OCHuman (occluded human dataset)
OCHuman is a dataset used in computer vision for human detection and segmentation, particularly focusing on occlusion scenarios.
Artificial Intelligence
Existential risk from artificial general intelligence
Existential risk from artificial general intelligence refers to the potential threats posed by AGI to humanity’s future, emphasizing the need for careful management and regulation.
PC-AVS (pose-controllable audio-visual system)
PC-AVS (pose-controllable audio-visual system) is a technology that integrates pose estimation with audio-visual synthesis, enabling interactive and controllable multimedia experiences. It allows users to manipulate audio and visual outputs based on detected human poses or movements.
Logistic regression
Logistic regression is a statistical method for predicting binary classes. It models the probability of a certain class or event occurring.
DeepDream
DeepDream is a computer vision program created by Google that uses a convolutional neural network to enhance and modify images, creating surreal visual effects.
AudioSet
AudioSet is a large-scale dataset for sound classification created by Google. It contains over 2 million human-labeled sound clips from various sources.
Voyage (embedding model)
Voyage is an embedding model designed for representing complex data in a continuous vector space, facilitating tasks such as similarity search, clustering, and machine learning integration. It aims to enhance the efficiency and accuracy of data retrieval and analysis across various domains.
Logit lens
The Logit lens is a statistical tool used in various fields to model and analyze categorical outcomes. It is particularly significant in fields like economics, healthcare, and social sciences.
Max Planck Institute for Intelligent Systems
The Max Planck Institute for Intelligent Systems is a German research institute dedicated to advancing the field of intelligent systems, encompassing robotics, machine learning, and materials science. It operates under the Max Planck Society and includes locations in Stuttgart and Tübingen.
Laplacian eigenmaps
Laplacian eigenmaps is a dimensionality reduction technique used in machine learning and data analysis, particularly for nonlinear data structures.