2020
phantom.png

Foundations of Multimodal Co-learning

Elsevier Information Fusion Journal (IF 11.21)

Amir Zadeh, Paul Pu Liang, Louis-Philippe Morency

MBERT.png

Multimodal Finetuning of Advanced Transformer Models

ACL Oral

Wasifur Rahman, Md Kamrul Hasan, Amir Zadeh, Sangwu Lee, Chengfeng Mao, Louis-Philippe Morency, Mohammed Ehsan Hoque

KL.jpg

Pseudo-Encoded Stochastic Variational Inference

Preprint

Amir Zadeh, Chengfeng Mao, Kelly Shi, Yiwei Zhang, Paul Pu Liang, Soujanya Poria, Louis-Philippe Morency

FMT.png

Factorized Multimodal Transformer for Multimodal Sequential Learning

Elsevier Information Fusion Journal (IF 11.21)

Amir Zadeh, Chengfeng Mao, Kelly Shi, Yiwei Zhang, Paul Pu Liang, Soujanya Poria, Louis-Philippe Morency

VAD.png

Variational Auto-Decoder: Neural Generative Modeling from Partial Data

Preprint

Amir Zadeh, Yao-Chong Lim, Paul Pu Liang, Louis-Philippe Morency

2019
SIQ.png

Social-IQ: A Question Answering Benchmark for Artificial Social Intelligence

CVPR Oral

Md Kamrul Hasan, Wasifur Rahman, Amir Zadeh, Jianyuan Zhong, Md Iftekhar Tanveer, Louis-Philippe Morency, Mohammed (Ehsan) Hoque

URFUNNY.png

UR-FUNNY: A Multimodal Language Dataset for Understanding Humor

EMNLP

Md Kamrul Hasan, Wasifur Rahman, Amir Zadeh, Jianyuan Zhong, Md Iftekhar Tanveer, Louis-Philippe Morency, Mohammed (Ehsan) Hoque

FMR.png

Learning Factorized Multimodal Representations

ICLR

Yao-Hung Hubert Tsai, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency, Ruslan Salakhutdinov

WCS.png

Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors

AAAI Spotlight

Yansen Wang, Ying Shen, Zhun Liu, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency

2018
Screen Shot 2020-02-14 at 11.30.07 PM.pn

Multimodal Language Analysis using Recurrent Multistage Fusion

EMNLP Oral

Paul Pu Liang, Ziyin Liu, Amir Zadeh, Louis-Philippe Morency

DFG

Human Multimodal Language in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Model

ACL Oral

Amir Zadeh, Paul Pu Liang, Jon Vanbriesen, Soujanya Poria, Edmund Tong, Erik Cambria, Louis-Philippe Morency

tensordecompose.jpg

Efficient Low-rank Multimodal Fusion With Modality-Specific Factors

ACL Oral

Zhun Liu, Ying Shen, Varun Lakshminarasimhan, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency

mfn.jpg

Memory Fusion Network for Multi-view Sequential Learning 

AAAI Oral

Amir Zadeh, Paul Liang, Navonil Mazumder, Soujanya Poria, Erik Cambria, Louis-Philippe Morency

marn.jpg

Multi-attention Recurrent Network for Human Communication Comprehension

AAAI Oral

Amir Zadeh, Paul Liang, Soujanya Poria, Erik Cambria, Prateek Vij, Louis-Philippe Morency

Screen Shot 2017-10-25 at 6.33.54 PM.png

OpenFace 2.0: Facial Behavior Analysis Toolkit

FG Oral

Tadas Baltrusaitis, Amir Zadeh, Yao-Chong Lim, Louis-Philippe Morency

cmn.jpg

MEMN: Multimodal Emotional Memory Network for Emotion Recognition in Dyadic Conversational Videos

NAACL

Devamanyu Hazarika, Soujanya Poria, Amir Zadeh, Erik Cambria, Louis-Philippe Morency, Roger Zimmerman

localglobal.jpg

Multimodal Local-Global Ranking Fusion for Emotion Recognition

ICMI

Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency

2017
TFN.jpg

Tensor Fusion Network for Multimodal Sentiment Analysis

EMNLP Oral

Amir Zadeh, Minghai Chen, Soujanya Poria, Erik Cambria, Louis-Philippe Morency

ctd.jpg

Context-Dependent Sentiment Analysis in User-Generated Videos

ACL Oral

Soujanya Poria, Erik Cambria, Navonil Mazumder, Amir Zadeh, Louis-Philippe Morency

trafic.jpg

Combatting Human Trafficking with Multimodal Deep Models 

ACL

Edmund Tong*, Amir Zadeh*, Cara Jones, Louis-Philippe Morency

ceclm.jpg

Convolutional Experts Constrained Local Models for Facial Landmark Detection

CVPR-w

Amir Zadeh, Tadas Baltrusaitis, Yao-Chong Lim Louis-Philippe Morency

wordl.jpg

Word-level Alignment with Reinforcement Learning for Multimodal Sentiment Analysis

ICMI Oral - Honorable Mention

Minghai Chen, Sen Wang, Paul Liang, Tadas Baltrusaitis, Amir Zadeh, Louis-Philippe Morency

catlstm.jpg

Multilevel Multiple Attentions for Contextual Multimodal Sentiment Analysis

ICDM Oral

Soujanya Poria, Erik Cambria, Devamanyu Hazarika, Navonil Mazumder, Amir Zadeh, Louis-Philippe Morency