Skip to search formSkip to main contentSkip to account menu

FitNets: Hints for Thin Deep Nets

This paper extends the idea of a student network that could imitate the soft output of a larger teacher network or ensemble of networks, using not only the outputs but also the intermediate representations learned by the teacher as hints to improve the training process and final performance of the student.
View PDF on arXiv (opens in a new tab)

The “Something Something” Video Database for Learning and Evaluating Visual Common Sense

This work describes the ongoing collection of the “something-something” database of video prediction tasks whose solutions require a common sense understanding of the depicted situation, and describes the challenges in crowd-sourcing this data at scale.
View on IEEE (opens in a new tab)

Theano: A Python framework for fast computation of mathematical expressions

The performance of Theano is compared against Torch7 and TensorFlow on several machine learning models and recently-introduced functionalities and improvements are discussed.
View PDF on arXiv (opens in a new tab)

Towards Deep Conversational Recommendations

This paper collects ReDial, a data set consisting of over 10,000 conversations centered around the theme of providing movie recommendations and uses this dataset to explore new neural architectures, mechanisms and methods suitable for composing conversational recommendation systems.
View PDF on arXiv (opens in a new tab)

FigureQA: An Annotated Figure Dataset for Visual Reasoning

FigureQA is envisioned as a first step towards developing models that can intuitively recognize patterns from visual representations of data, and preliminary results indicate that the task poses a significant machine learning challenge.
View PDF on arXiv (opens in a new tab)

Combining modality specific deep neural networks for emotion recognition in video

In this paper we present the techniques used for the University of Montréal's team submissions to the 2013 Emotion Recognition in the Wild Challenge. The challenge is to classify the emotions…
View on ACM (opens in a new tab)

ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events

This work presents a multichannel spatiotemporal CNN architecture for semi-supervised bounding box prediction and exploratory data analysis, and demonstrates that this approach is able to leverage temporal information and unlabeled data to improve the localization of extreme weather events.
View Paper (opens in a new tab)

Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction

This work presents a recurrent image generation model which takes into account both the generated output up to the current step as well as all past instructions for generation, and shows that the model is able to generate the background, add new objects, and apply simple transformations to existing objects.
View on IEEE (opens in a new tab)

Recurrent Neural Networks for Emotion Recognition in Video

This work focuses its presentation and experimental analysis on a hybrid CNN-RNN architecture for facial expression analysis that can outperform a previously applied CNN approach using temporal averaging for aggregation.
View on ACM (opens in a new tab)

Do Deep Convolutional Nets Really Need to be Deep and Convolutional?

Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation…
View Paper (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)