Philip H.S. Torr

9

Papers

88

Total Citations

Papers (9)

Vision-Language Models Do Not Understand Negation

Video Motion Transfer with Diffusion Transformers

FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models

RoDLA: Benchmarking the Robustness of Document Layout Analysis Models

Open-World Objectness Modeling Unifies Novel Object Detection

Olympus: A Universal Task Router for Computer Vision Tasks

CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor

Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation

Localizing Events in Videos with Multimodal Queries