Dihu Chen
YOU?
Author Swipe
View article: UASR: An Unified-Attention Mixer Network for Efficient Image Super-Resolution
UASR: An Unified-Attention Mixer Network for Efficient Image Super-Resolution Open
Recent works in single-image super-resolution (SISR) have brought notable improvements to the field. Transformer-based methods enhance reconstruction quality by capturing long-range dependencies. However, the quadratic computational comple…
View article: Text-and-Image Learning Transformer for Cross-Modal Person Re-Identification
Text-and-Image Learning Transformer for Cross-Modal Person Re-Identification Open
Text-based person re-identification aims to find the target person from a large pedestrian gallery with the given natural language description. Previous works mainly focus on embedding salient textual and visual representations in a common…
View article: AMVFNet: Attentive Multi-View Fusion Network for 3D Object Detection
AMVFNet: Attentive Multi-View Fusion Network for 3D Object Detection Open
Pillar-based method is significant in the field of LiDAR-based 3D object detection which could directly make use of efficient 2D backbone and save computational resources during reference. Existing methods usually sequentially project the …
View article: Class‐wised domain decoupling‐guided adversarial feature learning for cross‐age face recognition
Class‐wised domain decoupling‐guided adversarial feature learning for cross‐age face recognition Open
How to extract age‐independent identity features from face images has long been the major challenge in cross‐age face recognition task. In this letter, a class‐wised domain decoupling‐guided adversarial feature learning network to extract …
View article: 9.1 µW keyword spotting processor based on optimized MFCC and small‐footprint TENet in 28‐nm CMOS
9.1 µW keyword spotting processor based on optimized MFCC and small‐footprint TENet in 28‐nm CMOS Open
This letter proposes a low‐power keyword spotting (KWS) architecture based on a modified temporal efficient neural network (TENet) and a simplified mel‐frequency cepstrum coefficient (MFCC) algorithm. The optimized MFCC algorithm reduces t…
View article: A Depthwise Separable Convolution Hardware Accelerator for ShuffleNetV2
A Depthwise Separable Convolution Hardware Accelerator for ShuffleNetV2 Open
Convolutional neural networks (CNNs) have been widely applied in the field of computer vision with the development of artificial intelligence. MobileNet and ShuffleNet, among other depthwise separable convolutional neural networks, have ga…
View article: Multi‐level cross‐modality learning framework for text‐based person re‐identification
Multi‐level cross‐modality learning framework for text‐based person re‐identification Open
The target of text‐based person re‐identification (Re‐ID) is to retrieve the corresponding image of a person through the given text information. However, due to the homogeneous variety and modality heterogeneity, it is challenging to simul…
View article: Measurement and Control System for Atomic Force Microscope Based on Quartz Tuning Fork Self-Induction Probe
Measurement and Control System for Atomic Force Microscope Based on Quartz Tuning Fork Self-Induction Probe Open
In this paper, we introduce a low-cost, expansible, and compatible measurement and control system for atomic force microscopes (AFM) based on a quartz tuning fork (QTF) self-sensing probe and frequency modulation, which is mainly composed …
View article: Imaging the Permittivity of Thin Film Materials by Using Scanning Capacitance Microscopy
Imaging the Permittivity of Thin Film Materials by Using Scanning Capacitance Microscopy Open
Recently, great advances had been made by using scanning probe microscopy (SPM) to quantify the relative permittivity of thin film materials on a nanometer scale. The imaging techniques of permittivity for thin film materials with SPM, esp…
View article: Flexible pressure and temperature dual-mode sensor based on buckling carbon nanofibers for respiration pattern recognition
Flexible pressure and temperature dual-mode sensor based on buckling carbon nanofibers for respiration pattern recognition Open
Breathing condition is an essential physiological indicator closely related to human health. Wearable flexible breath sensors for respiration pattern recognition have attracted much attention as they can provide physiological signal detail…
View article: A Configurable Accelerator for Keyword Spotting Based on Small-Footprint Temporal Efficient Neural Network
A Configurable Accelerator for Keyword Spotting Based on Small-Footprint Temporal Efficient Neural Network Open
Keyword spotting (KWS) plays a crucial role in human–machine interactions involving smart devices. In recent years, temporal convolutional networks (TCNs) have performed outstandingly with less computational complexity, in comparison with …
View article: Highly Sensitive Piezoresistive Pressure Sensor Based on Super-Elastic 3D Buckling Carbon Nanofibers for Human Physiological Signals’ Monitoring
Highly Sensitive Piezoresistive Pressure Sensor Based on Super-Elastic 3D Buckling Carbon Nanofibers for Human Physiological Signals’ Monitoring Open
The three-dimensional (3D) carbon nanostructures/foams are commonly used as active materials for the high-performance flexible piezoresistive sensors due to their superior properties. However, the intrinsic brittleness and poor sensing pro…
View article: A lightweight hardware‐efficient recurrent network for video super‐resolution
A lightweight hardware‐efficient recurrent network for video super‐resolution Open
Recent studies in the field of video super‐resolution (VSR) have taken great advantage of neural networks and achieved remarkable performance. However, current neural network‐based VSR methods have the following two limitations: (1) sophis…
View article: Part-aware network: a simple but efficient method for occluded person re-identification
Part-aware network: a simple but efficient method for occluded person re-identification Open
Person re-identification is to query person across cameras and occlusion is one of the difficulties. Previous works have proved that local feature extraction and alignment are critical for occluded person re-identification. However, direct…
View article: Attentive Part-Based Alignment Network for Vehicle Re-Identification
Attentive Part-Based Alignment Network for Vehicle Re-Identification Open
Vehicle Re-identification (Re-ID) has become a research hotspot along with the rapid development of video surveillance. Attention mechanisms are utilized in vehicle Re-ID networks but often miss the attention alignment across views. In thi…
View article: Run-Time Hierarchical Management of Mapping, Per-Cluster DVFS and Per-Core DPM for Energy Optimization
Run-Time Hierarchical Management of Mapping, Per-Cluster DVFS and Per-Core DPM for Energy Optimization Open
Heterogeneous cluster-based multi/many-core systems (e.g., ARM big.LITTLE, supporting dynamic voltage and frequency scaling (DVFS) at cluster level and dynamic power management (DPM) at core level) have attracted much attention to optimize…
View article: Up/down-conversion luminescence of monoclinic Gd<sub>2</sub>O<sub>3</sub>:Er<sup>3+</sup> nanoparticles prepared by laser ablation in liquid
Up/down-conversion luminescence of monoclinic Gd<sub>2</sub>O<sub>3</sub>:Er<sup>3+</sup> nanoparticles prepared by laser ablation in liquid Open
Multifunctional luminescent materials are attracting attention nowadays. In this work, monoclinic Gd 2 O 3 :Er 3+ nanoparticles, which possess up-conversion luminescence and down-conversion luminescence properties, were successfully synthe…
View article: Multi‐label based view learning for vehicle re‐identification
Multi‐label based view learning for vehicle re‐identification Open
Due to the high similarity of different vehicles with similar appearances and the great diversity of camera viewpoints, vehicle re‐identification (ReID) is still a challenging task. It commonly maps query set image into a high dimensional …
View article: Two‐way constraint network for RGB‐Infrared person re‐identification
Two‐way constraint network for RGB‐Infrared person re‐identification Open
RGB‐Infrared person re‐identification (RGB‐IR Re‐ID) is a task aiming to retrieve and match person images between RGB images and IR images. Since most surveillance cameras capture RGB images during the day and IR images at night, RGB‐IR Re…
View article: Image translation with dual‐directional generative adversarial networks
Image translation with dual‐directional generative adversarial networks Open
Image‐to‐image translation is a class of vision and graphics problems where the goal is to learn the mapping between input images and output images. However, due to the unstable training and limited training samples, many existing GAN‐base…
View article: Dual semantic interdependencies attention network for person re‐identification
Dual semantic interdependencies attention network for person re‐identification Open
Attention mechanisms are widely used in re‐identification (reID) tasks, but few attention‐based architectures have considered integrating local features with their global dependencies, that is the previous works do not model the semantic i…
View article: Transformer with sparse self‐attention mechanism for image captioning
Transformer with sparse self‐attention mechanism for image captioning Open
Recently, transformer has been applied to the image caption model, in which the convolutional neural network and the transformer encoder act as the image encoder of the model, and the transformer decoder acts as the decoder of the model. H…
View article: Weakly supervised video action localisation via two‐stream action activation network
Weakly supervised video action localisation via two‐stream action activation network Open
This Letter introduces a weakly supervised method for human action localisation, dubbed Two‐stream Action Activation Network (TAAN). In order to generate both action category predictions and temporal location predictions only by video‐leve…
View article: A Wide-Band Digital Lock-In Amplifier and Its Application in Microfluidic Impedance Measurement
A Wide-Band Digital Lock-In Amplifier and Its Application in Microfluidic Impedance Measurement Open
In this work, we report on the design of a wide-band digital lock-in amplifier (DLIA) of up to 65 MHz and its application for electrical impedance measurements in microfluidic devices. The DLIA is comprised of several dedicated technologie…
View article: Regional attention generative adversarial network
Regional attention generative adversarial network Open
In this Letter, the authors propose a novel attention mechanism combined with a classical generative adversarial network (GAN) model to improve the visual quality of generated samples. This novel attention model is named regional attention…
View article: Multi-Scale Proposal Regression Network for Temporal Action Proposal Generation
Multi-Scale Proposal Regression Network for Temporal Action Proposal Generation Open
Temporal action detection, as a branch of video analysis, aims to locate the time points when the actions start and end, and classify the actions occurred in videos into correct categories. Generating high-quality proposals is a key step i…
View article: Image Inpainting Based on Patch-GANs
Image Inpainting Based on Patch-GANs Open
In this paper, we propose a novel image inpainting framework that takes advantage of holistic and structure information of the broken input image. Different from the existing models that complete the broken pictures using the holistic feat…
View article: Unsupervised Object-Level Image-to-Image Translation Using Positional Attention Bi-Flow Generative Network
Unsupervised Object-Level Image-to-Image Translation Using Positional Attention Bi-Flow Generative Network Open
Recent work in unsupervised image-to-image translation by adversarially learning mapping between different domains, which cannot distinguish the foreground and background. The existing methods of image-to-image translation mainly transfer …
View article: Category-Level Adversaries for Semantic Domain Adaptation
Category-Level Adversaries for Semantic Domain Adaptation Open
Recent advances in deep learning, especially deep convolutional neural networks, have led to great performance improvement over semantic segmentation systems. Unfortunately, training deep neural networks (DNNs) requires a humongous amount …