Max Bain

multimodal learning (4) vision-language model (3) audio description (3) transformer architecture (2) adversarial learning (2) contrastive learning (2) video understanding (2) adversarial debiasing (2) audio description generation (2) text generation (1) bias mitigation (1) context modeling (1) video captioning (1) fine-grained understanding (1) visual language model (1) weakly-supervised learning (1) societal bia (1) joint embedding (1) contrastive loss (1) video-text retrieval (1)