Domain: Computer Vision

14 terms

3D Reconstruction Intermediate

Recovering 3D structure from images.
CLIP Intermediate

Joint vision-language model aligning images and text.
Computer Vision Intermediate

AI focused on interpreting images/video: classification, detection, segmentation, tracking, and 3D understanding.
Convolutional Neural Network Intermediate

Networks using convolution operations with weight sharing and locality, effective for images and signals.
Cross-Attention Intermediate

Attention between different modalities.
Image Classification Intermediate

Assigning category labels to images.
Instance Segmentation Intermediate

Pixel-level separation of individual object instances.
Multimodal Fusion Intermediate

Combining signals from multiple modalities.
Object Detection Intermediate

Identifying and localizing objects in images, often with confidence scores and bounding rectangles.
Optical Flow Intermediate

Pixel motion estimation between frames.
Segmentation Intermediate

Assigning labels per pixel (semantic) or per instance (instance segmentation) to map object boundaries.
Semantic Segmentation Intermediate

Pixel-wise classification of image regions.
SLAM Intermediate

Simultaneous Localization and Mapping for robotics.
Vision Transformer Intermediate

Transformer applied to image patches.