I. Schwartz

Latest

• Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation
• Zero-shot video captioning with evolving pseudo-tokens
• AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation
• Discriminative Class Tokens for Text-to-Image Diffusion Models
• Describing Sets of Images with Textual-PCA
• Optimizing Relevance Maps of Vision Transformers Improves Robustness
• ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic
• Video and Text Matching with Conditioned Embeddings
• Ordered attention for coherent visual storytelling
• Latent space explanation by intervention
• Perceptual Score: Measuring Perceptiveness of Multi-Modal Classifiers
• Ensemble of MRR and NDCG models for Visual Dialog
• Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies
• A Simple Baseline for Audio-Visual Scene-Aware Dialog
• Factor Graph Attention
• High-Order Attention Models for Visual Question Answering