Chen Ju
YOU?
Author Swipe
View article: Photonic-Assisted Simultaneous Frequency and Angle of Arrival Measurement Based on Stimulated Brillouin Scattering
Photonic-Assisted Simultaneous Frequency and Angle of Arrival Measurement Based on Stimulated Brillouin Scattering Open
The multidimensional parameter measurement of microwave signals, including temporal, spatial, and frequency, is essential for electronic warfare and radar systems. In this article, we present a photonic scheme for real-time microwave frequ…
View article: BER-Ago: A simultaneous detection and inhibitor screening platform for multiple base excision repair proteins
BER-Ago: A simultaneous detection and inhibitor screening platform for multiple base excision repair proteins Open
View article: Unsupervised Domain Adaptation via Similarity-based Prototypes for Cross-Modality Segmentation
Unsupervised Domain Adaptation via Similarity-based Prototypes for Cross-Modality Segmentation Open
Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised doma…
View article: Integrative taxonomic evidence for a new species of genus Gracixalus (Anura, Rhacophoridae) from Mao'er Mountain, Guangxi, China
Integrative taxonomic evidence for a new species of genus Gracixalus (Anura, Rhacophoridae) from Mao'er Mountain, Guangxi, China Open
It has been shown that the taxonomy of Gracixalus jinxiuensis species complex is very confusing. In this study, we tested for the taxonomy of Gracixalus species from Mao’er Mountain, Guangxi, China, which was once recorded as G. jinxiuensi…
View article: HortiVQA-PP: Multitask Framework for Pest Segmentation and Visual Question Answering in Horticulture
HortiVQA-PP: Multitask Framework for Pest Segmentation and Visual Question Answering in Horticulture Open
A multimodal interactive system, HortiVQA-PP, is proposed for horticultural scenarios, with the aim of achieving precise identification of pests and their natural predators, modeling ecological co-occurrence relationships, and providing in…
View article: Integrative taxonomic evidence for a new species of the short-legged toads Brachytarsophrys (Anura, Megophryidae) from Guangxi, China
Integrative taxonomic evidence for a new species of the short-legged toads Brachytarsophrys (Anura, Megophryidae) from Guangxi, China Open
Currently, the genus Brachytarsophrys contains nine species. In this study, we describe a new species of Brachytarsophrys , named Brachytarsophrys guilinensis sp. nov. , from northeastern Guangxi, China, based on morphological, molecular, …
View article: Weighted C-type random 2 satisfiability in discrete hopfield neural network
Weighted C-type random 2 satisfiability in discrete hopfield neural network Open
View article: Alternaria alternata botybirnavirus 1 (AaBRV1) Infection Affects the Biological Characteristics of Its Host Fungus Alternaria alternata
Alternaria alternata botybirnavirus 1 (AaBRV1) Infection Affects the Biological Characteristics of Its Host Fungus Alternaria alternata Open
A botybirnavirus, Alternaria alternata botybirnavirus 1 (AaBRV1), had been identified from Alternaria alternata strain SD-BZF-19 isolated from diseased watermelon leaves in our previous study. In the current study, AaBRV1 was eliminated fr…
View article: Detectability of the chiral gravitational wave background from audible axions with the LISA-Taiji network
Detectability of the chiral gravitational wave background from audible axions with the LISA-Taiji network Open
The chiral gravitational wave background (GWB) can be produced by axion-like fields in the early universe. We perform parameter estimation for two types of chiral GWB with the LISA-Taiji network: axion-dark photon coupling and axion-Nieh–Y…
View article: Beyond Static Scenes: Camera-controllable Background Generation for Human Motion
Beyond Static Scenes: Camera-controllable Background Generation for Human Motion Open
In this paper, we investigate the generation of new video backgrounds given a human foreground video, a camera pose, and a reference scene image. This task presents three key challenges. First, the generated background should precisely fol…
View article: Detectability of the chiral gravitational wave background from audible axions with the LISA-Taiji network
Detectability of the chiral gravitational wave background from audible axions with the LISA-Taiji network Open
The chiral gravitational wave background (GWB) can be produced by axion-like fields in the early universe. We perform parameter estimation for two types of chiral GWB with the LISA-Taiji network: axion-dark photon coupling and axion-Nieh-Y…
View article: Underestimated species diversity in Zhangixalus (Anura, Rhacophoridae) with a description of two cryptic species from southern China
Underestimated species diversity in Zhangixalus (Anura, Rhacophoridae) with a description of two cryptic species from southern China Open
It has been shown that species diversity of tree frogs in the genus Zhangixalus might have been underestimated. In this study, based on previously published data and newly collected samples from China, we constructed a phylogeny of the gen…
View article: Contrast-Unity for Partially-Supervised Temporal Sentence Grounding
Contrast-Unity for Partially-Supervised Temporal Sentence Grounding Open
Temporal sentence grounding aims to detect event timestamps described by the natural language query from given untrimmed videos. The existing fully-supervised setting achieves great results but requires expensive annotation costs; while th…
View article: Probing Spin-2 Ultralight Dark Matter with Space-based Gravitational Wave Detectors in Millihertz
Probing Spin-2 Ultralight Dark Matter with Space-based Gravitational Wave Detectors in Millihertz Open
Spin-2 ultralight dark matter (ULDM) is a viable dark matter candidate and it can be constrained using gravitational wave (GW) observations. In this paper, we investigate the detectability of spin-2 ULDM by space-based GW interferometers. …
View article: Chiral Gravitational Wave Background from Audible Axion Via Nieh-Yan Term
Chiral Gravitational Wave Background from Audible Axion Via Nieh-Yan Term Open
View article: Alternative LISA-TAIJI networks: Detectability of the Parity Violation in Stochastic Gravitational Wave Background
Alternative LISA-TAIJI networks: Detectability of the Parity Violation in Stochastic Gravitational Wave Background Open
The detection of parity violation in the isotropic stochastic gravitational wave background (SGWB) will serve a crucial probe for new physics, particularly in parity-violating theories of gravity. The joint observations by the planned spac…
View article: Chiral Gravitational Wave Background from Audible Axion via Nieh-Yan Term
Chiral Gravitational Wave Background from Audible Axion via Nieh-Yan Term Open
Axions and axion-like particles can be probed through gravitational waves indirectly, often referred to as "audible axions". The usual concept of audible axion relies on the coupling between the axions and the gauge fields. Here we conside…
View article: Circularly Polarized Gravitational Wave Background Search with a Network of Space-borne Triangular Detectors
Circularly Polarized Gravitational Wave Background Search with a Network of Space-borne Triangular Detectors Open
Circularly polarized gravitational wave backgrounds are predicted in many well-motivated models of inflation and phase transitions involving spontaneous parity violation. In this work, we investigate the detection of such parity-violating …
View article: Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models
Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models Open
Vision-Language Large Models (VLMs) recently become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in the real-world scenarios. To achiev…
View article: Enhancing Cross-Domain Click-Through Rate Prediction via Explicit Feature Augmentation
Enhancing Cross-Domain Click-Through Rate Prediction via Explicit Feature Augmentation Open
Cross-domain CTR (CDCTR) prediction is an important research topic that studies how to leverage meaningful data from a related domain to help CTR prediction in target domain. Most existing CDCTR works design implicit ways to transfer knowl…
View article: Audio-Visual Segmentation via Unlabeled Frame Exploitation
Audio-Visual Segmentation via Unlabeled Frame Exploitation Open
Audio-visual segmentation (AVS) aims to segment the sounding objects in video frames. Although great progress has been witnessed, we experimentally reveal that current methods reach marginal performance gain within the use of the unlabeled…
View article: Special major 2 satisfiability logic in discrete Hopfield neural network
Special major 2 satisfiability logic in discrete Hopfield neural network Open
The satisfiability problem (SAT) of propositional logic formulas is of great significance in computer science and artificial intelligence. It is the primary NP-complete problem that has been proved and is broadly introduced into intelligen…
View article: Research on the Comprehensive Quality of Guizhou Zao Chili Products: A Comparison of Seven Chili Varieties in Guizhou
Research on the Comprehensive Quality of Guizhou Zao Chili Products: A Comparison of Seven Chili Varieties in Guizhou Open
View article: Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models
Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models Open
Vision-Language Large Models (VLMs) have become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in real-world scenarios. To achieve accele…
View article: Enhancing Cross-domain Click-Through Rate Prediction via Explicit Feature Augmentation
Enhancing Cross-domain Click-Through Rate Prediction via Explicit Feature Augmentation Open
Cross-domain CTR (CDCTR) prediction is an important research topic that studies how to leverage meaningful data from a related domain to help CTR prediction in target domain. Most existing CDCTR works design implicit ways to transfer knowl…
View article: A Machine Learning Approach to Supply Chain Vulnerability Early Warning System: Evidence from U.S. Semiconductor Industry
A Machine Learning Approach to Supply Chain Vulnerability Early Warning System: Evidence from U.S. Semiconductor Industry Open
This paper presents a machine learning-based early warning system for detecting and predicting defects in semiconductor devices. This study integrates network research models with advanced machine learning to develop a comprehensive framew…
View article: AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation
AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation Open
Open-vocabulary semantic segmentation is a challenging task that requires segmenting novel object categories at inference time. Recent studies have explored vision-language pre-training to handle this task, but suffer from unrealistic assu…
View article: Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation
Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation Open
The goal of the audio-visual segmentation (AVS) task is to segment the sounding objects in the video frames using audio cues. However, current fusion-based methods have the performance limitations due to the small receptive field of convol…
View article: Multi-Modal Prototypes for Open-World Semantic Segmentation
Multi-Modal Prototypes for Open-World Semantic Segmentation Open
In semantic segmentation, generalizing a visual system to both seen categories and novel categories at inference time has always been practically valuable yet challenging. To enable such functionality, existing methods mainly rely on eithe…
View article: Annotation-free Audio-Visual Segmentation
Annotation-free Audio-Visual Segmentation Open
The objective of Audio-Visual Segmentation (AVS) is to localise the sounding objects within visual scenes by accurately predicting pixel-wise segmentation masks. To tackle the task, it involves a comprehensive consideration of both the dat…