Related papers: Table-Top Scene Analysis Using Knowledge-Supervise…

Accurate and robust recognition and prediction of traffic situation plays an important role in autonomous driving, which is a prerequisite for risk assessment and effective decision making. Although there exist a lot of works dealing with…

Traditionally, autonomous reconnaissance applications have acted on explicit sets of historical observations. Aided by recent breakthroughs in generative technologies, this work enables robot teams to act beyond what is currently known…

Representing relevant information of a traffic scene and understanding its environment is crucial for the success of autonomous driving. Modeling the surrounding of an autonomous car using semantic relations, i.e., how different traffic…

Scene Graph Generation (SGG) is a visual understanding task, aiming to describe a scene as a graph of entities and their relationships with each other. Existing works rely on location labels in form of bounding boxes or segmentation masks,…

Teaching machines of scene contextual knowledge would enable them to interact more effectively with the environment and to anticipate or predict objects that may not be immediately apparent in their perceptual field. In this paper, we…

6-DoF object-agnostic grasping in unstructured environments is a critical yet challenging task in robotics. Most current works use non-optimized approaches to sample grasp locations and learn spatial features without concerning the grasping…

Graph representation of objects and their relations in a scene, known as a scene graph, provides a precise and discernible interface to manipulate a scene by modifying the nodes or the edges in the graph. Although existing works have shown…

Scene graphs provide structured semantic understanding beyond images. For downstream tasks, such as image retrieval, visual question answering, visual relationship detection, and even autonomous vehicle technology, scene graphs can not only…

A structured query can capture the complexity of object interactions (e.g. 'woman rides motorcycle') unlike single objects (e.g. 'woman' or 'motorcycle'). Retrieval using structured queries therefore is much more useful than single object…

Advancements in generative models have sparked significant interest in generating images while adhering to specific structural guidelines. Scene graph to image generation is one such task of generating images which are consistent with the…

Despite impressive advancements in Autonomous Driving Systems (ADS), navigation in complex road conditions remains a challenging problem. There is considerable evidence that evaluating the subjective risk level of various decisions can…

We consider the problem of classification of an object given multiple observations that possibly include different transformations. The possible transformations of the object generally span a low-dimensional manifold in the original signal…

As a structured prediction task, scene graph generation aims to build a visually-grounded scene graph to explicitly model objects and their relationships in an input image. Currently, the mean field variational Bayesian framework is the de…

We develop an approach for active semantic perception which refers to using the semantics of the scene for tasks such as exploration. We build a compact, hierarchical multi-layer scene graph that can represent large, complex indoor…

Visual scenes are extremely diverse, not only because there are infinite possible combinations of objects and backgrounds but also because the observations of the same scene may vary greatly with the change of viewpoints. When observing a…

The significant progress on Generative Adversarial Networks (GANs) has facilitated realistic single-object image generation based on language input. However, complex-scene generation (with various interactions among multiple objects) still…

Deep learning has shown state-of-art classification performance on datasets such as ImageNet, which contain a single object in each image. However, multi-object classification is far more challenging. We present a unified framework which…

Humans recognize the visual world at multiple levels: we effortlessly categorize scenes and detect objects inside, while also identifying the textures and surfaces of the objects along with their different compositional parts. In this…

Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random…

Humans effortlessly identify objects by leveraging a rich understanding of the surrounding scene, including spatial relationships, material properties, and the co-occurrence of other objects. In contrast, most computational object…