Yanying Chen

dblp:135/4958 · DBLP profile ↗
← Back
12ranked-venue papers
4as first author
8since 2021 · last 2026
—ORCID · conflict

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 3 · 3 since 2021Human-computer interaction and ubiquitous computing · 3 · 3 since 2021Graphics, computer vision, multimedia, augmented reality and games · 2 · 2 since 2021Theory of computation · 2 · 2 first-authorApplied, interdisciplinary, general and emerging computing · 2 · 2 first-author
YearPublicationVenuePosition
2026 Denoising diffusion bridge for cross-modal alignment in three-dimensional scene understanding
Yong Feng 0002, Wuyang Luan, Pu Xiao, Yanying Chen, Guofan Duan, Jintao Tan, Mingliang Zhou 0001
Eng. Appl. Artif. Intell.5
2026 Enhancing surface defect detection in industrial products through few-shot learning via meta-learning
Quanyou Zhang, Yong Feng 0002, Yanying Chen, Baohua Qiang, Zhangli Lan
Eng. Appl. Artif. Intell.3
2026 Unsupervised deep metric learning based on context and attention weighting
Shiya Li, Yong Feng 0002, Pu Xiao, Shi-hao Yuan, Guofan Duan, Yanying Chen, Baohua Qiang, Xiancai Xiong, Mingliang Zhou 0001
Multim. Syst.6
2025 Variational adversarial negative sampling for multimodal knowledge graph completion
Haohui Miao, Yong Feng 0002, Yanying Chen, Guofan Duan, Baohua Qiang, Mingliang Zhou 0001
Eng. Appl. Artif. Intell.3
2025 ViLNM: Visual-Language Noise Modeling for Text-to-Image Person Retrieval
abstract
Text-to-image person retrieval (TPR) focuses on finding a specific person based on the textual description, and most methods implicitly assume the training image-text pairs are correctly aligned. In practice, the image-text pairs exist under-correlated or false-correlated due to the low quality of the images and annotation errors. Meanwhile, remarkable similarities between different person identities may lead to a mismatch between text and image. To tackle the two issues, we present a Visual-Language Noise Modeling (ViLNM) method that successfully captures robust cross-modal associations even with noise. Specifically, we design a Noise Token Aware (NTA) module that eliminates the words in the textual description that do not match the image, utilizing the matched words to establish a more reliable association. Besides, to enhance the recognition ability of the model for different person identities, we propose a Joint Inter and Intra-Modal Contrastive Loss (JII) and Local Aggregation (LA) module to increase the feature differences between different person identities. We conduct comprehensive experiments on three public benchmarks, and ViLNM performs best.
Guolin Xu, Yong Feng 0002, Yanying Chen, Guofan Duan, Mingliang Zhou 0001
IEEE Signal Process. Lett.3
2024 Chinese CSUQ: Cross-Cultural Adaptation and Evaluation of Measurement Properties
abstract
The Computer System Usability Questionnaire is one of the most popular standardized usability questionnaires used to assess the perceived usability of computer software, and it has been rigorously translated into multiple languages. This article aims to complete the cross-cultural adaptation of CSUQ in a Chinese environment and examine the psychometric characteristics. We used the forward–backward translation method to complete the initial translation, and designed the psychometric experiment according to the measurement properties required by the consensus-based standards for the selection of health measurement instruments (COSMIN). The COSMIN risk of bias checklist and updated criteria for good measurement properties were used to examine the Chinese CSUQ. The results demonstrated good performance of the Chinese CSUQ in content validity, internal structure and the remaining measurement properties. The results of the factor analysis revealed a three-factor structure, as well as any discrepancy between the Chinese CSUQ and its original version. Therefore, the Chinese CSUQ can be used confidently by Chinese usability practitioners and also serve as an effective alternative to other standardized usability scales.
Yahan Xie, Yu Qiao 0001, Zhaohui Xia, Yanying Chen
Int. J. Hum. Comput. Interact.5
2024 Using animation to develop a usability questionnaire: Scale development and psychological measurements
Yiyang Zhang 0011, Yanying Chen
Int. J. Hum. Comput. Stud.3
2023 A Longitudinal Study of Children's Perceived Usability: Methodology and Measurements
abstract
This study examines longitudinal changes in children’s perceived usability based on two aspects. First, we developed a child-friendly usability questionnaire, which used cartoons to express the questionnaire response options. This approach provides an easy-to-understand five-point scale and a filling process using magnetic blocks, which together lead to highly reliable results. Additionally, we designed a longitudinal study to investigate the children’s perceived usability according to two measurement methods (immediate and retrospective). The children’s usability increased with longer durations of usage (i.e., increased repetitions of exercises). The short-term retrospective assessments depended on the most recent experience, whereas the long-term retrospective assessments were generally more positive.
Yiyang Zhang 0011, Yanying Chen
Int. J. Hum. Comput. Interact.3
2017 Zero-Error Relaying for Primitive Relay Channels
abstract
In a primitive relay channel, a new one-shot relaying scheme termed color-and-forward is proposed that guarantees a probability of error equal to zero. This relaying scheme constructs a relaying compression graph of relay outputs based on the joint conditional distribution of the relay and destination outputs, and forwards a minimum coloring of this graph. The n-letter extension of the proposed color-and-forward scheme is shown to be optimal in the sense that it results in the smallest needed out-of-band relay to destination link rate for the overall message rate to equal the single-input multiple-output outer bound for any fixed number of channel uses. This is used to obtain an upper bound on the asymptotic minimal relay to destination link rate needed to achieve the single-input multiple-output outer bound.
Yanying Chen, Natasha Devroye
IEEE Trans. Inf. Theory1
2016 The Capacity Region of the $L$ -User Gaussian Inverse Compute-and-Forward Problem
abstract
We consider an L-user multiple access channel where transmitter m has access to the linear equation um= ⊕l=1Lfmlwlof independent messages wl∈ Fpkl with fml∈ Fp, and the destination wishes to recover all L messages. This problem may be motivated as the last hop in a network where relay nodes employ the compute-and-forward strategy and decode linear equations of messages; we seek to do the reverse and extract messages from sums over a multiple access channel. In particular, we exploit the particular form of dependencies between the equations at the different relays to improve the reliable communication rates beyond those achievable by simply forwarding all equations to the destination independently. The presented achievable rate region for the discrete memoryless channel model is shown to be capacity for the additive white Gaussian noise channel.
Yanying Chen, Yiwei Song, Natasha Devroye
IEEE Trans. Inf. Theory1
2015 On the optimality of Colour-and-Forward relaying for a class of zero-error primitive relay channels
abstract
Recently a new “Colour-and-Forward” relaying strategy was proposed for the zero-error primitive relay channel, a relay channel in which the relay to destination link is out of band and of fixed, error-free capacity. This “Colour-and-Forward” scheme forwards the colour (from a minimum colouring) of the node corresponding to its received signal. This colouring is of a carefully designed graph based on the joint distribution of the relay and destination outputs given the transmit signal. This scheme was used to provide a non-trivial upper bound on the minimum required conference link capacity to allow the overall network to achieve the single-input multi-output (SIMO) upper bound. In this paper, we strengthen the result and show that this upper bound is tight if one wants to achieve the SIMO bound in the overall network for any fixed number of channel uses.
Yanying Chen, Natasha Devroye
ISIT1
2013 The capacity region of three user Gaussian inverse-compute-and-forward channels
abstract
We consider a three user multiple access channel where transmitter m has access to the linear equation um= Σ3l = 1fmlwlof independent messages w1ϵ Fpk1, w2 ϵ Fpk2, w3 ϵ Fpk3(and fmlϵ Fp), and the destination wishes to recover all three messages. This problem is motivated as the last hop in a network where relay nodes employ the Compute-and-Forward strategy and decode linear equations of messages; we seek to do the reverse and extract messages from sums over a multiple access channel. An achievable rate region for the two user problem was previously derived; here we extend and strengthen this work to show capacity for the two and three user Gaussian channel models subject to invertability conditions on the matrix of coefficients describing the given linear equations of messages. The optimal transmission scheme is not to independently send the three equations umover the MAC but rather to exploit their special correlation structure.
Yanying Chen, Yiwei Song, Natasha Devroye
ISIT1