Cerca risorse accademiche

We have developed a near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals. The computational appro...

The VideoToolbox is a free collection of two hundred C subroutines for Macintosh computers that calibrates and controls the computer-display interface to create accurately specified visual stimuli. High-level platform-in...

Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks...

The problem of efficient, interactive foreground/background segmentation in still images is of great practical importance in image editing. Classical image segmentation tools use either texture (colour) information, e.g....

Materie / parole chiave: Computer science; Segmentation; Artificial intelligence; Annotation; Volume (thermodynamics); Set (abstract data type); Training set; Pattern recognition (psychology); Test data; Computer vision; Physics; Quantum mechani...

The recent development of various methods of modulation such as PCM and PPM which exchange bandwidth for signal-to-noise ratio has intensified the interest in a general theory of communication. A basis for such a theory ...

Materie / parole chiave: Mathematical morphology; Morphology (biology); Image (mathematics); Artificial intelligence; Computer science; Morphological analysis; Computer vision; Image processing; Geology; Paleontology

Materie / parole chiave: Maxima and minima; Computer science; Robustness (evolution); Image registration; Artificial intelligence; Interpolation (computer graphics); Global optimization; Computer vision; Optimization problem; Motion (physics); A...

Materie / parole chiave: Maxima and minima; Computer science; Robustness (evolution); Image registration; Artificial intelligence; Global optimization; Interpolation (computer graphics); Optimization problem; Computer vision; Motion (physics); A...

We present a new algorithm, called marching cubes , that creates triangle models of constant density surfaces from 3D medical data. Using a divide-and-conquer approach to generate inter-slice connectivity, we create a ca...

We present a new algorithm, called marching cubes, that creates triangle models of constant density surfaces from 3D medical data. Using a divide-and-conquer approach to generate inter-slice connectivity, we create a cas...

Materie / parole chiave: Computer science; Pascal (unit); Spotting; Artificial intelligence; Segmentation; Minimum bounding box; Bounding overwatch; Object detection; Object (grammar); Context (archaeology); Computer vision; Image segmentation

Materie / parole chiave: Software; Image (mathematics); Computer science; Data science; Image processing; Image analysis; Computer graphics (images); Computer vision; Digital image processing; Programming language

We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm ...

This paper presents ORB-SLAM, a feature-based monocular simultaneous localization and mapping (SLAM) system that operates in real time, in small and large indoor and outdoor environments. The system is robust to severe m...

Materie / parole chiave: Computer science; Artificial intelligence; Convolutional neural network; Image (mathematics); Pixel; Perception; Transformation (genetics); Ground truth; Transfer (computing); Computer vision; Pattern recognition (psycho...

Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resol...

Materie / parole chiave: Computer science; Robustness (evolution); Artificial intelligence; Hessian matrix; Detector; Computer vision; Invariant (physics); Pattern recognition (psychology); Mathematics; Gene; Telecommunications; Biochemistry

Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning....

Materie / parole chiave: Computer science; Segmentation; Encoder; Artificial intelligence; Image segmentation; Feature (linguistics); Deep learning; Computer vision; Pattern recognition (psychology); Image (mathematics); Operating system; Lingui...

During the late 1990s, Huang introduced the algorithm called Empirical Mode Decomposition, which is widely used today to recursively decompose a signal into different modes of unknown but separate spectral bands. EMD is ...

Materie / parole chiave: computer science, computer security, computer vision, human-computer interaction, theoretical computer science; Science: Mathematics: Instruments and machines: Electronic computers. Computer science

Materie / parole chiave: computer science, information technology, communication technology, machine learning, computer vision; Technology: Technology (General): Industrial engineering. Management engineering: Information technology; Science: Ma...

Materie / parole chiave: artificial intelligence, autonomous robotics, computational intelligence, computer vision, cybersecurity, machine learning; Language and Literature: Philology. Linguistics: Computational linguistics. Natural language pro...