Deep Learning
Collaborative Uncertainty in Multi-Agent Trajectory Forecasting Bohan T ang
Uncertainty modeling is critical in trajectory forecasting systems for both interpretation and safety reasons.
Depth Uncertainty in Neural Networks
To solve this, we perform probabilistic reasoning over the depth of neural networks.
SIRI: Spatial Relation Induced Network For Spatial Description Resolution
Explicitly characterizing an object-level relationship while distilling spatial relationships are currently absent but crucial to this task. Mimicking humans, who sequentially traverse spatial relationship words and objects with a first-person view to locate their target, we propose a novel spatial relationship induced (SIRI) network.
Self-Supervised Deep Learning on Point Clouds by Reconstructing Space
Jonathan Sauder, Bjarne Sievers
Neural Information Processing Systems http://nips.cc/
The Point Where Reality Meets Fantasy: Mixed Adversarial Generators for Image Splice Detection
Vladimir V. Kniaz, Vladimir Knyaz, Fabio Remondino
Neural Information Processing Systems http://nips.cc/