eLife

Human EEG and artificial neural networks reveal disentangled representations and processing timelines of object real-world size and depth in natural images

Neural and computational evidence reveals that real-world size is a temporally late, semantically grounded, and hierarchically stable dimension of object representation in both human brains and ...
GitHub

weikaih04/Synthetic-Detection-Segmentation-Grounding-Data

A scalable pipeline for composing high-quality synthetic object segments into richly annotated images for object detection, instance segmentation, and visual grounding. High-resolution images with ...
IEEE

Deep Learning-Based Railway Foreign Object Intrusion Intelligent Perception Using Attention-Aggregated Semantic Segmentation

Abstract: Foreign object intrusion detection (FOID) is one of the critical tasks to ensure the safe and efficient operation of trains. Semantic segmentation, which involves pixel-level recognition of ...
IEEE

Point Cloud Segmentation Algorithm Based on Improved Euclidean Clustering

Abstract: Point cloud segmentation is a crucial technique for object recognition and localization, widely employed in various applications such as point cloud registration, 3D reconstruction, object ...
GitHub

atlan-antillia/TensorFlow-FlexUNet-Tiled-Image-Segmentation-Drone-Image

Since the images and masks of the original Drone Images are very large (3.8K to 4.4K pixels width), we adopted the following Divide-and-Conquer Strategy for building our segmentation model. 1. Tiled ...