Abstract
Understanding non-human primate behavior is essential for advancing animal welfare and uncovering the roots of human sociality. However, automated analysis remains limited. Existing methods, many of which are human-centric, are typically task-specific, handling detection, tracking, or behavior recognition in isolation. We present AlphaChimp, an end-to-end and unified framework for chimpanzee detection, tracking, and spatiotemporal behavior recognition. To address the unique challenges of chimpanzee video analysis, such as frequent occlusions and social interactions, we build upon a DETR-based architecture with crucial modifications. Our model integrates multi-resolution temporal features to capture long-term contextual cues and employs attention mechanisms to model spatial relationships between individuals. This unique design allows AlphaChimp to jointly capture individual and social interactions. Evaluated on the ChimpACT dataset, the only benchmark with fine-grained spatiotemporal annotations of chimpanzee behavior, our method achieves state-of-the-art performance, with a 10% gain in tracking and a 20% improvement in behavior recognition, particularly for social behaviors. It also surpasses recent video foundation models. Our approach bridges computer vision and primatology, enabling scalable, objective analysis of primate social behavior to facilitate future research. We release our code and models at project page and hope this will facilitate future research in animal social dynamics.
Yutang Lin
Tong Class '23
I’m an undergraduate student at Yuanpei College, Peking University, pursuing a Bachelor’s degree in Computer Science. My research interests include computer vision, robotics, and machine learning.
Federico Rossano
Associate Professor
