Changes in the equine facial repertoire during different orthopedic pain intensities.

A number of facial expressions are associated with pain in horses, however, the entire display of facial activities during orthopedic pain have yet to be described. The aim of the present study was to exhaustively map changes in facial activities in eight resting horses during a progression from sound to mild and moderate degree of orthopedic pain, induced by lipopolysaccharides (LPS) administered in the tarsocrural joint. Lameness progression and regression was measured by objective gait analysis during movement, and facial activities were described by EquiFACS in video sequences (n = 348, total length 892.5 min) of the horses obtained when resting in their box stalls. Predictive modeling identified 16 action units and action descriptors, related to ears, eyes, and lower face. Lower lip depressor (AU16), lips part (AU25), half blink (AU47), single ear forward (SEAD101) and single ear rotator (SEAD104) were selected as co-occurring significantly more in horses with pain than in horses without pain. The major change in co-occurring facial activities occurred in the transition from no pain to mild pain. In conclusion, resting horses with induced orthopedic pain showed a dynamic upper and lower facial repertoire and the relationship between level of pain intensity and facial activity appears complex.

Sharing pain: Using pain domain transfer for video recognition of low grade orthopedic pain in horses.

Orthopedic disorders are common among horses, often leading to euthanasia, which often could have been avoided with earlier detection. These conditions often create varying degrees of subtle long-term pain. It is challenging to train a visual pain recognition method with video data depicting such pain, since the resulting pain behavior also is subtle, sparsely appearing, and varying, making it challenging for even an expert human labeller to provide accurate ground-truth for the data. We show that a model trained solely on a dataset of horses with acute experimental pain (where labeling is less ambiguous) can aid recognition of the more subtle displays of orthopedic pain. Moreover, we present a human expert baseline for the problem, as well as an extensive empirical study of various domain transfer methods and of what is detected by the pain recognition method trained on clean experimental pain in the orthopedic dataset. Finally, this is accompanied with a discussion around the challenges posed by real-world animal behavior datasets and how best practices can be established for similar fine-grained action recognition tasks. Our code is available at https://github.com/sofiabroome/painface-recognition.