138 Result(s)
within
Chapter
Jie CHEN
Computer Science
-
Chapter and Conference Paper
Dynamic Gesture Recognition Based on 3D Central Difference Separable Residual LSTM Coordinate Attention Networks
The recognition of dynamic gestures has garnered significant attention in the field of human-computer interaction. However, several factors unrelated to the gestures, such as background, and spatial scale, pos...
-
Chapter and Conference Paper
Object-Aware Transfer-Based Black-Box Adversarial Attack on Object Detector
Deep neural networks have been demonstrated to be vulnerable to adversarial noise from attacks. Compared with white-box attacks, black-box attacks fool deep neural networks to yield erroneous predictions witho...
-
Chapter and Conference Paper
Two-Stage Deep Learning Segmentation for Tiny Brain Regions
Accurate segmentation of brain regions has become increasingly important in the early diagnosis of brain diseases. Widely used methods for brain region segmentation usually rely on atlases and deformations, wh...
-
Chapter and Conference Paper
AST: An Attention-Guided Segment Transformer for Drone-Based Cross-View Geo-Localization
To tackle the problem of drone-based cross-view geo-localization, we address how to match drone-view images and satellite-view images, which is extremely challenging due to the variability of view angles and v...
-
Chapter and Conference Paper
CCA-Secure Identity-Based Matchmaking Encryption from Standard Assumptions
Identity-based Matchmaking Encryption (IB-ME) is a new form of encryption that enables anonymous communication by specifying identities for both sender and receiver. Its applications in network services put fo...
-
Chapter and Conference Paper
OD-Enhanced Dynamic Spatial-Temporal Graph Convolutional Network for Metro Passenger Flow Prediction
Metro passenger flow prediction is crucial for efficient urban transportation planning and resource allocation. However, it faces two challenges. The first challenge is extracting the diverse passenger flow pa...
-
Chapter and Conference Paper
Public-Key Encryption with Keyword Search in Multi-user, Multi-challenge Setting under Adaptive Corruptions
In the past decade, much progress has been made on proposing encryption schemes with multi-user security. However, no known work aims at constructing a Public-key Encryption with Keyword Search (PEKS) scheme t...
-
Chapter and Conference Paper
Registered Attribute-Based Signature
This paper introduces the notion of registered attribute-based signature (registered ABS). Distinctly different from classical attribute-based signature (ABS), registered ABS allows any user to generate their own...
-
Chapter and Conference Paper
Leakage-Resilient Attribute-Based Encryption with Attribute-Hiding
In this work, we present two generic frameworks for leakage-resilient attribute-based encryption (ABE), which is an improved version of ABE that can be proven secure even when part of the secret key is leaked....
-
Chapter and Conference Paper
Unsupervised KeyPhrase Extraction Based on Multi-granular Semantics Feature Fusion
In Unsupervised Keyphrase Extraction (UKE) tasks, candidate phrases are ranked based on their similarity to the document embedding. However, This method assumes that every document focuses on only one topic. A...
-
Chapter and Conference Paper
Improved Fully Adaptive Decentralized MA-ABE for NC1 from MDDH
We improve the first and the only existing prime-order fully adaptively secure decentralized Multi-Authority Attribute-Based Encryption (MA-ABE) scheme for NC1 in Datta-Komargodski-Waters [Eurocrypt ’23]. Comp...
-
Chapter and Conference Paper
M2MTR: Reposition Idle Taxis in the Many-to-Many Manner with Multi-agent Reinforcement Learning
Ride-hailing apps, such as Didi and Uber, allow people to easily request a ride by inputting their desired origin and destination locations. Due to transportation system complexity and vast city areas, uneven ...
-
Chapter and Conference Paper
A Coverless Image Steganography Method Based on Feature Matrix Map**
To address the challenge that the current coverless image steganography (CIS) method requires more cover images and more information, a coverless image steganography method based on feature matrix map** is p...
-
Chapter and Conference Paper
Adaptive Deep Learning Approximation for Allen-Cahn Equation
Solving general non-linear partial differential equations (PDE) precisely and efficiently has been a long-lasting challenge in the field of scientific computing. Based on the deep learning framework for solvin...
-
Chapter and Conference Paper
OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark Under Heterogeneous AI Computing Platforms
In this paper, we present OpenMedIA, an open-source toolbox library containing a rich set of deep learning methods for medical image analysis under heterogeneous Artificial Intelligence (AI) computing platform...
-
Chapter and Conference Paper
A Survey of Traffic Classification Technology for Smart Home Based on Machine Learning
With the wide use of smart home devices and the privacy of their activities, more and more research have focused on the traffic classification for smart home, and traffic classification technology can infer th...
-
Chapter and Conference Paper
An Inclusive Task-Aware Framework for Radiology Report Generation
To avoid the tedious and laborious radiology report writing, the automatic generation of radiology reports has drawn great attention recently. Previous studies attempted to directly transfer the image captioni...
-
Chapter and Conference Paper
Using User’s Expression Propensity for Sarcasm Detection Based on Sequential Three-Way Decision
Sarcasm detection is mainly to distinguish whether the target comment is sarcasm that can help identify the actual sentiment. The previous sarcasm detection mainly focused on text features using vocabulary, gr...
-
Chapter and Conference Paper
When Active Learning Meets Implicit Semantic Data Augmentation
Active learning (AL) is a label-efficient technique for training deep models when only a limited labeled set is available and the manual annotation is expensive. Implicit semantic data augmentation (ISDA) effe...
-
Chapter and Conference Paper
Temporal-MPI: Enabling Multi-plane Images for Dynamic Scene Modelling via Temporal Basis Learning
Novel view synthesis of static scenes has achieved remarkable advancements in producing photo-realistic results. However, key challenges remain for immersive rendering of dynamic scenes. One of the seminal ima...
