Search papers, labs, and topics across Lattice.
4
0
4
1
FineX boosts fine-grained action recognition accuracy by over 7% on challenging datasets, leveraging a unique fusion of visual and skeletal representations.
Explicitly modeling skin lesions as graphs with integrated metadata leads to significant improvements in classification accuracy over traditional CNN/ViT methods.
Achieve state-of-the-art fine-grained action recognition with a lightweight, plug-and-play RGB-only module that outperforms heavier multimodal models.
Virtual histological staining can now achieve unprecedented fidelity thanks to a novel diffusion transformer architecture that balances spatial constraints and semantic guidance.
