Open AccessProceedings Article
Multimodal Deep Learning
Jiquan Ngiam,Aditya Khosla,Mingyu Kim,Juhan Nam,Honglak Lee,Andrew Y. Ng +5 more
- pp 689-696
Reads0
Chats0
TLDR
This work presents a series of tasks for multimodal learning and shows how to train deep networks that learn features to address these tasks, and demonstrates cross modality feature learning, where better features for one modality can be learned if multiple modalities are present at feature learning time.Abstract:
Deep networks have been successfully applied to unsupervised feature learning for single modalities (e.g., text, images or audio). In this work, we propose a novel application of deep networks to learn features over multiple modalities. We present a series of tasks for multimodal learning and show how to train deep networks that learn features to address these tasks. In particular, we demonstrate cross modality feature learning, where better features for one modality (e.g., video) can be learned if multiple modalities (e.g., audio and video) are present at feature learning time. Furthermore, we show how to learn a shared representation between modalities and evaluate it on a unique task, where the classifier is trained with audio-only data but tested with video-only data and vice-versa. Our models are validated on the CUAVE and AVLetters datasets on audio-visual speech classification, demonstrating best published visual speech classification on AVLetters and effective shared representation learning.read more
Citations
More filters
Journal ArticleDOI
Multitask Representation Learning for Multimodal Estimation of Depression Level
TL;DR: In this paper, a multitask learning attention-based deep neural network model was proposed to classify the level of depression in the Wizard of Oz interview corpus, where acoustic, textual, and visual modalities were used to train the network.
Proceedings ArticleDOI
Procedural Modeling Using Autoencoder Networks
TL;DR: This work proposes a method to enable intuitive exploration of such high dimensional procedural modeling spaces within a lower dimensional space learned through autoencoder network training, and structuring the learned lowerdimensional space for continuous exploration with respect to shape features.
Journal ArticleDOI
Role of machine learning in medical research: A survey
Arunim Garg,Vijay Mago +1 more
TL;DR: This literature review identifies a clear shift of artificial intelligence techniques used in the medical domain, with deep learning methods taking precedence over machine learning methods.
Posted Content
Transfer Learning for Speech and Language Processing
Dong Wang,Thomas Fang Zheng +1 more
TL;DR: Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks as discussed by the authors, and is traditionally studied in the name of ''model adaptation'' in the context of cross-lingual learning.
Posted Content
Multimodal Generative Models for Scalable Weakly-Supervised Learning
Mike Wu,Noah D. Goodman +1 more
TL;DR: In this article, a multimodal variational autoencoder (MVAE) was proposed to solve the multi-modal inference problem by using a product-of-experts inference network and a sub-sampled training paradigm.
References
More filters
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Journal ArticleDOI
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
Journal ArticleDOI
A fast learning algorithm for deep belief nets
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Proceedings ArticleDOI
Extracting and composing robust features with denoising autoencoders
TL;DR: This work introduces and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern.
Journal ArticleDOI
Hearing lips and seeing voices
Harry McGurk,John Macdonald +1 more
TL;DR: The study reported here demonstrates a previously unrecognised influence of vision upon speech perception, on being shown a film of a young woman's talking head in which repeated utterances of the syllable [ba] had been dubbed on to lip movements for [ga].