Guest Editors

• Hyun Soo Park; University of Minnesota
• Helge Rhodin; University of British Columbia
• Angjoo Kanazawa; University of California, Berkeley
• Natalia Neverova; Facebook AI Research
• Shohei Nobuhara; Kyoto University
• Michael Black; Max Planck Institute for Intelligent Systems

Many biological organisms are evolved to exhibit diverse quintessential behaviors via physical and social interactions with surroundings, and understanding these behaviors is a fundamental goal of multiple disciplines including neuroscience, biology, animal husbandry, ecology, and animal conservation. For example, ethogramming characterizes the behavioral states and their transitions, which further provides a scientific basis to understand innate human behaviors, e.g., decision making, attention, and group behaviors. These analyses require objective, repeatable, and scalable measurements of animal behaviors that are not possible with existing methodologies that leverage manual encoding from animal experts and specialists. Recently, computer vision has been making a groundbreaking impact by providing a new tool that enables computational measurements of the behaviors. 

Despite its significance, the area of animal tracking and modeling is still under-explored and under-represented in computer vision, compared to that of human subjects. While computer vision methods to track, model, and reconstruct humans are highly inspirational, we argue that these methods are not necessarily applicable to a new animal species without non-trivial modifications. This performance degradation stems from various reasons including scarce annotated data, characteristic body movements and constraints (e.g., bipedal vs. quadrupedal vs. polypedal), irregular/homogeneous skin texture, and limited resolution due to remote sensing. This requires a series of innovations. 

This special issue is motivated by the amount of enthusiasm (more than 50 paper submissions and 120 attendances) seen at our CVPR 2021 workshop on CV4Animals: Computer Vision for Animal Tracking and Modeling, which showcased interdisciplinary demands and interests in the topic. However, there exists no formal publication venue to consolidate this newly emerging field. We, therefore, propose this special issue, aiming to address this. 

Aims and Scope

• Animal motion capture and data
  • Marker/markerless capture
  • Camera trap remote capture
  • Underwater capture
  • Neuro-motor data recording
• Animal behavior tracking
  • Fine-grain detection/segmentation/categorization of animals and their species
  • 2D/3D pose/shape estimation
  • Skin texture reconstruction
  • Deformable body modeling
  • Counting
  • Re-Identification
• Animal behavior modeling
  • Behavioral state characterization/classification (ethogramming)
  • Dynamics of group/herd/flock behavior
  • Behavior analysis and prediction
  • Neuro-motor relation learning
  • Behavior assessment  

Important Dates

Full paper submission deadline: March 27, 2022
Review deadline: June 18, 2022
Author response deadline: July 22, 2022
Final notification: September 23, 2022
Final manuscript submission: October 28, 2022