Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Extraction: Partition and Distribution Coefficients

Extraction: Partition and Distribution Coefficients

The distribution law or Nernst's distribution law is the law that governs the distribution of a solute between two immiscible solvents. This law, also known as the partition law, states that if a solute is added to the mixture of two immiscible solvents at a constant temperature, the solute is distributed between the two solvents in such a way that the ratio of solute concentrations in the solvents remains constant at equilibrium.
For extracting a solute from an aqueous phase into an organic...

Vector Algebra: Method of Components

Vector Algebra: Method of Components

It is cumbersome to find the magnitudes of vectors using the parallelogram rule or using the graphical method to perform mathematical operations like addition, subtraction, and multiplication. There are two ways to circumvent this algebraic complexity. One way is to draw the vectors to scale, as in navigation, and read approximate vector lengths and angles (directions) from the graphs. The other way is to use the method of components.
In many applications, the magnitudes and directions of...

Collisions in Multiple Dimensions: Problem Solving

Collisions in Multiple Dimensions: Problem Solving

In multiple dimensions, the conservation of momentum applies in each direction independently. Hence, to solve collisions in multiple dimensions, we should write down the momentum conservation in each direction separately. To help understand collisions in multiple dimensions, consider an example.
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...

Area Computation by the Alternative Coordinate Method

Area Computation by the Alternative Coordinate Method

The alternative coordinate method, also known as the Shoelace Formula, is a technique for determining the area of a traverse using Cartesian coordinates. This method relies on the sequential arrangement of x and y coordinates for each point of the shape, ensuring accuracy and ease of application.In this approach, each corner's x and y coordinates are listed as fractions, with the x-coordinate as the numerator and the y-coordinate as the denominator. These coordinates are arranged sequentially...

Structural Classification of Joints

Structural Classification of Joints

Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...

Deconvolution

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

'Ion-freeze' efficiency in perovskite solar cells: time scales for ion immobilization.

EES solar·2025

Same author

Ego4D: Around the World in 3,600 Hours of Egocentric Video.

IEEE transactions on pattern analysis and machine intelligence·2024

Same author

HistoPerm: A permutation-based view generation approach for improving histopathologic feature representation learning.

Journal of pathology informatics·2023

Same author

Generalized Few-Shot Video Classification With Video Retrieval and Feature Generation.

IEEE transactions on pattern analysis and machine intelligence·2021

Same author

Resolution-based distillation for efficient histology image classification.

Artificial intelligence in medicine·2021

Same author

Discovering Digital Tumor Signatures-Using Latent Code Representations to Manipulate and Classify Liver Lesions.

Cancers·2021

Search research articles

Related Experiment Videos

A dual decomposition approach to feature correspondence.

Lorenzo Torresani¹, Vladimir Kolmogorov, Carsten Rother

¹Department of Computer Science, Dartmouth College, 6211 Sudikoff Lab, Hanover, NH 03755, USA. lorenzo@cs.dartmouth.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence

|May 9, 2012

Summary

This study introduces a new dual decomposition (DD) method for matching sparse image features, outperforming existing algorithms. The approach efficiently finds global optima, enabling accurate learning for superior state-of-the-art results in computer vision tasks.

Related Experiment Videos

Area of Science:

Computer Vision
Machine Learning
Computational Geometry

Background:

Establishing correspondences between sparse image features is challenging due to nonrigid mappings, clutter, and occlusion.
Existing graph matching algorithms struggle with NP-hard optimization problems inherent in feature matching.

Purpose of the Study:

To develop a novel and efficient approach for robust feature matching under challenging conditions.
To introduce a new optimization technique for energy minimization in graph matching problems.

Main Methods:

Formulating feature matching as an energy minimization problem with an objective function considering appearance and spatial arrangement.
Developing a novel dual decomposition (DD) technique for optimizing the energy function, addressing the NP-hard nature of graph matching.
Training and evaluating the learned matching model on various computer vision tasks.

Main Results:

The proposed dual decomposition (DD) method significantly outperforms existing graph matching algorithms.
DD successfully finds the global minimum for the objective function in most cases within a minute.
The learned matching model achieves superior performance compared to state-of-the-art methods on multiple matching tasks.

Conclusions:

Dual decomposition (DD) offers an efficient and effective solution for establishing correspondences between sparse image features.
The ability to globally optimize the objective function enables accurate model parameter learning.
This approach advances the state-of-the-art in nonrigid feature matching, particularly in the presence of clutter and occlusion.