Neural Information Processing Systems http://nips.cc/

Open-vocabulary object detection via vision and language knowledge distillation.

Human actions in egocentric videos often feature hand-object interactions composed of a verb (performed by the hand) applied to an object.

An essential aspect of any machine learning system is understanding what the model does not know.

Wepropose a 3D capsule network for videos, called VideoCapsuleNet: a unified network for action detection which can jointly perform pixel-wise action segmentation along with action classification. The proposed network is a generalization of capsule network from 2D to 3D, which takes a sequence of video frames as input. The 3D generalization drastically increases the number of capsules in the network, making capsule routing computationally expensive.

Neural Information Processing Systems http://nips.cc/

Likewise, independently withamodified named JP2-WSI15].

Finding tight linear bounds for activation functions in neural networks is an essential part of several state of the art neural network robustness certification tools.

There aretwointeresting andwell-studied computational paradigms aimed attackling uncertainty.