Our new oral at ICCV’19 now has a presentation & video:
Deep Cooking: Predicting Relative Food Ingredient Amounts from Images
This is a joint work by Jiatong Li, Ricardo Guerrero and Vladimir Pavlovic. The paper is accepted by the 5th International Workshop on Multimedia Assisted Dietary Management (MADiMa), ACM International Conference on Multimedia (ACMMM2019).

Abstract
In this paper, we study … Read the rest
Task-Discriminative Domain Alignment for Unsupervised Domain Adaptation
This is a joint work by Behnam Gholami, Pritish Sahu, Minyoung Kim, Vladimir Pavlovic
Our new paper on Domain Adaptation was accepted in Multi-Discipline Approach for Learning Concepts – Zero-Shot, One-Shot, Few-Shot, and Beyond and Beyond Workshop in conjunction with ICCV 2019.

Abstract
… Read the restUnsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach
This is a joint work by Behnam Gholami, Pritish Sahu, Ognjen Rudovic, Konstantinos Bousmalis, Vladimir Pavlovic

Abstract
Unsupervised domain adaptation (uDA) models focus on pairwise adaptation settings where there is a single, labeled, source and a single target domain. However, in many real-world settings … Read the rest
Fast Adaptation of Deep Models for Facial Action Unit Detection Using Model-Agnostic Meta-Learning
Mihee Lee, Ognjen (Oggi) Rudovic, Vladimir Pavlovic, and Maja Pantic


Abstract
Detecting facial action units (AU) is one of the fundamental steps in automatic recognition of facial expression of emotions and cognitive states. Though there have been a variety of … Read the rest
Relevance Factor VAE: Learning and Identifying Disentangled Factors
Minyoung Kim, Yuting Wang, Pritish Sahu, and Vladimir Pavlovic.

Abstract
We propose a novel VAE-based deep auto- encoder model that can learn disentangled latent representations in a fully unsupervised manner, endowed with the ability to identify all … Read the rest
Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network
Hai X. Pham, Yuting Wang & Vladimir Pavlovic.

Abstract
This paper presents Generative Adversarial Talking Head, a novel deep generative neural network that enables fully automatic facial expression synthesis of an arbitrary portrait with continuous action unit (AU) coefficients. … Read the rest
End-to-end Learning for 3D Facial Animation from Speech, ICMI 2018
This is a joint work by Hai Xuan Pham, Yuting Wang, and Vladimir Pavlovic. The paper was accepted by the 20th ACM International Conference on Multimodal Interaction.

Abstract
We present a deep learning framework for real-time speech-driven 3D facial animation … Read the rest
Scenario Generalization of Data-driven Imitation Models in Crowd Simulation, MIG2019
Our new paper on crowd simulation was accepted by ACM SIGGRAPH Conference on Motion, Interaction and Games 2019. Congratulations to Gang!

ABSTRACT
Crowd simulation, the study of the movement of multiple agents in complex environments, presents a unique application domain for … Read the rest
Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement – ICCV’19 Oral
Our new paper on Bayesian representation learning was accepted as Oral at ICCV 2019. Congratulations to Minyoung, Yuting, and Pritish!
Abstract
We propose a family of novel hierarchical Bayesian deep auto-encoder models capable of identifying disentangled factors of variability in … Read the rest