• Publications
  • Influence
OpenFace: An open source facial behavior analysis toolkit
TLDR
We present OpenFace - an open source tool intended for computer vision and machine learning researchers, affective computing community and people interested in building interactive applications based on facial behavior analysis. Expand
  • 732
  • 117
  • PDF
Hidden Conditional Random Fields
TLDR
We present a discriminative latent variable model for classification problems in structured domains where inputs can be represented by a graph of local observations. Expand
  • 552
  • 98
  • PDF
OpenFace 2.0: Facial Behavior Analysis Toolkit
TLDR
We present OpenFace 2.0 - a tool intended for computer vision and machine learning researchers, affective computing community and people interested in building interactive applications based on facial behavior analysis. Expand
  • 332
  • 61
  • PDF
Latent-Dynamic Discriminative Models for Continuous Gesture Recognition
TLDR
In this paper, we develop a discriminative framework for simultaneous sequence segmentation and labeling which can capture both intrinsic and extrinsic class dynamics. Expand
  • 395
  • 57
  • PDF
Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph
TLDR
We introduce CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI), the largest dataset of sentiment analysis and emotion recognition to date. Expand
  • 129
  • 46
  • PDF
Multimodal Machine Learning: A Survey and Taxonomy
TLDR
We identify and explore five core technical challenges (and related sub-challenges) surrounding multimodal machine learning. Expand
  • 603
  • 44
  • PDF
3D Constrained Local Model for rigid and non-rigid facial tracking
TLDR
We present 3D Constrained Local Model (CLM-Z) for robust facial feature tracking under varying pose. Expand
  • 268
  • 44
  • PDF
Speaker-Follower Models for Vision-and-Language Navigation
TLDR
We propose an approach to vision-and-language navigation that addresses both these issues with an embedded speaker model and a panoramic action space. Expand
  • 123
  • 44
  • PDF
Context-Dependent Sentiment Analysis in User-Generated Videos
TLDR
We propose a LSTM-based model that enables utterances to capture contextual information from their surroundings in the same video, thus aiding the classification process. Expand
  • 243
  • 43
  • PDF
Tensor Fusion Network for Multimodal Sentiment Analysis
TLDR
We introduce a novel model, termed Tensor Fusion Network, which learns both intra- and inter-modality dynamics end-to-end for multimodal sentiment analysis. Expand
  • 252
  • 41
  • PDF