978 citations · 7k across the 148 of their papers we have counts for
18 papers · 1 filter
Detecting unseen visual relations using analogies
Julia Peyre, Ivan Laptev, Cordelia Schmid +1
We seek to detect visual relations in images of the form of triplets t = (subject, predicate, object), such as "person riding dog", where training examples of the individual entiti…
A Structured Model For Action Detection
Yubo Zhang, Pavel Tokmakov, Martial Hebert +1
A dominant paradigm for learning-based approaches in computer vision is training generic models, such as ResNet for image recognition, or I3D for video understanding, on large data…
Modulated Policy Hierarchies
Alexander Pashevich, Danijar Hafner, James Davidson +2
Solving tasks with sparse rewards is a main challenge in reinforcement learning. While hierarchical controllers are an intuitive approach to this problem, current methods often req…
Déjà Vu: an empirical evaluation of the memorization properties of ConvNets
Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid +1
Convolutional neural networks memorize part of their training data, which is why strategies such as data augmentation and drop-out are employed to mitigate overfitting. This paper…
On the Importance of Visual Context for Data Augmentation in Scene Understanding
Nikita Dvornik, Julien Mairal, Cordelia Schmid
Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training e…
Actor-Centric Relation Network
Chen Sun, Abhinav Shrivastava, Carl Vondrick +3
Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level and model temporal context with 3D ConvNets. Here, we go one step…