DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding
This work addresses privacy-preserving human activity analysis for applications like recognition and re-identification, but it is incremental as it builds on existing datasets and contrastive learning methods.
The paper tackles the underexplored use of LiDAR point clouds for human activity understanding by introducing DeSPITE, a model that learns a joint embedding space across point clouds, skeletons, IMU data, and text, enabling novel tasks like cross-modal matching and retrieval.
Despite LiDAR (Light Detection and Ranging) being an effective privacy-preserving alternative to RGB cameras to perceive human activities, it remains largely underexplored in the context of multi-modal contrastive pre-training for human activity understanding (e.g., human activity recognition (HAR), retrieval, or person re-identification (RE-ID)). To close this gap, our work explores learning the correspondence between LiDAR point clouds, human skeleton poses, IMU data, and text in a joint embedding space. More specifically, we present DeSPITE, a Deep Skeleton-Pointcloud-IMU-Text Embedding model, which effectively learns a joint embedding space across these four modalities. At the heart of our empirical exploration, we have combined the existing LIPD and Babel datasets, which enabled us to synchronize data of all four modalities, allowing us to explore the learning of a new joint embedding space. Our experiments demonstrate novel human activity understanding tasks for point cloud sequences enabled through DeSPITE, including Skeleton<->Pointcloud<->IMU matching, retrieval, and temporal moment retrieval. Furthermore, we show that DeSPITE is an effective pre-training strategy for point cloud HAR through experiments in MSR-Action3D and HMPEAR.