Over the last few years, we have witnessed tremendous progress on many subtasks of autonomous driving, including perception, motion forecasting, and motion planning.
We are interested in understanding whether retrieval-based localization approaches are good enough in the context of self-driving vehicles.
One of the main difficulties of scaling current localization systems to large environments is the on-board storage required for the maps.
Compressing large neural networks is an important step for their deployment in resource-constrained computational platforms.
Multi-codebook quantization (MCQ) is the task of expressing a set of vectors as accurately as possible in terms of discrete entries in multiple bases.
Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels.
Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality.
Recently, Babenko and Lempitsky introduced Additive Quantization (AQ), a generalization of Product Quantization (PQ) where a non-independent set of codebooks is used to compress vectors into small binary codes.
We describe a new approach to transfer knowledge across views for action recognition by using examples from a large collection of unlabelled mocap data.