Bryan Russell

video understanding (4) multimodal learning (4) self-supervised learning (4) cross-modal retrieval (3) audio-visual learning (3) view synthesis (2) convolutional neural network (2) surface normal prediction (2) video retrieval (2) neural rendering (2) contrastive learning (2) image matching (2) vision-language model (2) neural radiance field (2) pose estimation (2) 3d vision (2) music recommendation (2) depth estimation (2) scene understanding (2) video localization (2)