Similar Items: SkelFormer: An adaptive hierarchical transformer-based approach on skeleton graphs for human action recognition in video sequences
- VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition
- RigidFormer: Learning Rigid Dynamics using Transformers
- Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements
- Enhancing Building Change Detection in ChangeFormer by Integrating Deformable Attention Transformer
- SCBI_MapReduce, a New Ruby Task-Farm Skeleton for Automated Parallelisation and Distribution in Chunks of Sequences: The Implementation of a Boosted Blast+
- Bounding linear head reduction and visible interaction through skeletons