Similar Items: Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements
- Learning Coarse-to-Fine Osteoarthritis Representations under Noisy Hierarchical Labels
- Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictions
- Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision
- Representation Fréchet Loss for Visual Generation
- Exploring the Limits of End-to-End Feature-Affinity Propagation for Single-Point Supervised Infrared Small Target Detection
- A Benchmark for Interactive World Models with a Unified Action Generation Framework