Abstract: Benefiting from the powerful feature extraction and feature correlation modeling capabilities of convolutional neural networks (CNNs) and Transformer models, these techniques have been ...

Abstract: Aligned text-image encoders such as CLIP have become the de-facto model for vision-language tasks. Further-more, modality-specific encoders achieve impressive per-formances in their ...

VideoPrism is a general-purpose video encoder designed to handle a wide spectrum of video understanding tasks, including classification, retrieval, localization, captioning, and question answering. It ...