Chuanyi Zhang
YOU?
Author Swipe
View article: HMCFormer (hierarchical multi-scale convolutional transformer): a hybrid CNN+Transformer network for intelligent VIA screening
HMCFormer (hierarchical multi-scale convolutional transformer): a hybrid CNN+Transformer network for intelligent VIA screening Open
Cervical cancer ranks first in incidence among malignant tumors of the female reproductive system, and 80% of women who die from cervical cancer worldwide are from developing countries. Visual inspection with acetic acid (VIA) screening ba…
View article: Commentary on “Same-day discharge vs. inpatient stay in laparoscopic sleeve gastrectomy: a systematic review and meta-analysis”
Commentary on “Same-day discharge vs. inpatient stay in laparoscopic sleeve gastrectomy: a systematic review and meta-analysis” Open
View article: Commentary on “Radiomics and machine learning model for predicting overall survival in IDH wild-type glioblastoma after gross total resection: a multicenter study”
Commentary on “Radiomics and machine learning model for predicting overall survival in IDH wild-type glioblastoma after gross total resection: a multicenter study” Open
View article: Commentary on “The causal effects of primary biliary cholangitis on irritable bowel syndrome: a Mendelian randomization study”
Commentary on “The causal effects of primary biliary cholangitis on irritable bowel syndrome: a Mendelian randomization study” Open
View article: Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions
Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions Open
While densely annotated image captions significantly facilitate the learning of robust vision-language alignment, methodologies for systematically optimizing human annotation efforts remain underexplored. We introduce Chain-of-Talkers (CoT…
View article: RemoteSAM: Towards Segment Anything for Earth Observation
RemoteSAM: Towards Segment Anything for Earth Observation Open
We aim to develop a robust yet flexible visual foundation model for Earth observation. It should possess strong capabilities in recognizing and localizing diverse visual targets while providing compatibility with various input-output inter…
View article: Perfect spin-triplet pairing in two-dimensional Ising superconductors purified by indirect excitons
Perfect spin-triplet pairing in two-dimensional Ising superconductors purified by indirect excitons Open
Much research effort has been devoted to interfacial or two-dimensional (2D) superconductors, but the underlying pairing mechanisms and pairing symmetries are highly controversial in most cases. Here we propose an innovative approach to pr…
View article: Co-LLaVA: Efficient Remote Sensing Visual Question Answering via Model Collaboration
Co-LLaVA: Efficient Remote Sensing Visual Question Answering via Model Collaboration Open
Large vision language models (LVLMs) are built upon large language models (LLMs) and incorporate non-textual modalities; they can perform various multimodal tasks. Applying LVLMs in remote sensing (RS) visual question answering (VQA) tasks…
View article: Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models
Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models Open
View article: Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions
Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions Open
View article: RemoteTrimmer: Adaptive Structural Pruning for Remote Sensing Image Classification
RemoteTrimmer: Adaptive Structural Pruning for Remote Sensing Image Classification Open
Since high resolution remote sensing image classification often requires a relatively high computation complexity, lightweight models tend to be practical and efficient. Model pruning is an effective method for model compression. However, …
View article: Study on artificial intelligence recognition pre-processing algorithm for cervical cancer
Study on artificial intelligence recognition pre-processing algorithm for cervical cancer Open
INTRODUCTION: Cervical cancer is the most common malignant tumor in the female reproductive system, with the number of deaths due to cervical cancer in developing countries accounting for 80% of the global total. In China, the incidence ra…
View article: Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Images
Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Images Open
The Direct Segment Anything Model (DirectSAM) excels in class-agnostic contour extraction. In this paper, we explore its use by applying it to optical remote sensing imagery, where semantic contour extraction-such as identifying buildings,…
View article: Tissue factor (F3) gene variants and thrombotic risk among middle-aged and older adults: A population-based cohort study
Tissue factor (F3) gene variants and thrombotic risk among middle-aged and older adults: A population-based cohort study Open
Background: Tissue factor (TF), encoded by the F3 gene, is the main initiator of blood coagulation. The molecular epidemiology of the F3 gene and the relation to venous thromboembolism (VTE) remains to be determined. Objectives: The aim wa…
View article: Few-shot adaptation of multi-modal foundation models: a survey
Few-shot adaptation of multi-modal foundation models: a survey Open
Multi-modal (vision-language) models, such as CLIP, are replacing traditional supervised pre-training models (e.g., ImageNet-based pre-training) as the new generation of visual foundation models. These models with robust and aligned semant…
View article: Making Large Vision Language Models to be Good Few-shot Learners
Making Large Vision Language Models to be Good Few-shot Learners Open
Few-shot classification (FSC) is a fundamental yet challenging task in computer vision that involves recognizing novel classes from limited data. While previous methods have focused on enhancing visual features or incorporating additional …
View article: Domain-invariant Progressive Knowledge Distillation for UAV-based Object Detection
Domain-invariant Progressive Knowledge Distillation for UAV-based Object Detection Open
Knowledge distillation (KD) is an effective method for compressing models in object detection tasks. Due to limited computational capability, UAV-based object detection (UAV-OD) widely adopt the KD technique to obtain lightweight detectors…
View article: Rare and Common Genetic Variation Underlying Atrial Fibrillation Risk
Rare and Common Genetic Variation Underlying Atrial Fibrillation Risk Open
Importance Atrial fibrillation (AF) has a substantial genetic component. The importance of polygenic risk is well established, while the contribution of rare variants to disease risk warrants characterization in large cohorts. Objective To…
View article: Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models
Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models Open
Machine unlearning empowers individuals with the `right to be forgotten' by removing their private or sensitive information encoded in machine learning models. However, it remains uncertain whether MU can be effectively applied to Multimod…
View article: Group Benefits Instances Selection for Data Purification
Group Benefits Instances Selection for Data Purification Open
Manually annotating datasets for training deep models is very labor-intensive and time-consuming. To overcome such inferiority, directly leveraging web images to conduct training data becomes a natural choice. Nevertheless, the presence of…
View article: MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing
MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing Open
Multimodal knowledge editing represents a critical advancement in enhancing the capabilities of Multimodal Large Language Models (MLLMs). Despite its potential, current benchmarks predominantly focus on coarse-grained knowledge, leaving th…
View article: A large meta-analysis identifies genes associated with anterior uveitis
A large meta-analysis identifies genes associated with anterior uveitis Open
View article: Corrigendum to “Evaluation of breast cancer malignancy, prognostic factors and molecular subtypes using a continuous-time random-walk MR diffusion model” [Eur. J. Radiol. 166 (2023) 111003]
Corrigendum to “Evaluation of breast cancer malignancy, prognostic factors and molecular subtypes using a continuous-time random-walk MR diffusion model” [Eur. J. Radiol. 166 (2023) 111003] Open
View article: Incorporating Domain Knowledge Graph into Multimodal Movie Genre Classification with Self-Supervised Attention and Contrastive Learning
Incorporating Domain Knowledge Graph into Multimodal Movie Genre Classification with Self-Supervised Attention and Contrastive Learning Open
Multimodal movie genre classification has always been regarded as a demanding multi-label classification task due to the diversity of multimodal data such as posters, plot summaries, trailers and metadata. Although existing works have made…
View article: Group Benefits Instance for Data Purification
Group Benefits Instance for Data Purification Open
View article: Three Stream Based Multi-level Event Contrastive Learning for Text-Video Event Extraction
Three Stream Based Multi-level Event Contrastive Learning for Text-Video Event Extraction Open
Text-video based multimodal event extraction refers to identifying event information from the given text-video pairs. Existing methods predominantly utilize video appearance features (VAF) and text sequence features (TSF) as input informat…
View article: On the Study of Sample Complexity for Polynomial Neural Networks
On the Study of Sample Complexity for Polynomial Neural Networks Open
As a general type of machine learning approach, artificial neural networks have established state-of-art benchmarks in many pattern recognition and data analysis tasks. Among various kinds of neural networks architectures, polynomial neura…
View article: Accurate Identification of Transcription Regulatory Sequences and Genes in Coronaviruses
Accurate Identification of Transcription Regulatory Sequences and Genes in Coronaviruses Open
Transcription regulatory sequences (TRSs), which occur upstream of structural and accessory genes as well as the 5′ end of a coronavirus genome, play a critical role in discontinuous transcription in coronaviruses. We introduce two problem…
View article: A Sternoclavicular Joint-Specific Plate for the Displaced Medial-End Clavicle Fracture
A Sternoclavicular Joint-Specific Plate for the Displaced Medial-End Clavicle Fracture Open
Objectives This study aimed to introduce a sternoclavicular joint (SCJ)-specific plate for the treatment of medial-end clavicle fracture and evaluate the clinical and radiological results of this method. Methods From January 2006 to Decemb…
View article: The efficacy and safety of anterior versus posterior approach for the treatment of thoracolumbar burst fractures: a systematic review and meta-analysis
The efficacy and safety of anterior versus posterior approach for the treatment of thoracolumbar burst fractures: a systematic review and meta-analysis Open
The posterior approach appeared to be superior to the anterior approach in the treatment of TBFs. However, more high-quality randomized controlled trials should be conducted to confirm the conclusions of this study and guide clinical decis…