Related papers: Agent-Centric Relation Graph for Object Visual Nav…
Robots operating in real-world environments frequently encounter unknown objects with complex structures and articulated components, such as doors, drawers, cabinets, and tools. The ability to perceive, track, and manipulate these objects…
Much of the remarkable progress in computer vision has been focused around fully supervised learning mechanisms relying on highly curated datasets for a variety of tasks. In contrast, humans often learn about their world with little to no…
In order to answer semantically-complicated questions about an image, a Visual Question Answering (VQA) model needs to fully understand the visual scene in the image, especially the interactive dynamics between different objects. We propose…
Dynamic community detection has been prospered as a powerful tool for quantifying changes in dynamic brain network connectivity patterns by identifying strongly connected sets of nodes. However, as the network science problems and network…
We study lifelong visual perception in an embodied setup, where we develop new models and compare various agents that navigate in buildings and occasionally request annotations which, in turn, are used to refine their visual perception…
Home-assistant robots have been a long-standing research topic, and one of the biggest challenges is searching for required objects in housing environments. Previous object-goal navigation requires the robot to search for a target object…
In this work, we seek new insights into the underlying challenges of the Scene Graph Generation (SGG) task. Quantitative and qualitative analysis of the Visual Genome dataset implies -- 1) Ambiguity: even if inter-object relationship…
Incorporating relational reasoning in neural networks for object recognition remains an open problem. Although many attempts have been made for relational reasoning, they generally only consider a single type of relationship. For example,…
Reasoning about the relationships between object pairs in images is a crucial task for holistic scene understanding. Most of the existing works treat this task as a pure visual classification task: each type of relationship or phrase is…
Scene graph generation (SGG) aims to understand the visual objects and their semantic relationships from one given image. Until now, lots of SGG datasets with the eyelevel view are released but the SGG dataset with the overhead view is…
Representations are crucial for a robot to learn effective navigation policies. Recent work has shown that mid-level perceptual abstractions, such as depth estimates or 2D semantic segmentation, lead to more effective policies when provided…
Behavior prediction in dynamic, multi-agent systems is an important problem in the context of self-driving cars, due to the complex representations and interactions of road components, including moving agents (e.g. pedestrians and vehicles)…
Forecasting long-term human motion is a challenging task due to the non-linearity, multi-modality and inherent uncertainty in future trajectories. The underlying scene and past motion of agents can provide useful cues to predict their…
Predicting future motions of nearby agents is essential for an autonomous vehicle to take safe and effective actions. In this paper, we propose TSGN, a framework using Temporal Scene Graph Neural Networks with projected vectorized…
Long-distance transport plays a vital role in the economic growth of countries. However, there is a lack of systems being developed for monitoring and support of long-route vehicles (LRV). Sustainable and context-aware transport systems…
We present a framework for learning visually-guided quadruped locomotion by integrating exteroceptive sensing and central pattern generators (CPGs), i.e. systems of coupled oscillators, into the deep reinforcement learning (DRL) framework.…
Technologies to predict human actions are extremely important for applications such as human robot cooperation and autonomous driving. However, a majority of the existing algorithms focus on exploiting visual features of the videos and do…
Dialogue policy plays an important role in task-oriented spoken dialogue systems. It determines how to respond to users. The recently proposed deep reinforcement learning (DRL) approaches have been used for policy optimization. However,…
Visual relation detection methods rely on object information extracted from RGB images such as 2D bounding boxes, feature maps, and predicted class probabilities. We argue that depth maps can additionally provide valuable information on…
Mapping and scene representation are fundamental to reliable planning and navigation in mobile robots. While purely geometric maps using voxel grids allow for general navigation, obtaining up-to-date spatial and semantically rich…