AnimalMotionCLIP: Embedding motion in CLIP for Animal Behavior Analysis
This work addresses the specific challenge of fine-grained temporal action recognition in animal behavior analysis, which is incremental as it builds on existing CLIP models.
The paper tackled the problem of adapting CLIP for animal behavior recognition by integrating motion information and temporal modeling, achieving superior performance on the Animal Kingdom dataset compared to state-of-the-art methods.
Recently, there has been a surge of interest in applying deep learning techniques to animal behavior recognition, particularly leveraging pre-trained visual language models, such as CLIP, due to their remarkable generalization capacity across various downstream tasks. However, adapting these models to the specific domain of animal behavior recognition presents two significant challenges: integrating motion information and devising an effective temporal modeling scheme. In this paper, we propose AnimalMotionCLIP to address these challenges by interleaving video frames and optical flow information in the CLIP framework. Additionally, several temporal modeling schemes using an aggregation of classifiers are proposed and compared: dense, semi dense, and sparse. As a result, fine temporal actions can be correctly recognized, which is of vital importance in animal behavior analysis. Experiments on the Animal Kingdom dataset demonstrate that AnimalMotionCLIP achieves superior performance compared to state-of-the-art approaches.