Search
Search Results
-
A full-detection association tracker with confidence optimization for real-time multi-object tracking
Multi-object tracking (MOT) aims to obtain trajectories with unique identifiers for multiple objects in a video stream. In current approaches,...
-
Multi-source-free Domain Adaptive Object Detection
To enhance the transferability of object detection models in real-world scenarios where data is sampled from disparate distributions, considerable...
-
Exploiting Diffusion Prior for Real-World Image Super-Resolution
We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution....
-
Virtual home staging and relighting from a single panorama under natural illumination
Virtual staging technique can digitally showcase a variety of real-world scenes. However, relighting indoor scenes from a single image is challenging...
-
ACL-SAR: model agnostic adversarial contrastive learning for robust skeleton-based action recognition
Human skeleton data have been widely explored in action recognition and the human–computer interface recently, thanks to off-the-shelf motion sensors...
-
Evaluation of data augmentation techniques on subjective tasks
Data augmentation is widely applied in various computer vision problems for artificially increasing the size of a dataset by transforming the...
-
SkelVIT: consensus of vision transformers for a lightweight skeleton-based action recognition system
Skeleton-based action recognition systems receive the attention of many researchers due to their robustness to viewpoint and illumination changes,...
-
TOPCOAT: towards practical two-party Crystals-Dilithium
The development of threshold protocols based on lattice-signature schemes has been of increasing interest in the past several years. The main...
-
Enhanced speech emotion recognition using averaged valence arousal dominance map** and deep neural networks
This study delves into advancements in speech emotion recognition (SER) by establishing a novel approach for emotion map** and prediction using the...
-
Disturbance event triggered-model predictive tracking control for 4WIS–4WID mobile robot
Wheel-ground interactions during operation cause the robot to deviate from the reference trajectory, affecting the stability and safety of the robot....
-
End-to-end semi-supervised approach with modulated object queries for table detection in documents
Table detection, a pivotal task in document analysis, aims to precisely recognize and locate tables within document images. Although deep learning...
-
A deep learning based cognitive model to probe the relation between psychophysics and electrophysiology of flicker stimulus
The flicker stimulus is a visual stimulus of intermittent illumination. A flicker stimulus can appear flickering or steady to a human subject,...
-
Evaluative Item-Contrastive Explanations in Rankings
The remarkable success of Artificial Intelligence in advancing automated decision-making is evident both in academia and industry. Within the...
-
Improving Likert scale big data analysis in psychometric health economics: reliability of the new compositional data approach
Bipolar psychometric scales data are widely used in psychologic healthcare. Adequate psychological profiling benefits patients and saves time and...
-
Signal processing implementation of low-cost target speed detection of CW radar using FPGA
The low-cost Continuous Wave (CW) radar architecture for object speed detection is presented in this research. An FPGA (Field-Programmable Gate...
-
Intersecting realms: a cross-disciplinary examination of VR quality of experience research
The advent of virtual reality (VR) technology has necessitated a reevaluation of quality of experience (QoE) models. While numerous recent efforts...
-
Continual learning approaches to hand–eye calibration in robots
This study addresses the problem of hand–eye calibration in robotic systems by develo** Continual Learning (CL)-based approaches. Traditionally,...