
Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach
Variational autoencoder (VAE) is a very successful generative model whos...
read it

CHEF: Crossmodal Hierarchical Embeddings for Food Domain Retrieval
Despite the abundance of multimodal data, such as imagetext pairs, the...
read it

PrivateShared Disentangled Multimodal VAE for Learning of Hybrid Latent Representations
Multimodal generative models represent an important family of deep mode...
read it

MPG: A Multiingredient Pizza Image Generator with Conditional StyleGANs
Multilabel conditional image generation is a challenging problem in comp...
read it

Crossmodal Retrieval and Synthesis (XMRS): Closing the modality gap in shared subspace
Computational food analysis (CFA), a broad set of methods that attempt t...
read it

Learning Disentangled Latent Factors from Paired Data in CrossModal Retrieval: An Implicit Identifiable VAE Approach
We deal with the problem of learning the underlying disentangled latent ...
read it

Recursive Inference for Variational Autoencoders
Inference networks of traditional Variational Autoencoders (VAEs) are ty...
read it

PicturetoAmount (PITA): Predicting Relative Ingredient Amounts from Food Images
Increased awareness of the impact of food consumption on health and life...
read it

OrdinalContent VAE: Isolating OrdinalValued Content Factors in Deep Latent Variable Models
In deep representational learning, it is often desired to isolate a part...
read it

CookGAN: Meal Image Synthesis from Ingredients
In this work we propose a new computational framework, based on generati...
read it

Deep CrowdFlow Prediction in Built Environments
Predicting the behavior of crowds in complex environments is a key requi...
read it

Scenario Generalization of Datadriven Imitation Models in Crowd Simulation
Crowd simulation, the study of the movement of multiple agents in comple...
read it

TaskDiscriminative Domain Alignment for Unsupervised Domain Adaptation
Domain Adaptation (DA), the process of effectively adapting task models ...
read it

Deep Cooking: Predicting Relative Food Ingredient Amounts from Images
In this paper, we study the novel problem of not only predicting ingredi...
read it

Fast and Effective Adaptation of Facial Action Unit Detection Deep Model
Detecting facial action units (AU) is one of the fundamental steps in au...
read it

BayesFactorVAE: Hierarchical Bayesian Deep AutoEncoder Models for Factor Disentanglement
We propose a family of novel hierarchical Bayesian deep autoencoder mod...
read it

Efficient Deep Gaussian Process Models for VariableSized Input
Deep Gaussian processes (DGP) have appealing Bayesian properties, can ha...
read it

The Art of Food: Meal Image Synthesis from Ingredients
In this work we propose a new computational framework, based on generati...
read it

Visibility Constrained Generative Model for Depthbased 3D Facial Pose Tracking
In this paper, we propose a generative framework that unifies depthbase...
read it

Unsupervised Visual Domain Adaptation: A Deep MaxMargin Gaussian Process Approach
In unsupervised domain adaptation, it is widely known that the target do...
read it

Relevance Factor VAE: Learning and Identifying Disentangled Factors
We propose a novel VAEbased deep autoencoder model that can learn dise...
read it

Unsupervised MultiTarget Domain Adaptation: An Information Theoretic Approach
Unsupervised domain adaptation (uDA) models focus on pairwise adaptation...
read it

Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network
This paper presents Generative Adversarial Talking Head (GATH), a novel ...
read it

The Role of Datadriven Priors in Multiagent Crowd Trajectory Estimation
Trajectory interpolation, the process of fillingin the gaps and removin...
read it

Endtoend Learning for 3D Facial Animation from Raw Waveforms of Speech
We present a deep learning framework for realtime speechdriven 3D faci...
read it

Unsupervised Domain Adaptation with Copula Models
We study the task of unsupervised domain adaptation, where no labeled da...
read it

Sketchbased Face Editing in Video Using Identity Deformation Transfer
We address the problem of using handdrawn sketch to edit facial identit...
read it

Robust TimeSeries Retrieval Using Probabilistic Adaptive Segmental Alignment
Traditional pairwise sequence alignment is based on matching individual ...
read it

Variablestate Latent Conditional Random Fields for Facial Expression Recognition and Action Unit Detection
Automated recognition of facial expressions of emotions, and detection o...
read it

Robust Performancedriven 3D Face Tracking in Long Range Depth Scenes
We introduce a novel robust hybrid 3D face tracking framework from RGBD ...
read it

Intrinsic Nonstationary Covariance Function for Climate Modeling
Designing a covariance function that represents the underlying correlati...
read it

DMFVI: Distributed Mean Field Variational Inference using Bregman ADMM
Bayesian models provide a framework for probabilistic modelling of compl...
read it

Gaussian Process for Noisy Inputs with Ordering Constraints
We study the Gaussian Process regression model in the context of trainin...
read it

Discovering Characteristic Landmarks on Ancient Coins using Convolutional Networks
In this paper, we propose a novel method to find characteristic landmark...
read it

MultiCue Structure Preserving MRF for Unconstrained Video Segmentation
Video segmentation is a stepping stone to understanding video context. V...
read it

Fast ADMM Algorithm for Distributed Optimization with Adaptive Penalty
We propose new methods to speed up convergence of the Alternating Direct...
read it

Variational Learning in MixedState Dynamic Graphical Models
Many realvalued stochastic timeseries are locally linear (Gassian), bu...
read it

Heteroscedastic Conditional Ordinal Random Fields for Pain Intensity Estimation from Facial Images
We propose a novel method for automatic pain intensity estimation from f...
read it

Learning Hypergraph Labeling for Feature Matching
This study poses the feature correspondence problem as a hypergraph node...
read it