Related papers: Fast Point-Feature Label Placement for Dynamic Vis…

Vehicle environmental awareness is a crucial issue in improving road safety. Through a variety of sensors and vehicle-to-vehicle communication, vehicles can collect a wealth of data. However, to make these data useful, sensor data must be…

While modern visual recognition systems have made significant advancements, many continue to struggle with the open problem of learning from few exemplars. This paper focuses on the task of object detection in the setting where object…

Object localization is an important task in computer vision but requires a large amount of computational power due mainly to an exhaustive multiscale search on the input image. In this paper, we describe a near real-time multiscale search…

In this work, we propose a simple yet effective method to tackle the problem of imbalanced multi-class semantic segmentation in deep learning systems. One of the key properties for a good training set is the balancing among the classes.…

Learning to build 3D scene graphs is essential for real-world perception in a structured and rich fashion. However, previous 3D scene graph generation methods utilize a fully supervised learning manner and require a large amount of…

For several emerging technologies such as augmented reality, autonomous driving and robotics, visual localization is a critical component. Directly regressing camera pose/3D scene coordinates from the input image using deep neural networks…

Localization is a key requirement for mobile robot autonomy and human-robot interaction. Vision-based localization is accurate and flexible, however, it incurs a high computational burden which limits its application on many…

The Visual Simultaneous Localization and Mapping (V-SLAM) system has seen significant development in recent years, demonstrating high precision in environments with limited dynamic objects. However, their performance significantly…

Images or videos always contain multiple objects or actions. Multi-label recognition has been witnessed to achieve pretty performance attribute to the rapid development of deep learning technologies. Recently, graph convolution network…

Recently, video scene text detection has received increasing attention due to its comprehensive applications. However, the lack of annotated scene text video datasets has become one of the most important problems, which hinders the…

Fingerprint-based localization improves the positioning performance in challenging, non-line-of-sight (NLoS) dominated indoor environments. However, fingerprinting models require an expensive life-cycle management including recording and…

Graph convolutional networks have made great progress in graph-based semi-supervised learning. Existing methods mainly assume that nodes connected by graph edges are prone to have similar attributes and labels, so that the features smoothed…

In many applications the process of generating label information is expensive and time consuming. We present a new method that combines active and semi-supervised deep learning to achieve high generalization performance from a deep…

While current 3D object recognition research mostly focuses on the real-time, onboard scenario, there are many offboard use cases of perception that are largely under-explored, such as using machines to automatically generate high-quality…

Dynamic node classification is critical for modeling evolving systems like financial transactions and academic collaborations. In such systems, dynamically capturing node information changes is critical for dynamic node classification,…

Training and testing supervised object detection models require a large collection of images with ground truth labels. Labels define object classes in the image, as well as their locations, shape, and possibly other information such as…

Training high-quality instance segmentation models requires an abundance of labeled images with instance masks and classifications, which is often expensive to procure. Active learning addresses this challenge by striving for optimum…

We tackle the problem of learning an implicit scene representation for 3D instance segmentation from a sequence of posed RGB images. Towards this, we introduce 3DIML, a novel framework that efficiently learns a neural label field which can…

While training models and labeling data are resource-intensive, a wealth of pre-trained models and unlabeled data exists. To effectively utilize these resources, we present an approach to actively select pre-trained models while minimizing…

In the fast-evolving field of artificial intelligence, where models are increasingly growing in complexity and size, the availability of labeled data for training deep learning models has become a significant challenge. Addressing complex…