arXiv subjects

Louis-Philippe Morency

Publications and source records attributed to Louis-Philippe Morency.

At least 127 records · Page 7Linked to original sources

arXiv2018

Visual Referring Expression Recognition: What Do Systems Actually Learn?

We present an empirical analysis of the state-of-the-art systems for referring expression recognition -- the task of identifying the object in an image referred to by a natural language expression -- with the goal of gaining insight into how these systems reason about language and vision. Surprisingly, we find strong evidence that even sophisticated and linguistically-motivated models for this task may ignore the linguistic structure, instead relying on shallow correlations introduced by unintended biases in the data selection and annotation process. For example, we show that a system trained and tested on the input image $\textit{without the input referring expression}$ can achieve a precision of 71.2% in top-2 predictions. Furthermore, a system that predicts only the object category given the input can achieve a precision of 84.2% in top-2 predictions. These surprisingly positive results for what should be deficient prediction scenarios suggest that careful analysis of what our models are learning -- and further, how our data is constructed -- is critical as we seek to make substantive progress on grounded language tasks.

cs.CL↗

arXiv2018

Using Syntax to Ground Referring Expressions in Natural Images

We introduce GroundNet, a neural network for referring expression recognition -- the task of localizing (or grounding) in an image the object referred to by a natural language expression. Our approach to this task is the first to rely on a syntactic analysis of the input referring expression in order to inform the structure of the computation graph. Given a parse tree for an input expression, we explicitly map the syntactic constituents and relationships present in the tree to a composed graph of neural modules that defines our architecture for performing localization. This syntax-based approach aids localization of \textit{both} the target object and auxiliary supporting objects mentioned in the expression. As a result, GroundNet is more interpretable than previous methods: we can (1) determine which phrase of the referring expression points to which object in the image and (2) track how the localization of the target object is determined by the network. We study this property empirically by introducing a new set of annotations on the GoogleRef dataset to evaluate localization of supporting objects. Our experiments show that GroundNet achieves state-of-the-art accuracy in identifying supporting objects, while maintaining comparable performance in the localization of target objects.

cs.CV↗

arXiv2018

Video Analysis for Body-worn Cameras in Law Enforcement

The social conventions and expectations around the appropriate use of imaging and video has been transformed by the availability of video cameras in our pockets. The impact on law enforcement can easily be seen by watching the nightly news; more and more arrests, interventions, or even routine stops are being caught on cell phones or surveillance video, with both positive and negative consequences. This proliferation of the use of video has led law enforcement to look at the potential benefits of incorporating video capture systematically in their day to day operations. At the same time, recognition of the inevitability of widespread use of video for police operations has caused a rush to deploy all types of cameras, including body worn cameras. However, the vast majority of police agencies have limited experience in utilizing video to its full advantage, and thus do not have the capability to fully realize the value of expanding their video capabilities. In this white paper, we highlight some of the technology needs and challenges of body-worn cameras, and we relate these needs to the relevant state of the art in computer vision and multimedia research. We conclude with a set of recommendations.

cs.CY↗

arXiv2018

Multi-attention Recurrent Network for Human Communication Comprehension

Human face-to-face communication is a complex multimodal signal. We use words (language modality), gestures (vision modality) and changes in tone (acoustic modality) to convey our intentions. Humans easily process and understand face-to-face communication, however, comprehending this form of communication remains a significant challenge for Artificial Intelligence (AI). AI must understand each modality and the interactions between them that shape human communication. In this paper, we present a novel neural architecture for understanding human communication called the Multi-attention Recurrent Network (MARN). The main strength of our model comes from discovering interactions between modalities through time using a neural component called the Multi-attention Block (MAB) and storing them in the hybrid memory of a recurrent component called the Long-short Term Hybrid Memory (LSTHM). We perform extensive comparisons on six publicly available datasets for multimodal sentiment analysis, speaker trait recognition and emotion recognition. MARN shows state-of-the-art performance on all the datasets.

cs.AI↗

arXiv2018

Multimodal Sentiment Analysis with Word-Level Fusion and Reinforcement Learning

With the increasing popularity of video sharing websites such as YouTube and Facebook, multimodal sentiment analysis has received increasing attention from the scientific community. Contrary to previous works in multimodal sentiment analysis which focus on holistic information in speech segments such as bag of words representations and average facial expression intensity, we develop a novel deep architecture for multimodal sentiment analysis that performs modality fusion at the word level. In this paper, we propose the Gated Multimodal Embedding LSTM with Temporal Attention (GME-LSTM(A)) model that is composed of 2 modules. The Gated Multimodal Embedding alleviates the difficulties of fusion when there are noisy modalities. The LSTM with Temporal Attention performs word level fusion at a finer fusion resolution between input modalities and attends to the most important time steps. As a result, the GME-LSTM(A) is able to better model the multimodal structure of speech through time and perform better sentiment comprehension. We demonstrate the effectiveness of this approach on the publicly-available Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis (CMU-MOSI) dataset by achieving state-of-the-art sentiment classification and regression results. Qualitative analysis on our model emphasizes the importance of the Temporal Attention Layer in sentiment prediction because the additional acoustic and visual modalities are noisy. We also demonstrate the effectiveness of the Gated Multimodal Embedding in selectively filtering these noisy modalities out. Our results and analysis open new areas in the study of sentiment analysis in human communication and provide new models for multimodal fusion.

cs.LG↗

arXiv2018

Memory Fusion Network for Multi-view Sequential Learning

Multi-view sequential learning is a fundamental problem in machine learning dealing with multi-view sequences. In a multi-view sequence, there exists two forms of interactions between different views: view-specific interactions and cross-view interactions. In this paper, we present a new neural architecture for multi-view sequential learning called the Memory Fusion Network (MFN) that explicitly accounts for both interactions in a neural architecture and continuously models them through time. The first component of the MFN is called the System of LSTMs, where view-specific interactions are learned in isolation through assigning an LSTM function to each view. The cross-view interactions are then identified using a special attention mechanism called the Delta-memory Attention Network (DMAN) and summarized through time with a Multi-view Gated Memory. Through extensive experimentation, MFN is compared to various proposed approaches for multi-view sequential learning on multiple publicly available benchmark datasets. MFN outperforms all the existing multi-view approaches. Furthermore, MFN outperforms all current state-of-the-art models, setting new state-of-the-art results for these multi-view datasets.

cs.LG↗

arXiv2017

Lattice Recurrent Unit: Improving Convergence and Statistical Efficiency for Sequence Modeling

Recurrent neural networks have shown remarkable success in modeling sequences. However low resource situations still adversely affect the generalizability of these models. We introduce a new family of models, called Lattice Recurrent Units (LRU), to address the challenge of learning deep multi-layer recurrent models with limited resources. LRU models achieve this goal by creating distinct (but coupled) flow of information inside the units: a first flow along time dimension and a second flow along depth dimension. It also offers a symmetry in how information can flow horizontally and vertically. We analyze the effects of decoupling three different components of our LRU model: Reset Gate, Update Gate and Projected State. We evaluate this family on new LRU models on computational convergence rates and statistical efficiency. Our experiments are performed on four publicly-available datasets, comparing with Grid-LSTM and Recurrent Highway networks. Our results show that LRU has better empirical computational convergence rates and statistical efficiency values, along with learning more accurate language models.

cs.LG↗

arXiv2017

Multimodal Machine Learning: A Survey and Taxonomy

Our experience of the world is multimodal - we see objects, hear sounds, feel texture, smell odors, and taste flavors. Modality refers to the way in which something happens or is experienced and a research problem is characterized as multimodal when it includes multiple such modalities. In order for Artificial Intelligence to make progress in understanding the world around us, it needs to be able to interpret such multimodal signals together. Multimodal machine learning aims to build models that can process and relate information from multiple modalities. It is a vibrant multi-disciplinary field of increasing importance and with extraordinary potential. Instead of focusing on specific multimodal applications, this paper surveys the recent advances in multimodal machine learning itself and presents them in a common taxonomy. We go beyond the typical early and late fusion categorization and identify broader challenges that are faced by multimodal machine learning, namely: representation, translation, alignment, fusion, and co-learning. This new taxonomy will enable researchers to better understand the state of the field and identify directions for future research.

cs.LG↗

arXiv2017

Convolutional Experts Constrained Local Model for Facial Landmark Detection

Constrained Local Models (CLMs) are a well-established family of methods for facial landmark detection. However, they have recently fallen out of favor to cascaded regression-based approaches. This is in part due to the inability of existing CLM local detectors to model the very complex individual landmark appearance that is affected by expression, illumination, facial hair, makeup, and accessories. In our work, we present a novel local detector -- Convolutional Experts Network (CEN) -- that brings together the advantages of neural architectures and mixtures of experts in an end-to-end framework. We further propose a Convolutional Experts Constrained Local Model (CE-CLM) algorithm that uses CEN as local detectors. We demonstrate that our proposed CE-CLM algorithm outperforms competitive state-of-the-art baselines for facial landmark detection by a large margin on four publicly-available datasets. Our approach is especially accurate and robust on challenging profile images.

cs.CV↗

arXiv2017

Tensor Fusion Network for Multimodal Sentiment Analysis

Multimodal sentiment analysis is an increasingly popular research area, which extends the conventional language-based definition of sentiment analysis to a multimodal setup where other relevant modalities accompany language. In this paper, we pose the problem of multimodal sentiment analysis as modeling intra-modality and inter-modality dynamics. We introduce a novel model, termed Tensor Fusion Network, which learns both such dynamics end-to-end. The proposed approach is tailored for the volatile nature of spoken language in online videos as well as accompanying gestures and voice. In the experiments, our model outperforms state-of-the-art approaches for both multimodal and unimodal sentiment analysis.

cs.CL↗

arXiv2017

Preserving Intermediate Objectives: One Simple Trick to Improve Learning for Hierarchical Models

Hierarchical models are utilized in a wide variety of problems which are characterized by task hierarchies, where predictions on smaller subtasks are useful for trying to predict a final task. Typically, neural networks are first trained for the subtasks, and the predictions of these networks are subsequently used as additional features when training a model and doing inference for a final task. In this work, we focus on improving learning for such hierarchical models and demonstrate our method on the task of speaker trait prediction. Speaker trait prediction aims to computationally identify which personality traits a speaker might be perceived to have, and has been of great interest to both the Artificial Intelligence and Social Science communities. Persuasiveness prediction in particular has been of interest, as persuasive speakers have a large amount of influence on our thoughts, opinions and beliefs. In this work, we examine how leveraging the relationship between related speaker traits in a hierarchical structure can help improve our ability to predict how persuasive a speaker is. We present a novel algorithm that allows us to backpropagate through this hierarchy. This hierarchical model achieves a 25% relative error reduction in classification accuracy over current state-of-the art methods on the publicly available POM dataset.

cs.LG↗

arXiv2017

Combating Human Trafficking with Deep Multimodal Models

Human trafficking is a global epidemic affecting millions of people across the planet. Sex trafficking, the dominant form of human trafficking, has seen a significant rise mostly due to the abundance of escort websites, where human traffickers can openly advertise among at-will escort advertisements. In this paper, we take a major step in the automatic detection of advertisements suspected to pertain to human trafficking. We present a novel dataset called Trafficking-10k, with more than 10,000 advertisements annotated for this task. The dataset contains two sources of information per advertisement: text and images. For the accurate detection of trafficking advertisements, we designed and trained a deep multimodal model called the Human Trafficking Deep Network (HTDN).

cs.CL↗

arXiv2017

GazeDirector: Fully Articulated Eye Gaze Redirection in Video

We present GazeDirector, a new approach for eye gaze redirection that uses model-fitting. Our method first tracks the eyes by fitting a multi-part eye region model to video frames using analysis-by-synthesis, thereby recovering eye region shape, texture, pose, and gaze simultaneously. It then redirects gaze by 1) warping the eyelids from the original image using a model-derived flow field, and 2) rendering and compositing synthesized 3D eyeballs onto the output image in a photorealistic manner. GazeDirector allows us to change where people are looking without person-specific training data, and with full articulation, i.e. we can precisely specify new gaze directions in 3D. Quantitatively, we evaluate both model-fitting and gaze synthesis, with experiments for gaze estimation and redirection on the Columbia gaze dataset. Qualitatively, we compare GazeDirector against recent work on gaze redirection, showing better results especially for large redirection angles. Finally, we demonstrate gaze redirection on YouTube videos by introducing new 3D gaze targets and by manipulating visual behavior.

cs.CV↗

arXiv2017

Affect-LM: A Neural Language Model for Customizable Affective Text Generation

Human verbal communication includes affective messages which are conveyed through use of emotionally colored words. There has been a lot of research in this direction but the problem of integrating state-of-the-art neural language models with affective information remains an area ripe for exploration. In this paper, we propose an extension to an LSTM (Long Short-Term Memory) language model for generating conversational text, conditioned on affect categories. Our proposed model, Affect-LM enables us to customize the degree of emotional content in generated sentences through an additional design parameter. Perception studies conducted using Amazon Mechanical Turk show that Affect-LM generates naturally looking emotional sentences without sacrificing grammatical correctness. Affect-LM also learns affect-discriminative word representations, and perplexity experiments show that additional affective information in conversational text can improve language model prediction.

cs.CL↗

arXiv2017

Temporal Attention-Gated Model for Robust Sequence Classification

Typical techniques for sequence classification are designed for well-segmented sequences which have been edited to remove noisy or irrelevant parts. Therefore, such methods cannot be easily applied on noisy sequences expected in real-world applications. In this paper, we present the Temporal Attention-Gated Model (TAGM) which integrates ideas from attention models and gated recurrent networks to better deal with noisy or unsegmented sequences. Specifically, we extend the concept of attention model to measure the relevance of each observation (time step) of a sequence. We then use a novel gated recurrent network to learn the hidden representation for the final prediction. An important advantage of our approach is interpretability since the temporal attention weights provide a meaningful value for the salience of each time step in the sequence. We demonstrate the merits of our TAGM approach, both for prediction accuracy and interpretability, on three different tasks: spoken digit recognition, text-based sentiment analysis and visual event recognition.

cs.CV↗

arXiv2017

Select-Additive Learning: Improving Generalization in Multimodal Sentiment Analysis

Multimodal sentiment analysis is drawing an increasing amount of attention these days. It enables mining of opinions in video reviews which are now available aplenty on online platforms. However, multimodal sentiment analysis has only a few high-quality data sets annotated for training machine learning algorithms. These limited resources restrict the generalizability of models, where, for example, the unique characteristics of a few speakers (e.g., wearing glasses) may become a confounding factor for the sentiment classification task. In this paper, we propose a Select-Additive Learning (SAL) procedure that improves the generalizability of trained neural networks for multimodal sentiment analysis. In our experiments, we show that our SAL approach improves prediction accuracy significantly in all three modalities (verbal, acoustic, visual), as well as in their fusion. Our results show that SAL, even when trained on one dataset, achieves good generalization across two new test datasets.

cs.CL↗

arXiv2017

Deducing the severity of psychiatric symptoms from the human voice

Psychiatric illnesses are often associated with multiple symptoms, whose severity must be graded for accurate diagnosis and treatment. This grading is usually done by trained clinicians based on human observations and judgments made within doctor-patient sessions. Current research provides sufficient reason to expect that the human voice may carry biomarkers or signatures of many, if not all, these symptoms. Based on this conjecture, we explore the possibility of objectively and automatically grading the symptoms of psychiatric illnesses with reference to various standard psychiatric rating scales. Using acoustic data from several clinician-patient interviews within hospital settings, we use non-parametric models to learn and predict the relations between symptom-ratings and voice. In the process, we show that different articulatory-phonetic units of speech are able to capture the effects of different symptoms differently, and use this to establish a plausible methodology that could be employed for automatically grading psychiatric symptoms for clinical purposes.

cs.SD↗

arXiv2016

Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networks

Curriculum Learning emphasizes the order of training instances in a computational learning setup. The core hypothesis is that simpler instances should be learned early as building blocks to learn more complex ones. Despite its usefulness, it is still unknown how exactly the internal representation of models are affected by curriculum learning. In this paper, we study the effect of curriculum learning on Long Short-Term Memory (LSTM) networks, which have shown strong competency in many Natural Language Processing (NLP) problems. Our experiments on sentiment analysis task and a synthetic task similar to sequence prediction tasks in NLP show that curriculum learning has a positive effect on the LSTM's internal states by biasing the model towards building constructive representations i.e. the internal representation at the previous timesteps are used as building blocks for the final prediction. We also find that smaller models significantly improves when they are trained with curriculum learning. Lastly, we show that curriculum learning helps more when the amount of training data is limited.

cs.CL↗