Research

Dataset Distillation and Coreset Selection are techniques for compressing large-scale datasets into smaller, more manageable forms while preserving the essential information needed for model training. Dataset Distillation synthesizes a compact set of representative samples that encapsulate the knowledge of the full dataset, whereas Coreset Selection identifies and retains the most... Read more

Re-Identification (Re-ID) is the task of recognizing and matching a specific object or person across different cameras, viewpoints, or time instances. Unlike simple classification, Re-ID must handle large intra-class variations caused by changes in illumination, pose, occlusion, and background clutter. The goal is to learn discriminative feature representations that remain... Read more

{:en}Large-scale 3D point clouds (LS3DPCs) captured by terrestrial LiDAR scanners often exhibit reflection artifacts by glasses, which degrade the performance of related computer vision techniques. In this paper, we propose an efficient reflection removal algorithm for LS3DPCs. We first partition the unit sphere into local surface patches which are then... Read more

Person Search Person search has drawn considerable attention recently with the increasing demand for person re-identification from real world scene images. The conventional person re-identification takes a set of cropped person images and selects the images among them matching to a given query person. On the other hand, the person... Read more

{:en}A fast and optimized dehazing algorithm for hazy images and videos is proposed in this work. Based on the observation that a hazy image exhibits low contrast in general, we restore the hazy image by enhancing its contrast. However, the overcompensation of the degraded contrast may truncate pixel values and... Read more

{:en}The images taken through glass often capture a target transmitted scene as well as undesired reflected scenes. In this paper, we propose an optimization problem to remove reflection automatically from multiple glass images taken at slightly different camera locations. We first warp the multiple glass images to a reference image,... Read more