Crowdsourcing in computer vision

A Kovashka, O Russakovsky, L Fei-Fei… - … and Trends® in …, 2016 - nowpublishers.com
Computer vision systems require large amounts of manually annotated data to properly
learn challenging visual concepts. Crowdsourcing platforms offer an inexpensive method to …

Blind image quality assessment based on multichannel feature fusion and label transfer

Q Wu, H Li, F Meng, KN Ngan, B Luo… - … on Circuits and …, 2015 - ieeexplore.ieee.org
In this paper, we propose an efficient blind image quality assessment (BIQA) algorithm,
which is characterized by a new feature fusion scheme and a k-nearest-neighbor (KNN) …

Examining the influence of using first-person view drones as auxiliary devices in matte painting courses on college students' continuous learning intention

C Gu, J Sun, T Chen, W Miao, Y Yang, S Lin… - Journal of Intelligence, 2022 - mdpi.com
In terms of the teaching process of matte painting, it is essential for students to develop a
sound understanding of the relationship between virtual and physical environments. In this …

The role of visual attention in sentiment prediction

S Fan, M Jiang, Z Shen, BL Koenig… - Proceedings of the 25th …, 2017 - dl.acm.org
Automated assessment of visual sentiment has many applications, such as monitoring social
media and facilitating online advertising. In current research on automated visual sentiment …

Emotional attention: From eye tracking to computational modeling

S Fan, Z Shen, M Jiang, BL Koenig… - … on Pattern Analysis …, 2022 - ieeexplore.ieee.org
Attending selectively to emotion-eliciting stimuli is intrinsic to human vision. In this research,
we investigate how emotion-elicitation features of images relate to human selective …

Image visual realism: From human perception to machine computation

S Fan, TT Ng, BL Koenig, JS Herberg… - IEEE transactions on …, 2017 - ieeexplore.ieee.org
Visual realism is defined as the extent to which an image appears to people as a photo
rather than computer generated. Assessing visual realism is important in applications like …

Perceptual texture similarity estimation: An evaluation of computational features

X Dong, J Dong, MJ Chantler - IEEE Transactions on Pattern …, 2020 - ieeexplore.ieee.org
Estimation of texture similarity is fundamental to many material recognition tasks. This study
uses fine-grained human perceptual similarity ground-truth to provide a comprehensive …

Human perception of visual realism for photo and computer-generated face images

S Fan, R Wang, TT Ng, CYC Tan, JS Herberg… - ACM Transactions on …, 2014 - dl.acm.org
Computer-generated (CG) face images are common in video games, advertisements, and
other media. CG faces vary in their degree of realism, a factor that impacts viewer reactions …

SORDI. ai: large-scale synthetic object recognition dataset generation for industries

C Abou Akar, J Tekli, J Khalil, A Yaghi… - Multimedia Tools and …, 2024 - Springer
Smart robots play a crucial role in assisting human workers within manufacturing units (like
Industry 4.0) by perceiving and analyzing their surroundings using Deep Learning (DL) …

Visual sentiment prediction with attribute augmentation and multi-attention mechanism

Z Wu, M Meng, J Wu - Neural Processing Letters, 2020 - Springer
Recently, many methods that exploit attention mechanism to discover the relevant local
regions via visual attributes, have demonstrated promising performance in visual sentiment …