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
RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach.
Xiaoyong Pan,Hong-Bin Shen +1 more
TL;DR: A deep learning-based framework by using a novel hybrid convolutional neural network and deep belief network to predict the RBP interaction sites and motifs on RNAs, which can achieve promising performance and easily capture interpretable binding motifs.
Proceedings ArticleDOI
Pedestrian Parsing via Deep Decompositional Network
TL;DR: Experimental results show that the proposed new Deep Decompositional Network achieves better segmentation accuracy than the state-of-the-art methods on pedestrian images with or without occlusions.
Posted Content
ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation
TL;DR: This paper proposes an attention based user behavior modeling framework called ATRank, which it mainly uses for recommendation tasks, and explores ATRank to use one unified model to predict different types of user behaviors at the same time, showing a comparable performance with the highly optimized individual models.
Proceedings ArticleDOI
Linking Image and Text with 2-Way Nets
Aviv Eisenschtat,Lior Wolf +1 more
TL;DR: In this paper, a bi-directional neural network architecture for matching vectors from two data sources is introduced, which employs two tied neural network channels that project the two views into a common, maximally correlated space using the Euclidean loss.
Proceedings ArticleDOI
Neural Survival Recommender
How Jing,Alexander J. Smola +1 more
TL;DR: This work presents a model based on Long-Short Term Memory to estimate when a user will return to a site and what their future listening behavior will be, and shows that the resulting multitask problem can be solved accurately, when applied to two real-world datasets.
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].