74 Result(s)
within
Guozhen **ng
Computer Science
-
Chapter and Conference Paper
Research on General Automatic Test Platform for Onboard Automatic Train Protection
Traditional train control systems experience problems such as low efficiency, tedious operation, high labor costs, poor visibility, and difficulty in designing and maintaining test cases during manual function...
-
Chapter and Conference Paper
Transpose and Mask: Simple and Effective Logit-Based Knowledge Distillation for Multi-attribute and Multi-label Classification
Knowledge distillation (KD) improves a student network by transferring knowledge from a teacher network. Although KD has been extensively studied in single-labeled image classification, it is not well explored...
-
Chapter and Conference Paper
Automatic Search of Linear Structure: Applications to Keccak and Ascon
The linear structure technique was developed by Guo et al. at ASIACRYPT 2016, notably boosting the preimage attacks on Keccak. This technique transforming the preimage attack into solving algebraic systems allows...
-
Article
Object detection based on knowledge graph network
Object detection using convolutional neural networks addresses the recognition problem solely in terms of feature extraction and disregards knowledge and experience to explore higher-level relationships betwee...
-
Article
SMAF: a secure and makespan-aware framework for executing serverless workflows
We propose a secure and makespan-aware framework for executing serverless workflows named SMAF. SMAF can significantly help in improving the security performance in the execution of serverless workflow with li...
-
Chapter and Conference Paper
Frame Correlation Knowledge Distillation for Gait Recognition in the Wild
Recently, large deep models have achieved significant progress on gait recognition in the wild. However, such models come with a high cost of runtime and computational resource consumption. In this paper, we i...
-
Article
Software approaches for resilience of high performance computing systems: a survey
With the scaling up of high-performance computing systems in recent years, their reliability has been descending continuously. Therefore, system resilience has been regarded as one of the critical challenges f...
-
Article
AccNet: occluded scene text enhancing network with accretion blocks
Scene text with occlusions is common in the real world, and occluded text recognition is important for many machine vision applications. However, corresponding techniques are not well explored as public datase...
-
Article
Graph Searches and Their End Vertices
For a graph search algorithm, the end vertex problem is concerned with which vertices of a graph can be the last visited by this algorithm. We characterize all maximum cardinality searches on chordal graphs an...
-
Chapter and Conference Paper
Research on Cloud Office Resource Allocation Algorithm Based on Correction Weight PSO
With the development of science and technology, cloud computing technology has changed people's office methods. People begin to use cloud services to realize remote collaborative office, which can save costs a...
-
Chapter and Conference Paper
Exploring SAT for Cryptanalysis: (Quantum) Collision Attacks Against 6-Round SHA-3
In this work, we focus on collision attacks against instances of SHA-3 hash family in both classical and quantum settings. Since the 5-round collision attacks on SHA3-256 and other variants proposed by Guo et al.
-
Chapter and Conference Paper
Rebound Attacks on \(\textsf{SKINNY}\) Hashing with Automatic Tools
In ToSC’20, a new approach combining Mix-Integer Linear Programming (MILP) tool and Constraint Programming (CP) tool to search for boomerang distinguishers is proposed and later used for rebound attack in ASIA...
-
Chapter and Conference Paper
Few-Shot Knowledge Graph Entity Ty**
Knowledge graph entity ty**, which is an important way to complete knowledge graphs (KGs), aims at predicting the associating type of certain given entities without any external knowledge. However, previous ...
-
Article
Efficient detection of silent data corruption in HPC applications with synchronization-free message verification
Nowadays, high-performance computing (HPC) is step** forward to exascale era. However, silent data corruption (SDC) behaved as bit-flip** can cause disastrous consequences for scientific computation, which...
-
Article
Automated detection of retinopathy of prematurity by deep attention network
Retinopathy of prematurity (ROP) is a retinal vascular proliferative disease principally observed in infants born prematurely with low birth weight. ROP is the leading cause of childhood blindness. Early scree...
-
Article
User-level failure detection and auto-recovery of parallel programs in HPC systems
As the mean-time-between-failures (MTBF) continues to decline with the increasing number of components on large-scale high performance computing (HPC) systems, program failures might occur during the execution...
-
Chapter and Conference Paper
IPE Transformer for Depth Completion with Input-Aware Positional Embeddings
In contrast to traditional transformer blocks using a set of pre-defined parameters as positional embeddings, we propose the input-aware positional embedding (IPE) which is dynamically generated according to t...
-
Chapter and Conference Paper
Evaluation of Relationship Quality Within Dyads Through the Performance in Dual-Player Cooperative Tasks
Human beings are influenced widely by relationship among individuals. However, there is still a lack of a systematic, objective and direct way to assess the quality of relationships within dyads. The current s...
-
Chapter and Conference Paper
A Reliable Voice Perceptual Hash Authentication Algorithm
In order to protect the authenticity and integrity of voice, this paper proposes a reliable voice perceptual hash authentication algorithm. This algorithm considers the dynamic characteristics of voice signals...
-
Chapter and Conference Paper
An Automated Aggressive Posterior Retinopathy of Prematurity Diagnosis System by Squeeze and Excitation Hierarchical Bilinear Pooling Network
Aggressive Posterior Retinopathy of Prematurity (AP-ROP) is a special type of Retinopathy of Prematurity (ROP), which is one of the most common childhood blindness that occurs in premature infants. AP-ROP is u...
