Articles | arXiv Analytics

arXiv:1905.10590 (Published 2019-05-25)

A lower bound for the partition function from Chebyshev's inequality applied to a coin flipping model for the random partition

Mark Wildon

Categories: math.CO

Subjects: 05A17, 60C05

Keywords: coin flipping model, random partition, chebyshevs inequality, lower bound, partition function

arXiv:1905.10942 (Published 2019-05-27)

Noncommutative LR coefficients and crystal reflection operators

Edward Richmond, Vasu Tewari

Categories: math.CO

Subjects: 05E05

Keywords: crystal reflection operators, noncommutative lr coefficients, relate noncommutative littlewood-richardson coefficients, bessenrodt-luoto-van willigenburg, classical littlewood-richardson coefficients

arXiv:1905.10973 (Published 2019-05-27)

Generalized $q,t$-Catalan numbers

Eugene Gorsky, Graham Hawkes, Anne Schilling, Julianne Rainbolt

Categories: math.CO

Subjects: 05A18, 05A19, 05E05

Keywords: catalan numbers, khovanov-rozansky knot homology produces, explicit symmetric chain decomposition, equivariant euler characteristics, coefficients enumerate subdiagrams

arXiv:1905.10595 (Published 2019-05-25)

Unsupervised Single Image Underwater Depth Estimation

Honey Gupta, Kaushik Mitra

Categories: cs.CV, eess.IV

Keywords: single image underwater depth estimation, unsupervised single image underwater depth, single underwater image, generalized underwater depth datasets

arXiv:1905.10784 (Published 2019-05-26)

What is the relationship between face alignment and facial expression recognition?

Romain Belmonte, Benjamin Allaert, Pierre Tirilly, Ioan Marius Bilasco, Chaabane Djeraba, Nicu Sebe

Categories: cs.CV

Keywords: facial expression recognition, head pose variation, face alignment approaches, relationship, locate facial landmarks

arXiv:1905.10884 (Published 2019-05-26)

Bayesian Learning of Sum-Product Networks

Martin Trapp, Robert Peharz, Hong Ge, Franz Pernkopf, Zoubin Ghahramani

Categories: cs.LG, stat.ML

Keywords: sum-product networks, bayesian learning, monolithic bayesian posterior inference, bayesian spns, neural network architecture validation

arXiv:1905.11058 (Published 2019-05-27)

LAW: Learning to Auto Weight

Zhenmao Li, Yichao Wu, Ken Chen, Yudong WU, Shunfeng Zhou, Jiaheng Liu, Junjie Yan

Categories: cs.LG, cs.CV

Keywords: auto weight, origin cifar dataset, novel example weighting framework, experimental results demonstrate, weighting policy

arXiv:1905.10994 (Published 2019-05-27)

ODE$^2$VAE: Deep generative second order ODEs with Bayesian neural networks

Çağatay Yıldız, Markus Heinonen, Harri Lähdesmäki

Categories: stat.ML, cs.LG

Keywords: deep generative second order odes, bayesian neural networks, complex continuous-time latent dynamics, differential equation variational auto-encoder, second order ode model

arXiv:1905.11192 (Published 2019-05-27)

The Chan-Vese Model with Elastica and Landmark Constraints for Image Segmentation

Jintao Song, Huizhu Pan, Wuanquan Liu, Zhenkuan Pan

Categories: cs.CV

Keywords: image segmentation, landmark constraints, chan-vese model, variational level set model, simple gauss-seidel iterative method

arXiv:1905.11911 (Published 2019-05-28)

Controlling Neural Level Sets

Matan Atzmon, Niv Haim, Lior Yariv, Ofer Israelov, Haggai Maron, Yaron Lipman

Categories: cs.LG, stat.ML

Keywords: controlling neural level sets, neural networks represent fundamental properties, produce high fidelity surfaces, model non-linear manifold data, surface reconstruction

arXiv:1905.11926 (Published 2019-05-28)

Network Deconvolution

Chengxi Ye et al.

Categories: cs.LG, cs.CV, cs.NE, stat.ML

Keywords: network deconvolution, achieve better convergence rates, imagenet standard benchmark, convolutional neural networks, model weights

arXiv:1905.12385 (Published 2019-05-29)

The spiked matrix model with generative priors

Benjamin Aubin, Bruno Loureiro, Antoine Maillard, Florent Krzakala, Lenka Zdeborová

Categories: math.ST, cs.LG, eess.SP, math.PR, stat.ML, stat.TH

Keywords: generative priors, sparsity assumption, design enhanced spectral algorithms, generative models, reach optimal performance

arXiv:1905.12082 (Published 2019-05-28)

Memory Integrity of CNNs for Cross-Dataset Facial Expression Recognition

Dylan C. Tannugi, Alceu S. Britto Jr., Alessandro L. Koerich

Categories: cs.CV

Keywords: cross-dataset facial expression recognition, memory integrity, target dataset, fully connected layers, convolutional neural networks

arXiv:1905.12512 (Published 2019-05-29)

Smooth Shells: Multi-Scale Shape Registration with Functional Maps

Marvin Eisenberger, Zorah Lähner, Daniel Cremers

Categories: cs.CV, cs.GR

Keywords: smooth shells, multi-scale shape registration, functional maps, novel 3d shape correspondence method, markov chain monte carlo initialization

arXiv:1905.12731 (Published 2019-05-29)

Protecting quantum entanglement from qubit errors and leakage via repetitive parity measurements

C. C. Bultink et al.

Categories: quant-ph

Keywords: repetitive parity measurements, protecting quantum entanglement, qubit errors, leakage affects leading experimental platforms, entangled states

arXiv:1905.12964 (Published 2019-05-30)

A bialternant formula for odd symplectic characters and its application

Soichi Okada

Categories: math.CO

Subjects: 05E05

Keywords: bialternant formula, application, odd symplectic character identity, linear algebraic proof, odd symplectic groups

arXiv:1905.12665 (Published 2019-05-29)

Graph Learning Network: A Structure Learning Algorithm

Darwin Saire Pilco, Adín Ramírez Rivera

Categories: cs.LG, stat.ML

Keywords: graph learning network, structure learning algorithm, learn node embeddings, structure prediction functions, graph neural networks

arXiv:1905.12723 (Published 2019-05-29)

Extending Monocular Visual Odometry to Stereo Camera System by Scale Optimization

Jiawei Mo, Junaed Sattar

Categories: cs.CV

Keywords: extending monocular visual odometry, stereo camera system, enables stereo visual odometry, scale optimization enables stereo, optimization enables stereo visual

arXiv:1905.12660 (Published 2019-05-29)

Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators

Daniel Stoller, Sebastian Ewert, Simon Dixon

Categories: cs.LG, stat.ML

Keywords: training generative adversarial networks, incomplete observations, factorised discriminators, modularisation facilitates incorporating prior knowledge, image generation

Tags: github project

arXiv:1905.12681 (Published 2019-05-29)

What Makes Training Multi-Modal Networks Hard?

Weiyao Wang, Du Tran, Matt Feiszli

Categories: cs.CV, cs.LG

Keywords: training multi-modal networks hard, best single-modal network, single optimization strategy, multiple input modalities, gradient blending outperforms widely-used baselines

arXiv Analytics

ArticlesViews Reviews Comments Bookmarks Readers Ratings Score

Date Range

A lower bound for the partition function from Chebyshev's inequality applied to a coin flipping model for the random partition

Noncommutative LR coefficients and crystal reflection operators

Generalized $q,t$-Catalan numbers

Unsupervised Single Image Underwater Depth Estimation

What is the relationship between face alignment and facial expression recognition?

Bayesian Learning of Sum-Product Networks

LAW: Learning to Auto Weight

ODE$^2$VAE: Deep generative second order ODEs with Bayesian neural networks

The Chan-Vese Model with Elastica and Landmark Constraints for Image Segmentation

Controlling Neural Level Sets

Network Deconvolution

The spiked matrix model with generative priors

Memory Integrity of CNNs for Cross-Dataset Facial Expression Recognition

Smooth Shells: Multi-Scale Shape Registration with Functional Maps

Protecting quantum entanglement from qubit errors and leakage via repetitive parity measurements

A bialternant formula for odd symplectic characters and its application

Graph Learning Network: A Structure Learning Algorithm

Extending Monocular Visual Odometry to Stereo Camera System by Scale Optimization

Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators

What Makes Training Multi-Modal Networks Hard?

ArticlesViewsReviewsCommentsBookmarksReadersRatingsScore

Date Range

A lower bound for the partition function from Chebyshev's inequality applied to a coin flipping model for the random partition

Noncommutative LR coefficients and crystal reflection operators

Generalized $q,t$-Catalan numbers

Unsupervised Single Image Underwater Depth Estimation

What is the relationship between face alignment and facial expression recognition?

Bayesian Learning of Sum-Product Networks

LAW: Learning to Auto Weight

ODE$^2$VAE: Deep generative second order ODEs with Bayesian neural networks

The Chan-Vese Model with Elastica and Landmark Constraints for Image Segmentation

Controlling Neural Level Sets

Network Deconvolution

The spiked matrix model with generative priors

Memory Integrity of CNNs for Cross-Dataset Facial Expression Recognition

Smooth Shells: Multi-Scale Shape Registration with Functional Maps

Protecting quantum entanglement from qubit errors and leakage via repetitive parity measurements

A bialternant formula for odd symplectic characters and its application

Graph Learning Network: A Structure Learning Algorithm

Extending Monocular Visual Odometry to Stereo Camera System by Scale Optimization

Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators

What Makes Training Multi-Modal Networks Hard?

ArticlesViews Reviews Comments Bookmarks Readers Ratings Score