相关论文: ConceptFactory: Facilitate 3D Object Knowledge Ann…
The neural implicit representation has shown its effectiveness in novel view synthesis and high-quality 3D reconstruction from multi-view images. However, most approaches focus on holistic scene representation yet ignore individual objects…
Generating text descriptions of objects in 3D indoor scenes is an important building block of embodied understanding. Existing methods do this by describing objects at a single level of detail, which often does not capture fine-grained…
Recent advances in data-centric artificial intelligence highlight inherent limitations in object recognition datasets. One of the primary issues stems from the semantic gap problem, which results in complex many-to-many mappings between…
Dataset bias, where data points are skewed to certain concepts, is ubiquitous in machine learning datasets. Yet, systematically identifying these biases is challenging without costly, fine-grained attribute annotations. We present…
Inferring detailed 3D geometry of the scene is crucial for robotics applications, simulation, and 3D content creation. However, such information is hard to obtain, and thus very few datasets support it. In this paper, we propose an…
The main goal of concept-oriented programming (COP) is describing how objects are represented and accessed. It makes references (object locations) first-class elements of the program responsible for many important functions which are…
Articulated object manipulation is essential for various real-world robotic tasks, yet generalizing across diverse objects remains a major challenge. A key to generalization lies in understanding functional parts (e.g., door handles and…
With most modern visualization tools, authors need to transform their data into tidy formats to create visualizations they want. Because this requires experience with programming or separate data processing tools, data transformation…
3D object detection has become indispensable in the field of autonomous driving. To date, gratifying breakthroughs have been recorded in 3D object detection research, attributed to deep learning. However, deep learning algorithms are…
In recent years, neural implicit surface reconstruction has emerged as a popular paradigm for multi-view 3D reconstruction. Unlike traditional multi-view stereo approaches, the neural implicit surface-based methods leverage neural networks…
The automatic understanding of video content is advancing rapidly. Empowered by deeper neural networks and large datasets, machines are increasingly capable of understanding what is concretely visible in video frames, whether it be objects,…
We present and evaluate an approach for human-in-the-loop specification of shape reconstruction with annotations for basic robot-object interactions. Our method is based on the idea of model annotation: the addition of simple cues to an…
This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly. The concept-centric agent utilizes a vocabulary of neuro-symbolic concepts. These concepts, such as object, relation, and…
Intuitive observations show that a baby may inherently possess the capability of recognizing a new visual concept (e.g., chair, dog) by learning from only very few positive instances taught by parent(s) or others, and this recognition…
3D shape captioning is a challenging application in 3D shape understanding. Captions from recent multi-view based methods reveal that they cannot capture part-level characteristics of 3D shapes. This leads to a lack of detailed part-level…
Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding box regression as in traditional 3D object detection, 3D…
Open-vocabulary 3D object detection has gained significant interest due to its critical applications in autonomous driving and embodied AI. Existing detection methods, whether offline or online, typically rely on dense point cloud…
While recent research in image understanding has often focused on recognizing more types of objects, understanding more about the objects is just as important. Recognizing object parts and attributes has been extensively studied before, yet…
Concept-based interpretability for Convolutional Neural Networks (CNNs) aims to align internal model representations with high-level semantic concepts, but existing approaches largely overlook the semantic roles of individual filters and…
In deformable object manipulation, we often want to interact with specific segments of an object that are only defined in non-deformed models of the object. We thus require a system that can recognize and locate these segments in sensor…