150 citations · 832 across the 25 of their papers we have counts for
27 papers
Painter: Teaching Auto-regressive Language Models to Draw Sketches
Reza Pourreza, Apratim Bhattacharyya, Sunny Panchal +3
Large language models (LLMs) have made tremendous progress in natural language understanding and they have also been successfully adopted in other domains such as computer vision,…
Deductive Verification of Chain-of-Thought Reasoning
Zhan Ling, Yunhao Fang, Xuanlin Li +4
Large Language Models (LLMs) significantly benefit from Chain-of-Thought (CoT) prompting in performing various reasoning tasks. While CoT allows models to produce more comprehensiv…
Is end-to-end learning enough for fitness activity recognition?
Antoine Mercier, Guillaume Berger, Sunny Panchal +5
End-to-end learning has taken hold of many computer vision tasks, in particular, related to still images, with task-specific optimization yielding very strong performance. Neverthe…
Metaphors We Learn By
Roland Memisevic
Gradient based learning using error back-propagation (``backprop'') is a well-known contributor to much of the recent progress in AI. A less obvious, but arguably equally important…
Hierarchical Video Understanding
Farzaneh Mahdisoltani, Roland Memisevic, David Fleet
We introduce a hierarchical architecture for video understanding that exploits the structure of real world actions by capturing targets at different levels of granularity. We desig…
On the effectiveness of task granularity for transfer learning
Farzaneh Mahdisoltani, Guillaume Berger, Waseem Gharbieh +2
We describe a DNN for video classification and captioning, trained end-to-end, with shared features, to solve tasks at different levels of granularity, exploring the link between g…
The "something something" video database for learning and evaluating visual common sense
Raghav Goyal, Samira Ebrahimi Kahou, Vincent Michalski +11
Neural networks trained on datasets such as ImageNet have led to major advances in visual object classification. One obstacle that prevents networks from reasoning more deeply abou…
Incorporating long-range consistency in CNN-based texture generation
G. Berger, R. Memisevic
Gatys et al. (2015) showed that pair-wise products of features in a convolutional network are a very effective representation of image textures. We propose a simple modification to…
Theano: A Python framework for fast computation of mathematical expressions
The Theano Development Team, Rami Al-Rfou, Guillaume Alain +110
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has bee…
Architectural Complexity Measures of Recurrent Neural Networks
Saizheng Zhang, Yuhuai Wu, Tong Che +4
In this paper, we systematically analyze the connecting architectures of recurrent neural networks (RNNs). Our main contribution is twofold: first, we present a rigorous graph-theo…
Generating images with recurrent adversarial networks
Daniel Jiwoong Im, Chris Dongjoo Kim, Hui Jiang +1
Gatys et al. (2015) showed that optimizing pixels to match features in a convolutional network with respect reference image features is a way to render images of high visual qualit…
How far can we go without convolution: Improving fully-connected networks
Zhouhan Lin, Roland Memisevic, Kishore Konda
We propose ways to improve the performance of fully connected networks. We found that two approaches in particular have a strong effect on performance: linear bottleneck layers and…
Regularizing RNNs by Stabilizing Activations
David Krueger, Roland Memisevic
We stabilize the activations of Recurrent Neural Networks (RNNs) by penalizing the squared distance between successive hidden states' norms. This penalty term is an effective regul…
Denoising Criterion for Variational Auto-Encoding Framework
Daniel Jiwoong Im, Sungjin Ahn, Roland Memisevic +1
Denoising autoencoders (DAE) are trained to reconstruct their clean inputs with noise injected at the input level, while variational autoencoders (VAE) are trained with noise injec…
RATM: Recurrent Attentive Tracking Model
Samira Ebrahimi Kahou, Vincent Michalski, Roland Memisevic
We present an attention-based modular neural framework for computer vision. The framework uses a soft attention mechanism allowing models to be trained with gradient descent. It co…
Neural Networks with Few Multiplications
Zhouhan Lin, Matthieu Courbariaux, Roland Memisevic +1
For most deep learning algorithms training is notoriously time consuming. Since most of the computation in training neural networks is typically spent on floating point multiplicat…
Dropout as data augmentation
Xavier Bouthillier, Kishore Konda, Pascal Vincent +1
Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentat…
Conservativeness of untied auto-encoders
Daniel Jiwoong Im, Mohamed Ishmael Diwan Belghazi, Roland Memisevic
We discuss necessary and sufficient conditions for an auto-encoder to define a conservative vector field, in which case it is associated with an energy function akin to the unnorma…
EmoNets: Multimodal deep learning approaches for emotion recognition in video
Samira Ebrahimi Kahou, Xavier Bouthillier, Pascal Lamblin +15
The task of the emotion recognition in the wild (EmotiW) Challenge is to assign one of seven emotions to short video clips extracted from Hollywood style movies. The videos depict…
On Using Very Large Target Vocabulary for Neural Machine Translation
Sébastien Jean, Kyunghyun Cho, Roland Memisevic +1
Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches suc…
Modeling sequential data using higher-order relational features and predictive training
Vincent Michalski, Roland Memisevic, Kishore Konda
Bi-linear feature learning models, like the gated autoencoder, were proposed as a way to model relationships between frames in a video. By minimizing reconstruction error of one fr…
Zero-bias autoencoders and the benefits of co-adapting features
Kishore Konda, Roland Memisevic, David Krueger
Regularized training of an autoencoder typically results in hidden unit biases that take on large negative values. We show that negative biases are a natural result of using a hidd…
Unsupervised learning of depth and motion
Kishore Konda, Roland Memisevic
We present a model for the joint estimation of disparity and motion. The model is based on learning about the interrelations between images from multiple cameras, multiple frames i…
Learning to encode motion using spatio-temporal synchrony
Kishore Reddy Konda, Roland Memisevic, Vincent Michalski
We consider the task of learning to extract motion from videos. To this end, we show that the detection of spatial transformations can be viewed as the detection of synchrony betwe…