Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks102 from public data
- Adversarial-Learned Loss for Domain Adaptation201
The confusion matrix is introduced, which is learned through an adversarial manner in ALDA, to reduce the gap and align the feature distributions and outperforms state-of-the-art approaches in four standard domain adaptation datasets.
- CenterCLIP185
A multi-segment token clustering algorithm to find the most representative tokens and drop the non-essential ones, which surpasses existing state-of-the-art by a large margin on typical text-video benchmarks, while reducing the training memory cost and accelerating the inference speed.
- Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models158
This study proposes ProAttack, a novel and efficient method for performing clean-label backdoor attacks based on the prompt, which uses the prompt itself as a trigger, which does not require external triggers and ensures correct labeling of poisoned samples, improving the stealthy nature of the backdoor attack.
- CLIP4STR: A Simple Baseline for Scene Text Recognition With Pre-Trained Vision-Language Model74
This work transforms CLIP into a scene text reader and introduces CLIP4STR, a simple yet effective STR method built upon image and text encoders of CLIP, achieving state-of-the-art performance on 13 STR benchmarks.
- Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models62
This work proposes TTA with feedback to rectify the model output and prevent the model from becoming blindly confident, and builds different fully TTA pipelines with RLCF to improve the zero-shot generalization ability of various VLMs.
- Stock market trend prediction using dynamical Bayesian factor graph54
A new qualitative method using the concept of dynamical Bayesian factor graph for the prediction of stock market trend is developed and demonstrated by applying it in the analysis of market trends in the US stock market and Chinese stock market with good prediction results.
- AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge53
This paper proposes AntiLeak-Bench, an automated anti-leakage benchmarking framework that significantly reduces the cost of benchmark maintenance to accommodate emerging LLMs and highlights that data contamination likely exists before LLMs' cutoff time.
- 52
- Automated ICD coding for primary diagnosis via clinically interpretable machine learning51
The model has been demonstrated its effectiveness for automated primary diagnosis coding in the Chinese context and its results are interpretable and has the potential to assist clinical coders to improve coding efficiency and quality in Chinese inpatient settings.
- 39
- Toward Better Accuracy-Efficiency Trade-Offs: Divide and Co-Training37
It is argued that increasing the number of networks (ensemble) can achieve better accuracy-efficiency trade-offs than purely increasing the width and validated with 8 different neural architectures on common benchmarks through extensive experiments.
- 35
- ES-Net: Erasing Salient Parts to Learn More in Re-Identification29
A novel network, Erasing-Salient Net (ES-Net), to learn comprehensive features by erasing the salient areas in an image by using a trainable pooling layer P-pooling that generalizes global max and global average pooling.
- 29
- 24
- 23
- 21
- 21
- 21
- SCALoss: Side and Corner Aligned Loss for Bounding Box Regression15
Side Overlap (SO) loss is proposed by maximizing the side overlap of two bounding boxes, which puts more penalty for low overlapping bounding box cases, and the Corner Distance is added into the objective function to speed up the convergence.
- 14
- 14
- 13
- 9
- 9
- Tomato Stem and Leaf Segmentation and Phenotype Parameter Extraction Based on Improved Red Billed Blue Magpie Optimization Algorithm8
An efficient and adaptive intelligent optimization framework was constructed, which is capable of optimizing data processing strategies to achieve efficient and accurate processing of tomato point cloud data and helps to improve the intelligent management in agricultural production.
- Slimmable Networks for Contrastive Self-supervised Learning8
This work introduces another one-stage solution to obtain pre-trained small models without the need for extra teachers, namely, slimmable networks for contrastive self-supervised learning (SlimCLR), and introduces three techniques to make the main parameters produce dominant gradients and sub-networks have consistent outputs.
- 8
- A Dynamic Intrusion Detection System Capable of Detecting Unknown Attacks8
Experimental results show that DUA-IDS improves the classification accuracy of flow network data with unknown traffic attacks, and can accurately distinguish unknown traffic and correctly classify known traffic.
- 8
- Remaining Useful Life Prediction for Lithium-Ion Batteries Based on Hybrid Ensembles Allied with Data-Driven Approach7
A hybrid voting ensemble that combines Gradient Boosting, Random Forest, and K-Nearest Neighbors to forecast the fading capacity trend and knee point and outperforms single deep learning methods for RUL prediction and accurately identifies the knee point is introduced.
- Virtual biopsy using CT radiomics for evaluation of disagreement in pathology between endoscopic biopsy and postoperative specimens in patients with gastric cancer: a dual-energy CT generalizability study7
CT-based radiomics nomogram showed potential as a clinical aid for predicting pathologic disagreement status between biopsy samples and resected specimens in GC, and the SECT-based radiomics model is not recommended for DECT generalization.
- SplitNet: Divide and Co-training.7
It is shown that the number of networks is a new dimension of effective model scaling, besides depth/width/resolution, and small networks can achieve better ensemble performance than the large one with few or no extra parameters or FLOPs.
- Scalable Hash From Triplet Loss Feature Aggregation For Video De-duplication7
A novel content based video segmentation identification scheme that is invariant to the underlying codec and operational bit rates is proposed, it computes robust features from a triplet loss deep learning network that captures the invariance of the same content under different coding tools and strategy, while a scalable hashing solution is developed based on Fisher Vector aggregation of the convolutional features from the Triplet loss network.
- 6
- WuDaoMM: A large-scale Multi-Modal Dataset for Pre-training models6
A large-scale multi-modal corpora named WuDaoMM, totally containing more than 650M image-text pairs is introduced and the results show that WuDaoMM can be applied as an efficient dataset for VLPMs, especially for the model in text-to-image generation task.
- AutoPINN: When AutoML Meets Physics-Informed Neural Networks6
Automated Physics-Informed Neural Networks (AutoPINN), a framework that enables the automated design of PINNs by combining AutoML and PINNs is proposed, which first tailor a search space that allows finding high-accuracy PINNs for PEC internal parameter estimation, and proposes a resource-aware search strategy to explore the search space to find the best PINN model under different resource constraints.
- Research on the Recognition of Car Models Based on Deep-learning Networks5
Based on deep-learning and artificial intelligence technology, car models recognition is very practical and could be widely used in automobile inspection, vehicle monitoring and second-hand car trading and GPU has also been applied for network training.
- Percutaneous full endoscopic C1 laminectomy for developmental atlantal stenosis with myelopathy: a case report of three cases and review of the literature4
A new minimally invasive approach; percutaneous full endoscopic C1 laminectomy (PFEC1L) is presented, for the treatment of DASM, and to consolidate the current literature on the condition to summarize its etiologies, clinical manifestations, diagnostic criteria, surgical management, and prognoses.
- 4
- 4
- Application-Aware Network Design Using Software Defined Networking for Application Performance Optimization for Big Data and Video Streaming4
A Software-Defined Network (SDN) approach in an Application-Aware Network (AAN) platform is proposed, which provides both underlying network functions and applicationlevel forwarding logics for Hadoop MapReduce and video streaming and can increase user perceived video bitrate by 100%.
- 4
- 3
- 3
- 3
- 3
- Vehicle detection in aerial image based on deep learning3
The method uses the YOLOv3 algorithm and optimizes the algorithm network, increases the number of rasters of the final predicted output, improves the detection ability of the network for dense groups, and verifies the effect by training a new model.
- 3
- 3
- 3
- A newly developed 2 mm needle arthroscope with high-definition for orthopedic outpatient knee joint examination2
The development of needle arthroscopy for outpatient knee joint examinations offers more accurate and detailed visualization of knee joint pathologies compared to traditional MRI imaging, with lower economic and time costs and provides a valuable diagnostic alternative for patients unsuitable for MRI examinations.
- 2
- Mid‐Term Efficacy and Safety of Mechanical Circulatory Support in High‐Risk Elective Chronic Total Occlusion Percutaneous Coronary Intervention: A Prospective Propensity‐Matched Cohort Study2
The present study aimed to evaluate the early and 1‐year outcomes of using percutaneous mechanical circulatory support devices in patients undergoing high‐risk chronic total occlusion (CTO) percutaneous coronary intervention (PCI) in patients undergoing high‐risk chronic total occlusion (CTO) percutaneous coronary intervention (PCI).
- Advancements in Diagnosis and Multimodal Treatment Strategies for Retroperitoneal Tumors2
This literature review aims to provide a comprehensive overview of existing research, delineating diagnostic pathways and optimal therapeutic strategies for RPT, and explores the potential of targeted therapies and immunotherapy.
- Personalized Shared Control for Automated Vehicles Considering Driving Capability and Styles2
The results show that the proposed personalized shared control system could achieve better performances in terms of different driving capabilities, styles, and complex scenarios than those only driven by human drivers or automated systems.
- Tensor-based multi-feature affinity graph learning for natural image segmentation2
A tensor-based multi-feature affinity graph learning algorithm is proposed, in which tensor is introduced in the algorithm to effectively obtain the higher-order information of image data, and the results prove that the proposed method achieves the optimal clustering performance and segmentation effect.
- Comparative Effectiveness and Safety of Ticagrelor Versus Clopidogrel for Elderly Chinese Patients Undergoing Percutaneous Coronary Intervention: A Single-Center Retrospective Cohort Study2
Ticagrelor was associated with a lower incidence of major adverse cardiovascular events than clopidogrel at 12 months in elderly Chinese patients with coronary artery disease, without a significant increase of Bleeding Academic Research Consortium bleeding events.
- 2
- 2
- A Novel Multi-Task Face Super-Resolution Framework Embedding Degraded Augmented GAN Networks2
The proposed multi-task facial super-resolution reconstruction framework embedded in a degraded augmented GAN network embeds a generative adversarial network composed of residual coding blocks in the network to solve the problem of single style and distortion of face reconstruction images caused by the training method obtained by the usual predefined degradation.
- 2
- 2
- 2
- 2
- Predictive models and analysis for webpage depth‐level dwell time2
Predicting the dwell time for a given user, page, depth triplet based on historic data collected by publishers and Factorization Machines in order to overcome the data sparsity issue and provide flexibility to add auxiliary information such as the visible area of a user's browser is proposed.
- Identifying Key Drivers of Return Reversal with Dynamical Bayesian Factor Graph2
A new method is developed to identify key drivers of return reversal by incorporating a comprehensive set of factors derived from different economic theories into one unified dynamical Bayesian factor graph, and finds that stocks with high turnover rates or high Amihud illiquidity measures have a greater probability of experiencing return reversals.
- 2
- Pixel-level binocular real-time high-precision depth estimation based on epipolar geometry constraints and resource-constrained systems1
This study proposes a binocular vision-based algorithm for high-precision depth measurement in resource-constrained hardware that achieves near-optimal solutions with significantly reduced computational load.
- Migration Learning and Multi-View Training for Low-Resource Machine Translation1
The experiments demonstrate that the model with multi-view training strategy significantly outperforms the baseline model in evaluation metrics such as BLEU, TER, and ChrF, and exhibits stronger robustness and accuracy in processing complex language structures and domain-specific terminology.
- 1
- An algorithm for abnormal behavior recognition based on sharing human target tracking features1
A novel model for abnormal behaviors recognition based on human target tracking is proposed, which implements the process of recognizing abnormal behaviors after human target tracking through feature sharing and a complete abnormal behavior recognition framework including target tracking, feature extraction, and behavior recognition is established.
- Temporal Convolutional Network-Based Model for Precision Time-Series Forecasting in Marine Fisheries1
- 1
- 1
- 1
- Analysis on Satisfaction and Influencing Factors of Traditional Chinese Medicine Medical Service Among Residents in Tianjin1
Tianjin residents have low satisfaction with TCM medical services, so it is suggested to accelerate the innovation of TCM technology, improve the effect ofTCM treatment, rationally allocate TCMmedical resources, and improve the satisfaction of residents.
- Learning Personalized Representations using Graph Convolutional Network1
This work builds a heterogeneous edge attributed graph based customers' past interactions with the invoked skills, and proposes a graph convolutional network (GCN) based model, namely Personalized Dynamic Routing Feature Encoder (PDRFE), that generates personalized customer representations learned from the built graph.
- 1
- 1
- 1
- 1
- An improved ChaCha algorithm based on quantum random numbers–
The new ChaCha is significantly improved to resist differential attacks while maintaining the high efficiency of the original ChaCha cipher, and its keystream successfully passes statistical randomness tests using the NIST and GM/T 0005-2021 standards, meeting cryptographic application requirements.
- –
- –
- Tomato seedling stem and leaf segmentation method based on an improved ResNet architecture–
The proposed X-ResNet model exhibits superior segmentation performance, demonstrating high accuracy in phenotypic trait extraction, and validates the feasibility of 3D point cloud technology for tomato phenotyping.
- –
- –
- –
- Human factor ergonomic analysis of cervical cancer intracavitary therapy transport process based on Jack virtual simulation technology–
The paper imports the three-dimensional model of intracavitary therapy transfer bed established in UG software into the ergonomics analysis software Jack and establishes the human body model that conforms to the body dimensions of patients with cervical cancer as well as thehuman body model of healthcare workers.
- –
- Ticagrelor Versus Clopidogrel in the treatment of Elderly Chinese Chronic Total Occlusion Patients Undergoing Percutaneous Coronary Intervention–
Investigation of the effectiveness and safety of Ticagrelor in comparison with Clopidogrel as an add-on therapy to Aspirin for elderly Chinese CTO patients who underwent elective PCI found it had an unfavorable effect on reducing the incidence of bleeding with the IPTW model.
- –
- –
- –
- Choose the Largest Contributor: A Fusion Coefficient Learning Network for Semantic Segmentation–
A fusion coefficient learning method that can guide us to select effective layers to fuse and is verified by massive experiments and proved to be effective on the PASCAL VOC2012, PASCal Context data set.
- –
- A Multi-view Approach for Visual Exploration of Temporal Multi-dimensional Vehicle Experiment Data–
This work introduces a new visual analytics approach to the vehicle experiment data with multi-dimensional and time-series characteristics that integrates four visualization techniques to explore potential patterns hidden in huge amounts of actual experiment data.
- Visual analysis of driving styles from vehicle experiment data–
This paper presents a multi-view approach to analyzing driving styles from vehicle experiment data with multi-dimensional and time-series characteristics, and integrates four visualizations, specialized in revealing different aspects of the driving styles.
- An improved algorithm for step counting based on Android phones–
This paper designs a method based on the combination of zero crossing detection and peak detection algorithm to detect the uplink zero point, the downlink zero point and the peak of the acceleration waveform, and count user’s step number by the dynamic threshold of the peak and time interval.
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.