Hassan Akbari

self-supervised learning (2) multimodal learning (2) contrastive learning (2) curriculum learning (1) visual grounding (1) semantic space (1) convolutional neural network (1) visual feature (1) alternating gradient descent (1) cosine similarity (1) transformer encoder (1) multimodal attention (1) multimodal transformer (1) phrase grounding (1) video action recognition (1) cross-modality alignment (1) multimodal contrastive learning (1) text-to-video retrieval (1) multimodal pre-training (1) video-audio-text alignment (1)