IEEE

Salient Object Detection of Dynamic Night Scenes via Bio-Inspired Spotlight Attention and Hierarchical Edge-Texture Fusion

Abstract: The perception of night scenes is of crucial importance for driving safety. In the dimly lit night environment, as the visibility of objects decreases, both experienced and inexperienced ...
IEEE

Spatial-Frequency Collaborative Learning for Camouflaged Object Detection

Abstract: Camouflaged object detection (COD) is a challenging task that struggles to accurately detect the objects concealed in the surrounding environment. This is largely attributed to the intrinsic ...
IEEE

UniROD: Unified Radar Object Detection with MAE-pretrained CNN-Transformer Fusion

Millimeter-wave radar object detection has become pivotal for autonomous driving systems requiring all-weather reliability. While conventional CFAR methods face limitations in classification ...
IEEE

Ensemble of Fast R-CNN with Bi-LSTM for Object Detection

Abstract: Object detection is a critical task in computer vision, with applications ranging from autonomous driving to medical imaging. Traditional object detection models, such as Fast R-CNN, have ...
IEEE

Unsupervised 3D Object Detection by Commonsense Clue

Abstract: Traditional 3D object detectors, whether fully-, semi-, or weakly-supervised, rely heavily on extensive human annotations. In contrast, this paper introduces an unsupervised 3D object ...
CNN

Astronomers detect a solar system they say should not be possible

An exoplanetary system about 116 light-years from Earth could flip the script on how planets form, according to researchers who discovered it using telescopes from NASA and the European Space Agency, ...
IEEE

Adaptive Receptive Field Network for Small Objects Detection in Remote Sensing Images

Abstract: Small object detection in remote sensing images is severely hampered by the significant scale variation even among small objects. Conventional methods often rely on a static receptive field ...
IEEE

Single-Domain Generalized Object Detection With Frequency Whitening and Contrastive Learning

Abstract: Single-Domain Generalization Object Detection (Single-DGOD) refers to training a model with only one source domain, enabling the model to generalize to any unseen domain. For instance, a ...
IEEE

A Verilog based Approach for Object Detection using CNN

Abstract: A Convolutional Neural Network (CNN) are a class of artificial neural networks specifically designed to process data with a grid-like topology, such as images, making them well-suited for ...
IEEE

Toward Size-Invariant Salient Object Detection: A Generic Evaluation

Abstract: This paper investigates a fundamental yet underexplored issue in Salient Object Detection (SOD): the size-invariant property for evaluation protocols, particularly in scenarios when multiple ...
IEEE

Active Learning for Object Detection With Vectorized Dual Pseudo Loss and Multiple Instance Offset Constraint

Abstract: Existing active learning methods for object detection face challenges, such as the lack of ground truth labels for regression loss, insufficient representation of unlabeled instance samples ...
IEEE

HUNTNet: Homomorphic Unified Nexus Topology for Camouflaged Object Detection

Abstract: Camouflaged object detection (COD) is challenging for both human and computer vision, as targets often blend into the background by sharing similar color, texture, or shape. While many ...