cross-modal learning

LEARNING TORSO PRIOR FOR CO-SPEECH GESTURE GENERATION WITH BETTER HAND SHAPE

Video Question Answering using Clip-guided Visual-text Attention

Learning Music Sequence Representation from Text Supervision

ENHANCING AFFECTIVE REPRESENTATIONS OF MUSIC-INDUCED EEG THROUGH MULTIMODAL SUPERVISION AND LATENT DOMAIN ADAPTATION

UNSUPERVISED AUDIO-CAPTION ALIGNING LEARNS CORRESPONDENCES BETWEEN INDIVIDUAL SOUND EVENTS AND TEXTUAL PHRASES

TIE YOUR EMBEDDINGS DOWN: CROSS-MODAL LATENT SPACES FOR END-TO-END SPOKEN LANGUAGE UNDERSTANDING