Amir Bar

12

Papers

422

Total Citations

Papers (12)

Sequential Modeling Enables Scalable Learning for Large Vision Models

Navigation World Models

Scaling Language-Free Visual Representation Learning

EgoPet: Egomotion and Interaction Data from an Animal's Perspective

Vision-Language Models Create Cross-Modal Task Representations

Learning Individual Styles of Conversational Gesture

Stochastic positional embeddings improve masked image modeling

DETReg: Unsupervised Pretraining With Region Priors for Object Detection

Object-Region Video Transformers

Learning Canonical Representations for Scene Graph to Image Generation

Visual Prompting via Image Inpainting

Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens