Related papers: Geometric Affordances from a Single Example via th…
Current work in lexical distributed representations maps each word to a point vector in low-dimensional space. Mapping instead to a density provides many interesting advantages, including better capturing uncertainty about a representation…
Visual design is critical to product success, and the subject of intensive marketing research effort. Yet visual elements, due to their holistic and interactive nature, do not lend themselves well to optimization using extant…
In this paper, we tackle the problem of detecting objects in 3D and forecasting their future motion in the context of self-driving. Towards this goal, we design a novel approach that explicitly takes into account the interactions between…
We consider the representation of operators in terms of tensor networks and their application to ground-state approximation and time evolution of systems with long-range interactions. We provide an explicit construction to represent an…
Affordance grounding focuses on predicting the specific regions of objects that are associated with the actions to be performed by robots. It plays a vital role in the fields of human-robot interaction, human-object interaction, embodied…
Affordance information about a scene provides important clues as to what actions may be executed in pursuit of meeting a specified goal state. Thus, integrating affordance-based reasoning into symbolic action plannning pipelines would…
Node embedding is the task of extracting concise and informative representations of certain entities that are connected in a network. Various real-world networks include information about both node connectivity and certain node attributes,…
Over recent years it has become well accepted that user interest is not static or immutable. There are a variety of contextual factors, such as time of day, the weather or the user's mood, that influence the current interests of the user.…
The space complexity of functional programs is not well understood. In particular, traditional implementation techniques are tailored to time efficiency, and space efficiency induces time inefficiencies, as it prefers re-computing to…
Multi-task indoor scene understanding is widely considered as an intriguing formulation, as the affinity of different tasks may lead to improved performance. In this paper, we tackle the new problem of joint semantic, affordance and…
Humans excel at acquiring knowledge through observation. For example, we can learn to use new tools by watching demonstrations. This skill is fundamental for intelligent systems to interact with the world. A key step to acquire this skill…
Learning robot manipulation from human videos is appealing due to the scale and diversity of human demonstrations, but transferring such demonstrations to executable robot behavior remains challenging. Prior work either relies on robot data…
Transformer architectures, capable of capturing sequential dependencies in the history of user interactions, have become the dominant approach in sequential recommender systems. Despite their success, such models consider sequence elements…
We investigate image segmentation of cells under the lens of scalar fields. Our goal is to learn a continuous scalar field on image domains such that its segmentation produces robust instances for cells present in images. This field is a…
We propose a framework for the linear prediction of a multi-way array (i.e., a tensor) from another multi-way array of arbitrary dimension, using the contracted tensor product. This framework generalizes several existing approaches,…
In this paper we study finite dimensional algebras, in particular finite semifields, through their correspondence with nonsingular threefold tensors. We introduce a alternative embedding of the tensor product space into a projective space.…
This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. In the context of dense matching, many works benefit from one of two forms of aggregation: feature aggregation,…
Open-Vocabulary 3D object affordance grounding aims to anticipate ``action possibilities'' regions on 3D objects with arbitrary instructions, which is crucial for robots to generically perceive real scenarios and respond to operational…
We approach the problem of high-DOF reaching-and-grasping via learning joint planning of grasp and motion with deep reinforcement learning. To resolve the sample efficiency issue in learning the high-dimensional and complex control of…
Transformers are a popular choice for classification tasks and as backbones for object detection tasks. However, their high latency brings challenges in their adaptation to lightweight object detection systems. We present an approximation…