Related papers: One-Shot Object Affordance Detection in the Wild
Amodal recognition is the ability of the system to detect occluded objects. Most SOTA Visual Recognition systems lack the ability to perform amodal recognition. Few studies have achieved amodal recognition through passive prediction or…
For robots to exhibit a high level of intelligence in the real world, they must be able to assess objects for which they have no prior knowledge. Therefore, it is crucial for robots to perceive object affordances by reasoning about physical…
Visual similarities discovery (VSD) is an important task with broad e-commerce applications. Given an image of a certain object, the goal of VSD is to retrieve images of different objects with high perceptual visual similarity. Although…
Recent years have witnessed huge successes in 3D object detection to recognize common objects for autonomous driving (e.g., vehicles and pedestrians). However, most methods rely heavily on a large amount of well-labeled training data. This…
Robots are increasingly expected to manipulate objects in ever more unstructured environments where the object properties have high perceptual uncertainty from any single sensory modality. This directly impacts successful object…
Most existing works on few-shot object detection (FSOD) focus on a setting where both pre-training and few-shot learning datasets are from a similar domain. However, few-shot algorithms are important in multiple domains; hence evaluation…
Applications of unmanned aerial vehicle (UAV) in logistics, agricultural automation, urban management, and emergency response are highly dependent on oriented object detection (OOD) to enhance visual perception. Although existing datasets…
Conventional camera-based 3D object detectors in autonomous driving are limited to recognizing a predefined set of objects, which poses a safety risk when encountering novel or unseen objects in real-world scenarios. To address this…
The past decade has witnessed significant progress on detecting objects in aerial images that are often distributed with large scale variations and arbitrary orientations. However most of existing methods rely on heuristically defined…
Accurate affordance detection and segmentation with pixel precision is an important piece in many complex systems based on interactions, such as robots and assitive devices. We present a new approach to affordance perception which enables…
Perceiving potential ``action possibilities'' (\ie, affordance) regions of images and learning interactive functionalities of objects from human demonstration is a challenging task due to the diversity of human-object interactions.…
This paper presents a novel joint neural networks approach to address the challenging one-shot object recognition and detection tasks. Inspired by Siamese neural networks and state-of-art multi-box detection approaches, the joint neural…
Few-shot multispectral object detection (FSMOD) addresses the challenge of detecting objects across visible and thermal modalities with minimal annotated data. In this paper, we explore this complex task and introduce a framework named…
Few-shot Open-set Object Detection (FOOD) poses a challenge in many open-world scenarios. It aims to train an open-set detector to detect known objects while rejecting unknowns with scarce training samples. Existing FOOD methods are subject…
Early object detection (OD) is a crucial task for the safety of many dynamic systems. Current OD algorithms have limited success for small objects at a long distance. To improve the accuracy and efficiency of such a task, we propose a novel…
Affordance grounding requires identifying where and how an agent should interact in open-world scenes, where actionable regions are often small, occluded, reflective, and visually ambiguous. Recent systems therefore combine multiple skills…
Grasping occluded objects in cluttered environments is an essential component in complex robotic manipulation tasks. In this paper, we introduce an AffordanCE-driven Next-Best-View planning policy (ACE-NBV) that tries to find a feasible…
Articulated objects are pervasive in daily life. However, due to the intrinsic high-DoF structure, the joint states of the articulated objects are hard to be estimated. To model articulated objects, two kinds of shape deformations namely…
Road attributes understanding is extensively researched to support vehicle's action for autonomous driving, whereas current works mainly focus on urban road nets and rely much on traffic signs. This paper generalizes the same issue to the…
We explore how intermediate policy representations can facilitate generalization by providing guidance on how to perform manipulation tasks. Existing representations such as language, goal images, and trajectory sketches have been shown to…