This article focuses on reasoning about the location and time behind images. Given that pre-trained vision-language models (VLMs) exhibit excellent image and text understanding capabilities, most existing methods leverage them to match visual cues with ...

Recovering structures from images with 180∘ or 360∘ FoV is pivotal in computer vision and computational photography, particularly for VR/AR/MR and autonomous robotics applications. Due to varying distortions and the complexity of indoor scenes, ...

Open-set object detection (OSOD) aims to detect the known categories and reject unknown objects in a dynamic world, which has achieved significant attention. However, previous approaches only consider this problem in data-abundant conditions, while ...

Creating digital twins of scenes has been widely studied in smart city applications. The development of 3D virtual games attracts many researchers. However, most products have high costs, neglect 3D recovery of the moving people, and lack ...

Library migration, which replaces the current library with a different one to retain the same software behavior, is common in software evolution. An essential part of this is finding an analogous API for the desired functionality. However, due to the ...

Real-time semantic segmentation of street scenes is an essential and challenging task for autonomous driving systems, which needs to achieve both high accuracy and efficiency. Moreover, numerous objects and stuff at different scales in street scenes ...

In the field of tunnel lining crack identification, the semantic segmentation algorithms based on convolution neural network (CNN) are extensively used. Owing to the inherent locality of CNN, these algorithms cannot make full use of context ...

We study the problem of few-shot open-set object detection (FOOD), whose goal is to quickly adapt a model to a small set of labeled samples and reject unknown class samples. Recent works usually use the weight sparsification for unknown rejection, but ...

Robust and accurate camera pose estimation is fundamental in computer vision. Learning-based regression approaches acquire six-degree-of-freedom camera parameters accurately from visual cues of an input image. However, most are trained on street-view and ...

Scene structure recovery is a crucial process for assisting scene reconstruction and understanding by extracting vital scene structure information and has been widely used in smart city, VR/AR and intelligent robot navigation. Omnidirectional ...

Online multi-object tracking aims at generating the trajectories for multiple objects in the surveillance scene. It remains a challenging problem in crowded scenes because objects often gather together and occlude in tracking frames. ...

Context modeling or multi-level feature fusion methods have been proved to be effective in improving semantic segmentation performance. However, they are not specialized to deal with the problems of pixel-context mismatch and spatial feature misalignment, ...

Panorama image has a large 360${}^{\circ }$ field of view, providing rich contextual information for object detection, widely used in virtual reality, augmented reality, scene understanding, etc. However, existing methods for object detection on panorama ...${}^{}$$$

Unsupervised domain adaptation person re-identification aims to adapt the model learned on a labeled source domain to an unlabeled target domain. It has attracted extensively attention in the computer vision community due to its important ...

Part information has been proven to be resistant to occlusions and viewpoint changes, which are main difficulties in car parsing and reconstruction. However, in the absence of datasets and approaches incorporating car parts, there are limited works that ...

Person re-identification (Re-ID) aims to match a person of interest across multiple non-overlapping camera views. This is a challenging task, partly because a person captured in surveillance video often undergoes intense pose variations. ...${}^{\mathrm{}}$

Aiming to solve the challenges of low detection accuracy, poor anti‐interference ability, and slow detection speed in the traditional tunnel lining defect detection methods, a novel deep learning‐based model, named You Only Look Once network v4 ...

The diabetic retinopathy (DR) detection based on deep learning is a powerful tool for early screening of DR. Although several automatic DR grading algorithms have been proposed, their performance is still limited by the characteristics of DR ...

The recent trend in Multi-Object Tracking (MOT) is heading towards using deep learning to detect objects and extract features. Although tracking frameworks using detection network have achieved outstanding performance in object locating on MOT, it ...

Unsupervised domain adaptation in person re-identification is a challenging task. The performance of models trained on a specific domain generally degrades significantly on other domains due to the domain gaps. State-of-the-art clustering-based ...