Vision Glossary
Browse 18 vision terms defined in plain English, from the cultural dictionary of computing.
18 Vision Terms
- CLIP
- A multimodal model trained to align images and text in a shared embedding space. It influences how models are trained, evaluated, or served, and it can...
- CLIP Model
- A model trained to align images and text in a shared embedding space so they can be compared semantically.
- Image Encoder
- A model component that converts image inputs into vector representations that other parts of the system can use for classification, retrieval, generation, or...
- Image-to-Image
- A generation task where one image is transformed into another while preserving selected structure or content. It influences how models are trained, evaluated,...
- Image Tokenizer
- A mechanism that transforms an image into a sequence of tokens or discrete units that a model can process, often as part of a multimodal architecture. Image...
- Large Vision Model
- A large-scale vision model pre-trained on broad image data for transfer to many downstream tasks. It influences how models are trained, evaluated, or served,...
- Multimodal
- Multimodal in AI describes systems that can process, understand, and generate content across multiple types of input and output, such as text, images, audio,...
- Multimodal AI
- AI systems that can process and generate multiple types of data — text, images, audio, video, and code — within a single model. GPT-4V, Claude 3, and Gemini...
- Multimodal Model
- A model that can process or generate across more than one data type, such as text, images, audio, or video.
- Semantic Web
- Semantic Web is a vision and set of technologies for extending the World Wide Web so that data is machine-readable and can be shared, linked, and reasoned...
- Vision Encoder
- A model component that converts image or visual input into encoded representations usable by downstream systems. Vision encoders are key building blocks in...
- Vision Feature
- A feature or representation extracted from visual input by a model or preprocessing system. Vision features help downstream models reason about shapes,...
- Vision Model
- A model designed to process images or visual data for tasks such as classification, detection, captioning, OCR, or multimodal reasoning. Vision models are...
- Vision Task
- A task involving visual input, such as classification, detection, segmentation, OCR, captioning, or visual question answering. Vision tasks often combine...
- Visual Grounding
- Linking model outputs or language understanding to specific elements in visual input so statements are tied to what is actually present in the image. Visual...
- Visual Instruction
- An instruction involving visual input, such as asking a model to describe, compare, annotate, or reason about an image or screenshot. Visual instructions are...
- Visual Understanding
- The ability of an AI system to interpret images, diagrams, screenshots, or other visual material meaningfully rather than only processing raw pixels. Visual...
- Web3
- A vision for a decentralized internet built on blockchain technology, where users own their data and identity. Coined by Ethereum co-founder Gavin Wood....
Related Topics
- Ai (9 terms in common)
- Encoders (2 terms in common)
- Audio (2 terms in common)
- Embeddings (2 terms in common)
- Multimodal (2 terms in common)
- Tokenization (1 terms in common)
- Web Standards (1 terms in common)
- Models (1 terms in common)
- Generation (1 terms in common)
- Transfer Learning (1 terms in common)
- Grounding (1 terms in common)
- Linked Data (1 terms in common)
- Transformation (1 terms in common)
- Tasks (1 terms in common)
- Llm (1 terms in common)
- Llms (1 terms in common)
- Understanding (1 terms in common)
- Features (1 terms in common)
- Decentralization (1 terms in common)
- Blockchain (1 terms in common)