This work thus presents Weighted Pointer interaction, a collection of error-aware pointing techniques that determine whether pointing should be performed by gaze, a fallback...
In this work, we present a novel framework for computing visual counterfactual explanations based on two key ideas.
We propose Detic, which simply trains the classifiers of a detector on image classification data and thus expands the vocabulary of detectors to tens of thousands of concepts.
We propose a method for estimating the 6DoF pose of a rigid object with an available 3D model from a single RGB image. Unlike classical correspondence-based methods which predict...
We introduce VSA-based constraints on adversarial learning for source-to-target translations by learning a hypervector mapping that inverts the translation to ensure consistency...
In this paper, we aim to solve the space-time aliasing problem by learning a spatio-temporal downsampler.
We introduce Housekeep, a benchmark to evaluate commonsense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by rearranging misplaced...
We present Pose-NDF, a continuous model for plausible human poses based on neural distance fields (NDFs). Pose or motion priors are important for generating realistic new poses...
We propose an architecture to create dense feature maps in novel views obtained by sphere-based neural rendering, and create complete renders using a global context inpainting model.
In this paper, we advocate an end-to-end reinforcement learning (RL) paradigm to demonstrate how an agent can learn directly from machine-readable music score to play the piano...
