Search
Search Results
-
Research on the algorithm of helmet-wearing detection based on the optimized yolov4
At construction sites, wearing hard hats is an important and effective measure to protect workers from accidental injury. In order to remind workers...
-
A Real World Dataset for Multi-view 3D Reconstruction
We present a dataset of 998 3D models of everyday tabletop objects along with their 847,000 real world RGB and depth images. Accurate annotation of... -
Light-Weight Multi-view Topology Consistent Facial Geometry and Reflectance Capture
We present a light-weight multi-view capture system with different lighting conditions to generate a topology consistent facial geometry and... -
Approximate Differentiable Rendering with Algebraic Surfaces
Differentiable renderers provide a direct mathematical link between an object’s 3D representation and images of that object. In this work, we develop... -
SAFaD: A System for Automatic Fall Detection on Surveillance Imagery
In this work we introduce SAFaD: A System for Automatic Fall Detection on Surveillance Imagery. Our system heavily relies in an intermediate... -
LocaliseBot: Multi-view 3D Object Localisation with Differentiable Rendering for Robot Gras**
Robot grasp typically follows five stages: object detection, object localisation, object pose estimation, grasp pose estimation, and grasp planning.... -
A Cross-Modal Face Reconstruction Method for Service on Blockchains
The current blockchain systems are suffering the low scalability. In order to improve the scalability and enable the storage of more critical facial... -
A review of 3D object detection based on autonomous driving
3D object detection is a popular research direction in recent years, which plays an important role in the fields of automatic driving, intelligent...
-
Identification of Bird’s Nest Hazard Level of Transmission Line Based on Improved Yolov5 and Location Constraints
Bird’s nest is a common defect in transmission line, which seriously affects the safe and stable operation of the line. This paper presents a method... -
Augmentation dataset of a two-dimensional neural network model for use in the car parts segmentation and car classification of three dimensions
In this study, three-dimensional (3D) spatial data, two-dimensional (2D) texture information, and automatic marking processes were used for the...
-
BENet: bi-directional enhanced network for image captioning
Transformer-based models have been used in image captioning to generate a natural language text for describing a given image accurately. In this...
-
Objects Can Move: 3D Change Detection by Geometric Transformation Consistency
AR/VR applications and robots need to know when the scene has changed. An example is when objects are moved, added, or removed from the scene. We... -
Re-Thinking Text Clustering for Images with Text
Text-VQA refers to the set of problems that reason about the text present in an image to answer specific questions regarding the image content.... -
Fabric defect detection algorithm based on residual energy distribution and Gabor feature fusion
Gabor filter is a time-frequency combined analysis method, which is suitable for detecting local anomalies in periodic textures. Gabor-based methods...
-
An image storage duplication detection method using recurrent learning for smart application services
Smart and intelligent application services rely on textual and visualization information for meeting user demands. Regardless of the textual data,...
-
Visual Mesh: Real-Time Object Detection Using Constant Sample Density
This paper proposes an enhancement of convolutional neural networks for object detection in resource-constrained robotics through a geometric input... -
Introduction to Deep Learning
Deep learning (DL) has made a major impact on data science in the last decade. This chapter introduces the basic concepts of this field. It includes... -
Geometrically-Aware Dual Transformer Encoding Visual and Textual Features for Image Captioning
When describing pictures from the point of view of human observers, the tendency is to prioritize eye-catching objects, link them to corresponding... -
Detection of inclusion by using 3D laser scanner in composite prepreg manufacturing technique using convolutional neural networks
Among different manufacturing techniques available for composite aircraft structures, prepreg-based manual layup is widely used. During the...
-
3D-MuPPET: 3D Multi-Pigeon Pose Estimation and Tracking
Markerless methods for animal posture tracking have been rapidly develo** recently, but frameworks and benchmarks for tracking large animal groups...