CLIP

Intermediate

Joint vision-language model aligning images and text.

Full Definition

Joint vision-language model aligning images and text.

Keywords

contrastive vision-language

Domains

Computer Vision

Related Terms

Multimodal Fusion related to

Combining signals from multiple modalities.

 Cross-Attention related to

Attention between different modalities.

 Optical Flow related to

Pixel motion estimation between frames.

 SLAM related to

Simultaneous Localization and Mapping for robotics.

 Image Classification related to

Assigning category labels to images.

 Instance Segmentation related to

Pixel-level separation of individual object instances.

 Semantic Segmentation related to

Pixel-wise classification of image regions.

 Vision Transformer related to

Transformer applied to image patches.

Concept Map

See how CLIP connects to other concepts.

Open Knowledge Graph