Related papers: Information Entropy Guided Height-aware Histogram …

3D object detection is an essential task in autonomous driving. Recent techniques excel with highly accurate detection rates, provided the 3D input data is obtained from precise but expensive LiDAR technology. Approaches based on cheaper…

Estimating the 3D position of human joints has become a widely researched topic in the last years. Special emphasis has gone into defining novel methods that extrapolate 2-dimensional data (keypoints) into 3D, namely predicting the…

Roadside vision centric 3D object detection has received increasing attention in recent years. It expands the perception range of autonomous vehicles, enhances the road safety. Previous methods focused on predicting per-pixel height rather…

Based on PixelHop and PixelHop++, which are recently developed using the successive subspace learning (SSL) framework, we propose an enhanced solution for object classification, called E-PixelHop, in this work. E-PixelHop consists of the…

Learning an effective similarity measure between image representations is key to the success of recent advances in visual search tasks (e.g. verification or zero-shot learning). Although the metric learning part is well addressed, this…

Feature engineering continues to play a critical role in image classification, particularly when interpretability and computational efficiency are prioritized over deep learning models with millions of parameters. In this study, we revisit…

Despite the fact that object detection, 3D pose estimation, and sub-category recognition are highly correlated tasks, they are usually addressed independently from each other because of the huge space of parameters. To jointly model all of…

Point cloud registration is a central theme in computer vision, with alignment algorithms continuously improving for greater robustness. Commonly used methods evaluate Euclidean distances between point clouds and minimize an objective…

3D occupancy prediction aims to infer dense, voxel-wise scene semantics from sensor observations, where the 2D-to-3D view transformation serves as a crucial step in bridging image features and volumetric representations. Most previous…

Explicit high-order feature interactions efficiently capture essential structural knowledge about the data of interest and have been used for constructing generative models. We present a supervised discriminative High-Order Parametric…

Efficient representation of point clouds is fundamental for LiDAR-based 3D object detection. While recent grid-based detectors often encode point clouds into either voxels or pillars, the distinctions between these approaches remain…

Monocular height estimation (MHE) from very-high-resolution (VHR) optical imagery remains challenging due to limited structural cues and the high cost and geographic constraints of conventional elevation data such as airborne LiDAR and…

Multi-view 3D object detection is a crucial component of autonomous driving systems. Contemporary query-based methods primarily depend either on dataset-specific initialization of 3D anchors, introducing bias, or utilize dense attention…

Holographic displays promise to deliver unprecedented display capabilities in augmented reality applications, featuring a wide field of view, wide color gamut, spatial resolution, and depth cues all in a compact form factor. While emerging…

Given an image of a white shoe drawn on a blackboard, how are the white pixels deemed (say by human minds) to be informative for recognizing the shoe without any labeling information on the pixels? Here we investigate such a ``white shoe''…

The 3D Human Pose Estimation (3D HPE) task uses 2D images or videos to predict human joint coordinates in 3D space. Despite recent advancements in deep learning-based methods, they mostly ignore the capability of coupling accessible texts…

PointPillars is the fastest 3D object detector that exploits pseudo image representations to encode features for 3D objects in a scene. Albeit efficient, PointPillars is typically outperformed by state-of-the-art 3D detection methods due to…

We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data. This framework is designed to aggregate multiple classifiers updated locally using private data and to ensure that no…

Heterogeneous information networks (HINs) are ubiquitous in real-world applications. In the meantime, network embedding has emerged as a convenient tool to mine and learn from networked data. As a result, it is of interest to develop HIN…

Running deep learning models on resource-constrained edge devices has drawn significant attention due to its fast response, privacy preservation, and robust operation regardless of Internet connectivity. While these devices already cope…