Yuning Chai

TL;DR: This work introduces a new large scale, high quality, diverse dataset, consisting of well synchronized and calibrated high quality LiDAR and camera data captured across a range of urban and suburban geographies, and studies the effects of dataset size and generalization across geographies on 3D detection methods.

TL;DR: In this paper, a large scale, high quality, and diverse dataset for self-driving data is presented, consisting of LiDAR and camera data captured across a range of urban and suburban geographies.

TL;DR: MultiPath as discussed by the authors leverages a fixed set of future state-sequence anchors that correspond to modes of the trajectory distribution, and regresses offsets from anchor waypoints along with uncertainties, yielding a Gaussian mixture at each time step.

TL;DR: FEELVOS as discussed by the authors uses a semantic pixel-wise embedding together with a global and a local matching mechanism to transfer information from the first frame and from the previous frame of the video to the current frame.

TL;DR: The model builds a model of the base-level category that can be fitted to images, producing high-quality foreground segmentation and mid-level part localizations, and improves the categorization accuracy over the state-of-the-art.