behaviour recognition, including the so far unexplored impact of background durations. (i.e., the count of background frames within foreground videos). The dataset is available at https://obrookes.github.io/panaf-fgbg.github.io
Related Material