Zhiming Ding
YOU?
Author Swipe
View article: Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay
Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay Open
Continually adapting edge models in cloud-edge collaborative object detection for traffic monitoring suffers from catastrophic forgetting, where models lose previously learned knowledge when adapting to new data distributions. This is espe…
View article: High-Quality Pseudo-Label Generation Based on Visual Prompt Assisted Cloud Model Update
High-Quality Pseudo-Label Generation Based on Visual Prompt Assisted Cloud Model Update Open
Generating high-quality pseudo-labels on the cloud is crucial for cloud-edge object detection, especially in dynamic traffic monitoring where data distributions evolve. Existing methods often assume reliable cloud models, neglecting potent…
View article: Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach
Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach Open
Prompt trading has emerged as a significant intellectual property concern in recent years, where vendors entice users by showcasing sample images before selling prompt templates that can generate similar images. This work investigates a cr…
View article: Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach
Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach Open
View article: MindRef: Mimicking Human Memory for Hierarchical Reference Retrieval with Fine-Grained Location Awareness
MindRef: Mimicking Human Memory for Hierarchical Reference Retrieval with Fine-Grained Location Awareness Open
View article: Extract Information from Hybrid Long Documents Leveraging LLMs: A Framework and Dataset
Extract Information from Hybrid Long Documents Leveraging LLMs: A Framework and Dataset Open
Large Language Models (LLMs) demonstrate exceptional performance in textual understanding and tabular reasoning tasks. However, their ability to comprehend and analyze hybrid text, containing textual and tabular data, remains unexplored. T…
View article: Dynamic Disentangled Fusion Network for RGBT Tracking
Dynamic Disentangled Fusion Network for RGBT Tracking Open
RGBT tracking usually suffers from various challenging factors of low resolution, similar appearance, extreme illumination, thermal crossover and occlusion, to name a few. Existing works often study complex fusion models to handle challeng…
View article: StraGo: Harnessing Strategic Guidance for Prompt Optimization
StraGo: Harnessing Strategic Guidance for Prompt Optimization Open
Prompt engineering is pivotal for harnessing the capabilities of large language models (LLMs) across diverse applications. While existing prompt optimization methods improve prompt effectiveness, they often lead to prompt drifting, where n…
View article: Research on the Spatial Data Intelligent Foundation Model
Research on the Spatial Data Intelligent Foundation Model Open
This report focuses on spatial data intelligent large models, delving into the principles, methods, and cutting-edge applications of these models. It provides an in-depth discussion on the definition, development history, current status, a…
View article: A Clustering Method with Graph Maximum Decoding Information
A Clustering Method with Graph Maximum Decoding Information Open
The clustering method based on graph models has garnered increased attention for its widespread applicability across various knowledge domains. Its adaptability to integrate seamlessly with other relevant applications endows the graph mode…
View article: A Hybrid Control Path Planning Architecture Based on Traffic Equilibrium Assignment for Emergency
A Hybrid Control Path Planning Architecture Based on Traffic Equilibrium Assignment for Emergency Open
Unconventional events exacerbate the imbalance between regional transportation demand and limited road network resources. Scientific and efficient path planning serves as the foundation for rapidly restoring equilibrium to the road network…
View article: Query Optimization in Distributed Database Based on Improved Artificial Bee Colony Algorithm
Query Optimization in Distributed Database Based on Improved Artificial Bee Colony Algorithm Open
Query optimization is one of the key factors affecting the performance of database systems that aim to enact the query execution plan with minimum cost. Particularly in distributed database systems, due to the multiple copies of the data t…
View article: AIOT Пространственно-временное управление данными и анализ данных
AIOT Пространственно-временное управление данными и анализ данных Open
В докладе представлены основные проблемы и решения AIoT (AI+IOT), а также его применения и перспективы
View article: Next Point-of-Interest Recommendation Based on Joint Mining of Spatial–Temporal and Semantic Sequential Patterns
Next Point-of-Interest Recommendation Based on Joint Mining of Spatial–Temporal and Semantic Sequential Patterns Open
With the widespread use of the location-based social networks (LBSNs), the next point-of-interest (POI) recommendation has become an essential service, which aims to understand the user’s check-in behavior at the current moment by analyzin…
View article: Small Temperature is All You Need for Differentiable Architecture Search
Small Temperature is All You Need for Differentiable Architecture Search Open
Differentiable architecture search (DARTS) yields highly efficient gradient-based neural architecture search (NAS) by relaxing the discrete operation selection to optimize continuous architecture parameters that maps NAS from the discrete …
View article: Rethink DARTS Search Space and Renovate a New Benchmark
Rethink DARTS Search Space and Renovate a New Benchmark Open
DARTS search space (DSS) has become a canonical benchmark for NAS whereas some emerging works pointed out the issue of narrow accuracy range and claimed it would hurt the method ranking. We observe some recent studies already suffer from t…
View article: Domain-adaptive graph neural network for few-shot learning
Domain-adaptive graph neural network for few-shot learning Open
The task of few-shot classification (FSC) is to build a model to discriminate novel categories that do not present in training categories with limited labeled samples. However, in many applications, the training categories and novel catego…
View article: Enabling and Analyzing How to Efficiently Extract Information from Hybrid Long Documents with LLMs
Enabling and Analyzing How to Efficiently Extract Information from Hybrid Long Documents with LLMs Open
Large Language Models (LLMs) demonstrate exceptional performance in textual understanding and tabular reasoning tasks. However, their ability to comprehend and analyze hybrid text, containing textual and tabular data, remains underexplored…
View article: Data from AURKA Governs Self-Renewal Capacity in Glioma-Initiating Cells via Stabilization/Activation of β-catenin/Wnt Signaling
Data from AURKA Governs Self-Renewal Capacity in Glioma-Initiating Cells via Stabilization/Activation of β-catenin/Wnt Signaling Open
Glioma-initiating cells (GIC), which are characterized by their self-renewal capacity and tumorigenicity, were recently identified as a highly tumorigenic subpopulation of glioblastoma multiforme and are considered responsible for glioblas…
View article: Data from AURKA Governs Self-Renewal Capacity in Glioma-Initiating Cells via Stabilization/Activation of β-catenin/Wnt Signaling
Data from AURKA Governs Self-Renewal Capacity in Glioma-Initiating Cells via Stabilization/Activation of β-catenin/Wnt Signaling Open
Glioma-initiating cells (GIC), which are characterized by their self-renewal capacity and tumorigenicity, were recently identified as a highly tumorigenic subpopulation of glioblastoma multiforme and are considered responsible for glioblas…
View article: Supplementary Table 1, Figures 1 - 8 from AURKA Governs Self-Renewal Capacity in Glioma-Initiating Cells via Stabilization/Activation of β-catenin/Wnt Signaling
Supplementary Table 1, Figures 1 - 8 from AURKA Governs Self-Renewal Capacity in Glioma-Initiating Cells via Stabilization/Activation of β-catenin/Wnt Signaling Open
PDF file - 2835K, Supplementary Table 1. Differentially regulated Wnt signaling genes by AURKA identified by q-PCR. Supplementary Fig. 1. AURKA and stem cell markers' expressions in mouse model tumor samples. Supplementary Fig. 2. Stem cel…
View article: Supplementary Table 1, Figures 1 - 8 from AURKA Governs Self-Renewal Capacity in Glioma-Initiating Cells via Stabilization/Activation of β-catenin/Wnt Signaling
Supplementary Table 1, Figures 1 - 8 from AURKA Governs Self-Renewal Capacity in Glioma-Initiating Cells via Stabilization/Activation of β-catenin/Wnt Signaling Open
PDF file - 2835K, Supplementary Table 1. Differentially regulated Wnt signaling genes by AURKA identified by q-PCR. Supplementary Fig. 1. AURKA and stem cell markers' expressions in mouse model tumor samples. Supplementary Fig. 2. Stem cel…
View article: Skyline-Based Sorting Approach for Rail Transit Stations Visualization
Skyline-Based Sorting Approach for Rail Transit Stations Visualization Open
Urban rail transit is an essential part of the urban public transportation system. The reasonable spatial data visualization of urban rail transit stations can provide a more intuitive way for the majority of travelers to arrange travel pl…
View article: Latent Semantic Sequence Coding Applied to Taxi Travel Time Estimation
Latent Semantic Sequence Coding Applied to Taxi Travel Time Estimation Open
Taxi travel time estimation based on real-time traffic flow collection in IoT has been well explored; however, it becomes a challenge to use the limited taxi data to estimate the travel time. Most of the existing methods in this scenario r…
View article: A Novel Traffic Flow Reduction Method Based on Incomplete Vehicle History Spatio-Temporal Trajectory Data
A Novel Traffic Flow Reduction Method Based on Incomplete Vehicle History Spatio-Temporal Trajectory Data Open
In order to improve the effect of path planning in emergencies, the missing position imputation and velocity restoration in vehicle trajectory provide data support for emergency path planning and analysis. At present, there are many method…
View article: A Novel Trajectory Based Prediction Method for Urban Subway Design
A Novel Trajectory Based Prediction Method for Urban Subway Design Open
In recent years, with the development of various types of public transportation, they are also more and more closely connected. Among them, subway transportation has become the first choice of major cities. However, the planning of subway …
View article: Emergency logistics scheduling with multiple supply-demand points based on grey interval
Emergency logistics scheduling with multiple supply-demand points based on grey interval Open
This study aimed to address the problem of post-disaster emergency material dispatching from multiple supply points to multiple demand points. In large-scale natural disasters, it is very important for multiple emergency material supply po…
View article: An Internet of Things based scalable framework for disaster data management
An Internet of Things based scalable framework for disaster data management Open
View article: A Continuous Taxi Pickup Path Recommendation under The Carbon Neutrality Context
A Continuous Taxi Pickup Path Recommendation under The Carbon Neutrality Context Open
In the context of the carbon neutrality target, carbon reduction in the daily operation of the transportation system is more important than that in productive activities. There are few travel services that can quantify low-carbon travel, w…
View article: Robustifying DARTS by Eliminating Information Bypass Leakage via Explicit Sparse Regularization
Robustifying DARTS by Eliminating Information Bypass Leakage via Explicit Sparse Regularization Open
Differentiable architecture search (DARTS) is a promising end to end NAS\nmethod which directly optimizes the architecture parameters through general\ngradient descent. However, DARTS is brittle to the catastrophic failure\nincurred by the…