X-CLIP is a multimodal model developed by Microsoft that extends CLIP to the video domain. It learns joint embeddings between video clips and text, enabling zero-shot video classification, retrieval, and other video-language tasks. The base-patch32 variant is available on Hugging Face for integration into computer vision and multimedia applications.
Xclip Base Patch32 sits in PulseGate's Other AI category. It focuses on aligning video content with natural language descriptions for retrieval, classification, and understanding tasks. It is built as an open-source project for developers. Xclip Base Patch32 is open source under the Open Source license. The product ships for the web and API.
It is developed by Microsoft (United States), and the product first shipped in 2019. Development happens publicly on GitHub with 1.1k stars. Key capabilities include Video Understanding, Text-Video Alignment, and Contrastive Learning.
Latest indexed changes and source events
microsoft/xclip-base-patch32 verified by the PulseGate indexer
Other apps tracked under the same category.
