Michel Olvera

multimodal learning (2) zero-shot learning (2) multi-modal learning (1) deep learning (1) audio source separation (1) knowledge graph (1) knowledge graph embedding (1) semantic embedding (1) cross-modal alignment (1) vision-language model (1) multimodal alignment (1) audio captioning (1) token distribution (1) sound event detection (1) semantic grounding (1) audio-visual alignment (1) audio-language model (1) contrastive language-audio pretraining (1) neural network (1) zero-shot recognition (1)