Improving Aspect-Level Sentiment Analysis with Aspect Extraction

May 03, 2020
Navonil Majumder, Rishabh Bhardwaj, Soujanya Poria, Amir Zadeh, Alexander Gelbukh, Amir Hussain, Louis-Philippe Morency

  Access Model/Code and Paper

Interpretable Multimodal Routing for Human Multimodal Language

Apr 29, 2020
Yao-Hung Hubert Tsai, Martin Q. Ma, Muqiao Yang, Ruslan Salakhutdinov, Louis-Philippe Morency

  Access Model/Code and Paper

Diverse and Admissible Trajectory Forecasting through Multimodal Context Understanding

Apr 03, 2020
Seong Hyeon Park, Gyubok Lee, Manoj Bhat, Jimin Seo, Minseok Kang, Jonathan Francis, Ashwin R. Jadhav, Paul Pu Liang, Louis-Philippe Morency

  Access Model/Code and Paper

On Emergent Communication in Competitive Multi-Agent Teams

Mar 04, 2020
Paul Pu Liang, Jeffrey Chen, Ruslan Salakhutdinov, Louis-Philippe Morency, Satwik Kottur

* AAMAS 2020 

  Access Model/Code and Paper

Learning Not to Learn in the Presence of Noisy Labels

Feb 16, 2020
Liu Ziyin, Blair Chen, Ru Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda

  Access Model/Code and Paper

Think Locally, Act Globally: Federated Learning with Local and Global Representations

Jan 06, 2020
Paul Pu Liang, Terrance Liu, Liu Ziyin, Ruslan Salakhutdinov, Louis-Philippe Morency

* Workshop on Federated Learning for Data Privacy and Confidentiality, NeurIPS 2019, Vancouver, Canada 

  Access Model/Code and Paper

Context-Dependent Models for Predicting and Characterizing Facial Expressiveness

Dec 10, 2019
Victoria Lin, Jeffrey M. Girard, Louis-Philippe Morency

  Access Model/Code and Paper

Factorized Multimodal Transformer for Multimodal Sequential Learning

Nov 22, 2019
Amir Zadeh, Chengfeng Mao, Kelly Shi, Yiwei Zhang, Paul Pu Liang, Soujanya Poria, Louis-Philippe Morency

  Access Model/Code and Paper

WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation

Nov 21, 2019
Amir Zadeh, Tianjun Ma, Soujanya Poria, Louis-Philippe Morency

  Access Model/Code and Paper

To React or not to React: End-to-End Visual Pose Forecasting for Personalized Avatar during Dyadic Conversations

Oct 05, 2019
Chaitanya Ahuja, Shugao Ma, Louis-Philippe Morency, Yaser Sheikh

  Access Model/Code and Paper

Transformer Dissection: An Unified Understanding for Transformer's Attention via the Lens of Kernel

Aug 30, 2019
Yao-Hung Hubert Tsai, Shaojie Bai, Makoto Yamada, Louis-Philippe Morency, Ruslan Salakhutdinov

* EMNLP 2019 

  Access Model/Code and Paper

M-BERT: Injecting Multimodal Information in the BERT Structure

Aug 15, 2019
Wasifur Rahman, Md Kamrul Hasan, Amir Zadeh, Louis-Philippe Morency, Mohammed Ehsan Hoque

  Access Model/Code and Paper

Language2Pose: Natural Language Grounded Pose Forecasting

Jul 02, 2019
Chaitanya Ahuja, Louis-Philippe Morency

  Access Model/Code and Paper

Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization

Jul 01, 2019
Paul Pu Liang, Zhun Liu, Yao-Hung Hubert Tsai, Qibin Zhao, Ruslan Salakhutdinov, Louis-Philippe Morency

  Access Model/Code and Paper

Deep Gamblers: Learning to Abstain with Portfolio Theory

Jun 29, 2019
Liu Ziyin, Zhikang Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda

  Access Model/Code and Paper

Multimodal Transformer for Unaligned Multimodal Language Sequences

Jun 01, 2019
Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J. Zico Kolter, Louis-Philippe Morency, Ruslan Salakhutdinov

  Access Model/Code and Paper

Strong and Simple Baselines for Multimodal Utterance Embeddings

May 14, 2019
Paul Pu Liang, Yao Chong Lim, Yao-Hung Hubert Tsai, Ruslan Salakhutdinov, Louis-Philippe Morency

* NAACL 2019 

  Access Model/Code and Paper

UR-FUNNY: A Multimodal Language Dataset for Understanding Humor

Apr 14, 2019
Md Kamrul Hasan, Wasifur Rahman, Amir Zadeh, Jianyuan Zhong, Md Iftekhar Tanveer, Louis-Philippe Morency, Mohammed, Hoque

  Access Model/Code and Paper

Variational Auto-Decoder

Apr 03, 2019
Amir Zadeh, Yao-Chong Lim, Paul Pu Liang, Louis-Philippe Morency

* Link to code and data available from https://github.com/A2Zadeh/Variational-Autodecoder 

  Access Model/Code and Paper

Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph

Mar 27, 2019
Yao-Hung Hubert Tsai, Santosh Divvala, Louis-Philippe Morency, Ruslan Salakhutdinov, Ali Farhadi

* CVPR 2019. Supplementary included. Fixing a small typo 

  Access Model/Code and Paper

Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities

Dec 19, 2018
Hai Pham, Paul Pu Liang, Thomas Manzini, Louis-Philippe Morency, Barnabas Poczos

* AAAI 2019 

  Access Model/Code and Paper

Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors

Nov 26, 2018
Yansen Wang, Ying Shen, Zhun Liu, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency

* Accepted by AAAI2019 

  Access Model/Code and Paper

Speaker-Follower Models for Vision-and-Language Navigation

Oct 27, 2018
Daniel Fried, Ronghang Hu, Volkan Cirik, Anna Rohrbach, Jacob Andreas, Louis-Philippe Morency, Taylor Berg-Kirkpatrick, Kate Saenko, Dan Klein, Trevor Darrell

* NIPS 2018 

  Access Model/Code and Paper

Multimodal Polynomial Fusion for Detecting Driver Distraction

Oct 24, 2018
Yulun Du, Chirag Raman, Alan W Black, Louis-Philippe Morency, Maxine Eskenazi

* INTERSPEECH 2018 

  Access Model/Code and Paper

Multimodal Language Analysis with Recurrent Multistage Fusion

Aug 12, 2018
Paul Pu Liang, Ziyin Liu, Amir Zadeh, Louis-Philippe Morency

* EMNLP 2018 

  Access Model/Code and Paper

Multimodal Local-Global Ranking Fusion for Emotion Recognition

Aug 12, 2018
Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency

* ACM International Conference on Multimodal Interaction (ICMI 2018) 

  Access Model/Code and Paper

Learning Factorized Multimodal Representations

Jun 16, 2018
Yao-Hung Hubert Tsai, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency, Ruslan Salakhutdinov

  Access Model/Code and Paper

Efficient Low-rank Multimodal Fusion with Modality-Specific Factors

May 31, 2018
Zhun Liu, Ying Shen, Varun Bharadhwaj Lakshminarasimhan, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency

* * Equal contribution. 10 pages. Accepted by ACL 2018 

  Access Model/Code and Paper

Visual Referring Expression Recognition: What Do Systems Actually Learn?

May 30, 2018
Volkan Cirik, Louis-Philippe Morency, Taylor Berg-Kirkpatrick

* NAACL2018 short 

  Access Model/Code and Paper