Xinyu Tian
YOU?
Author Swipe
View article: Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting
Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting Open
Prompting has emerged as a practical way to adapt frozen vision-language models (VLMs) for video anomaly detection (VAD). Yet, existing prompts are often overly abstract, overlooking the fine-grained human-object interactions or action sem…
View article: Early-life glyphosate exposure impairs intestinal antioxidant status and induces growth retardation in post-hatched chicks
Early-life glyphosate exposure impairs intestinal antioxidant status and induces growth retardation in post-hatched chicks Open
View article: A fully-integrated flexible in-sensor computing circuit based on gel-gated organic electrochemical transistors
A fully-integrated flexible in-sensor computing circuit based on gel-gated organic electrochemical transistors Open
Organic electrochemical transistors (OECTs) are promising technologies for biosensing and brain-inspired computing due to their low-power signal amplification and neuron-like behavior. However, their manufacturing remains complex, especial…
View article: Antioxidant Intervention Against Microplastic Hazards
Antioxidant Intervention Against Microplastic Hazards Open
Microplastic pollution (<5 mm) poses a serious threat to the environment and human health, inducing cellular stress damage in organisms (especially through oxidative stress). The damage results from excessive reactive oxygen species and im…
View article: Green Fabrication of Phosphorus-Containing Chitosan Derivatives via One-Step Protonation for Multifunctional Flame-Retardant, Anti-Dripping, and Antibacterial Coatings on Polyester Fabrics
Green Fabrication of Phosphorus-Containing Chitosan Derivatives via One-Step Protonation for Multifunctional Flame-Retardant, Anti-Dripping, and Antibacterial Coatings on Polyester Fabrics Open
With the increasing urgency of petroleum resource scarcity and environmental challenges, the development of degradable bio-based flame retardants has become crucial for enhancing the fire safety of organic materials. In this work, a phosph…
View article: Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition
Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition Open
Few-shot adaptation for Vision-Language Models (VLMs) presents a dilemma: balancing in-distribution accuracy with out-of-distribution generalization. Recent research has utilized low-level concepts such as visual attributes to enhance gene…
View article: Generative Distribution Prediction: A Unified Approach to Multimodal Learning
Generative Distribution Prediction: A Unified Approach to Multimodal Learning Open
Accurate prediction with multimodal data-encompassing tabular, textual, and visual inputs or outputs-is fundamental to advancing analytics in diverse application domains. Traditional approaches often struggle to integrate heterogeneous dat…
View article: Speech Translation Refinement using Large Language Models
Speech Translation Refinement using Large Language Models Open
Recent advancements in large language models (LLMs) have demonstrated their remarkable capabilities across various language tasks. Inspired by the success of text-to-text translation refinement, this paper investigates how LLMs can improve…
View article: SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Models
SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Models Open
Detecting out-of-distribution (OOD) data is crucial in real-world machine learning applications, particularly in safety-critical domains. Existing methods often leverage language information from vision-language models (VLMs) to enhance OO…
View article: Supply Chain Economic Decision-Making Based on Reinforcement Learning Algorithm
Supply Chain Economic Decision-Making Based on Reinforcement Learning Algorithm Open
View article: Recent Advances in Automatic Modulation Classification Technology: Methods, Results, and Prospects
Recent Advances in Automatic Modulation Classification Technology: Methods, Results, and Prospects Open
As an essential technology for spectrum sensing and dynamic spectrum access, automatic modulation classification (AMC) is a critical step in intelligent wireless communication systems, aiming at automatically recognizing the modulation sch…
View article: Study on carbon emission calculation during the materialization phase of subway stations and comparative analysis of carbon emissions from various construction methods
Study on carbon emission calculation during the materialization phase of subway stations and comparative analysis of carbon emissions from various construction methods Open
To enhance the low-carbon construction level of subway stations, this paper, based on life cycle theory and the carbon emission factor method, summarizes the carbon emission calculation methods and relevant standards. Preliminary versions …
View article: Tumor biomarkers for diagnosis, prognosis and targeted therapy
Tumor biomarkers for diagnosis, prognosis and targeted therapy Open
Tumor biomarkers, the substances which are produced by tumors or the body’s responses to tumors during tumorigenesis and progression, have been demonstrated to possess critical and encouraging value in screening and early diagnosis, progno…
View article: Facile Fabrication of Highly Efficient Chitosan-Based Multifunctional Coating for Cotton Fabrics with Excellent Flame-Retardant and Antibacterial Properties
Facile Fabrication of Highly Efficient Chitosan-Based Multifunctional Coating for Cotton Fabrics with Excellent Flame-Retardant and Antibacterial Properties Open
Interest in the development of eco-friendly, sustainable, and convenient bio-based coatings to enhance flame retardancy and antibacterial properties in cotton fabrics is growing. In this work, chitosan was protonated at its amino groups us…
View article: Integrating generative AI into financial market prediction for improved decision making
Integrating generative AI into financial market prediction for improved decision making Open
This study provides an in-depth analysis of the model architecture and key technologies of generative artificial intelligence, combined with specific application cases, and uses conditional generative adversarial networks ( cGAN ) and time…
View article: Study on energy evolution and fractal characteristics of sandstone with different fracture dip angles under uniaxial compression
Study on energy evolution and fractal characteristics of sandstone with different fracture dip angles under uniaxial compression Open
View article: Construction of Automated Experiment Software Platform Based on Hardware Integration
Construction of Automated Experiment Software Platform Based on Hardware Integration Open
The combination of automation and biotechnology has led to the emergence of numerous automated biological experiment platforms. However, the utilization of such software necessitates the purchase of a comprehensive equipment package, which…
View article: Integrating Generative AI into Financial Market Prediction for Improved Decision Making
Integrating Generative AI into Financial Market Prediction for Improved Decision Making Open
This study provides an in-depth analysis of the model architecture and key technologies of generative artificial intelligence, combined with specific application cases, and uses conditional generative adversarial networks ( cGAN ) and time…
View article: OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments
OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments Open
Environment representations endowed with sophisticated semantics are pivotal for facilitating seamless interaction between robots and humans, enabling them to effectively carry out various tasks. Open-vocabulary maps, powered by Visual-Lan…
View article: Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques
Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques Open
In the realm of computational knowledge representation, Knowledge Graph Reasoning (KG-R) stands at the forefront of facilitating sophisticated inferential capabilities across multifarious domains. The quintessence of this research elucidat…
View article: Development of Carbon Emission Calculation Software for the Materialization Phase of Subway Stations and Research on Low-Carbon Construction Design
Development of Carbon Emission Calculation Software for the Materialization Phase of Subway Stations and Research on Low-Carbon Construction Design Open
View article: ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models
ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models Open
Although soft prompt tuning is effective in efficiently adapting Vision-Language (V&L) models for downstream tasks, it shows limitations in dealing with distribution shifts. We address this issue with Attribute-Guided Prompt Tuning (ArGue)…
View article: Deep learning assisted sparse array ultrasound imaging
Deep learning assisted sparse array ultrasound imaging Open
This study aims to restore grating lobe artifacts and improve the image resolution of sparse array ultrasonography via a deep learning predictive model. A deep learning assisted sparse array was developed using only 64 or 16 channels out o…
View article: MobileRaT: A Lightweight Radio Transformer Method for Automatic Modulation Classification in Drone Communication Systems
MobileRaT: A Lightweight Radio Transformer Method for Automatic Modulation Classification in Drone Communication Systems Open
Nowadays, automatic modulation classification (AMC) has become a key component of next-generation drone communication systems, which are crucial for improving communication efficiency in non-cooperative environments. The contradiction betw…
View article: A Spectral Approach for the Dynamic Bradley-Terry Model
A Spectral Approach for the Dynamic Bradley-Terry Model Open
The dynamic ranking, due to its increasing importance in many applications, is becoming crucial, especially with the collection of voluminous time-dependent data. One such application is sports statistics, where dynamic ranking aids in for…
View article: A Real-Time Vehicle Speed Prediction Method Based on a Lightweight Informer Driven by Big Temporal Data
A Real-Time Vehicle Speed Prediction Method Based on a Lightweight Informer Driven by Big Temporal Data Open
At present, the design of modern vehicles requires improving driving performance while meeting emission standards, leading to increasingly complex power systems. In autonomous driving systems, accurate, real-time vehicle speed prediction i…
View article: Stretchable ultrasonic arrays for the three-dimensional mapping of the modulus of deep tissue
Stretchable ultrasonic arrays for the three-dimensional mapping of the modulus of deep tissue Open
Serial assessment of the biomechanical properties of tissues can be used to aid the early detection and management of pathophysiological conditions, to track the evolution of lesions and to evaluate the progress of rehabilitation. However,…
View article: Intrinsically Stretchable Organic Electrochemical Transistors with Rigid‐Device‐Benchmarkable Performance
Intrinsically Stretchable Organic Electrochemical Transistors with Rigid‐Device‐Benchmarkable Performance Open
Intrinsically stretchable organic electrochemical transistors (OECTs) are being pursued as the next‐generation tissue‐like bioelectronic technologies to improve the interfacing with the soft human body. However, the performance of current …
View article: A General Divergence Modeling Strategy for Salient Object Detection
A General Divergence Modeling Strategy for Salient Object Detection Open
Salient object detection is subjective in nature, which implies that multiple estimations should be related to the same input image. Most existing salient object detection models are deterministic following a point to point estimation lear…
View article: Recent Advances in Bioinspired Hydrogels: Materials, Devices, and Biosignal Computing
Recent Advances in Bioinspired Hydrogels: Materials, Devices, and Biosignal Computing Open
The remarkable ability of biological systems to sense and adapt to complex environmental conditions has inspired new materials and novel designs for next-generation wearable devices. Hydrogels are being intensively investigated for their v…