Zhen Zhao
YOU?
Author Swipe
View article: Capital logic, consumption, and anxiety: Rereading fromm in contemporary psychology
Capital logic, consumption, and anxiety: Rereading fromm in contemporary psychology Open
This paper revisits Erich Fromm’s theory of social psychoanalysis to exam- ine the persistence of psychological distress in contemporary societies shaped by capital logic and consumer culture. There is a fundamental difference between Fromm…
View article: Targeted therapy for knee osteoarthritis: From basic to clinics
Targeted therapy for knee osteoarthritis: From basic to clinics Open
As the aging population grows and lifestyle factors become more prevalent, the incidence of knee osteoarthritis (KOA) is expected to continue to increase in the coming decades. This presents a substantial public health challenge with an im…
View article: Deep cross entropy fusion for pulmonary nodule classification based on ultrasound Imagery
Deep cross entropy fusion for pulmonary nodule classification based on ultrasound Imagery Open
Introduction Accurate differentiation of benign and malignant pulmonary nodules in ultrasound remains a clinical challenge due to insufficient diagnostic precision. We propose the Deep Cross-Entropy Fusion (DCEF) model to enhance classific…
View article: TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting
TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting Open
Real-world time series often have multiple frequency components that are intertwined with each other, making accurate time series forecasting challenging. Decomposing the mixed frequency components into multiple single frequency components…
View article: Identification of 4876 Bent-tail Radio Galaxies in the FIRST Survey Using Deep Learning Combined with Visual Inspection
Identification of 4876 Bent-tail Radio Galaxies in the FIRST Survey Using Deep Learning Combined with Visual Inspection Open
Bent-tail radio galaxies (BTRGs) are characterized by bent radio lobes. This unique shape is mainly caused by the movement of the galaxy within a cluster, during which the radio jets are deflected by the intracluster medium. A combined met…
View article: A Turbo-Inference Strategy for Object Detection and Instance Segmentation
A Turbo-Inference Strategy for Object Detection and Instance Segmentation Open
View article: Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation
Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation Open
View article: Chinese patent medicine for atherosclerosis: a systematic review and Meta-analysis of randomized controlled trials.
Chinese patent medicine for atherosclerosis: a systematic review and Meta-analysis of randomized controlled trials. Open
CPM could have certain clinical efficacy in the treatment of AS. However, more double-blinded placebo-controlled RCTs are required in further evaluations to provide stronger evidence.
View article: Proceedings of the 32nd ACM International Conference on Multimedia
Proceedings of the 32nd ACM International Conference on Multimedia Open
A plethora of text-guided image editing methods has recently been developed by leveraging the impressive capabilities of large-scale diffusion-based generative models especially Stable Diffusion. Despite the success of diffusion models in …
View article: UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation Open
Semi-supervised semantic segmentation (SSS) aims at learning rich visual knowledge from cheap unlabeled images to enhance semantic segmentation capability. Among recent works, UniMatch improves its precedents tremendously by amplifying the…
View article: PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis
PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis Open
Point cloud analysis has seen substantial advancements due to deep learning, although previous Transformer-based methods excel at modeling long-range dependencies on this task, their computational demands are substantial. Conversely, the M…
View article: Training-Free Unsupervised Prompt for Vision-Language Models
Training-Free Unsupervised Prompt for Vision-Language Models Open
Prompt learning has become the most effective paradigm for adapting large pre-trained vision-language models (VLMs) to downstream tasks. Recently, unsupervised prompt tuning methods, such as UPL and POUF, directly leverage pseudo-labels as…
View article: Roll with the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning
Roll with the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning Open
While semi-supervised learning (SSL) has yielded promising results, the more realistic SSL scenario remains to be explored, in which the unlabeled data exhibits extremely high recognition difficulty, e.g., fine-grained visual classificatio…
View article: van Hove Singularity-Driven Emergence of Multiple Flat Bands in Kagome Superconductors
van Hove Singularity-Driven Emergence of Multiple Flat Bands in Kagome Superconductors Open
The newly discovered Kagome superconductors AV$_3$Sb$_5$ (A=K, Rb and Cs) continue to bring surprises in generating unusual phenomena and physical properties, including anomalous Hall effect, unconventional charge density wave, electronic …
View article: Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation
Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation Open
Improving data utilization, especially for imperfect data from task failures, is crucial for robotic manipulation due to the challenging, time-consuming, and expensive data collection process in the real world. Current imitation learning (…
View article: Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning
Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning Open
While semi-supervised learning (SSL) has yielded promising results, the more realistic SSL scenario remains to be explored, in which the unlabeled data exhibits extremely high recognition difficulty, e.g., fine-grained visual classificatio…
View article: Alternate Diverse Teaching for Semi-supervised Medical Image Segmentation
Alternate Diverse Teaching for Semi-supervised Medical Image Segmentation Open
Semi-supervised medical image segmentation studies have shown promise in training models with limited labeled data. However, current dominant teacher-student based approaches can suffer from the confirmation bias. To address this challenge…
View article: Clean Label Disentangling for Medical Image Segmentation with Noisy Labels
Clean Label Disentangling for Medical Image Segmentation with Noisy Labels Open
Current methods focusing on medical image segmentation suffer from incorrect annotations, which is known as the noisy label issue. Most medical image segmentation with noisy labels methods utilize either noise transition matrix, noise-robu…
View article: Progressive Classifier and Feature Extractor Adaptation for Unsupervised Domain Adaptation on Point Clouds
Progressive Classifier and Feature Extractor Adaptation for Unsupervised Domain Adaptation on Point Clouds Open
Unsupervised domain adaptation (UDA) is a critical challenge in the field of point cloud analysis. Previous works tackle the problem either by feature extractor adaptation to enable a shared classifier to distinguish domain-invariant featu…
View article: GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation
GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation Open
While the recent advances in Multimodal Large Language Models (MLLMs) constitute a significant leap forward in the field, these models are predominantly confined to the realm of input-side multimodal comprehension, lacking the capacity for…
View article: Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer
Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer Open
Scene text recognition (STR) in the wild frequently encounters challenges when coping with domain variations, font diversity, shape deformations, etc. A straightforward solution is performing model fine-tuning tailored to a specific scenar…
View article: Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning
Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning Open
In semi-supervised learning, unlabeled samples can be utilized through augmentation and consistency regularization. However, we observed certain samples, even undergoing strong augmentation, are still correctly classified with high confide…
View article: Rethinking Data Perturbation and Model Stabilization for Semi-supervised Medical Image Segmentation
Rethinking Data Perturbation and Model Stabilization for Semi-supervised Medical Image Segmentation Open
Studies on semi-supervised medical image segmentation (SSMIS) have seen fast progress recently. Due to the limited labelled data, SSMIS methods mainly focus on effectively leveraging unlabeled data to enhance the segmentation performance. …
View article: Towards Semi-supervised Learning with Non-random Missing Labels
Towards Semi-supervised Learning with Non-random Missing Labels Open
Semi-supervised learning (SSL) tackles the label missing problem by enabling the effective usage of unlabeled data. While existing SSL methods focus on the traditional setting, a practical and challenging scenario called label Missing Not …
View article: Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning
Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning Open
Semi-supervised learning is attracting blooming attention, due to its success in combining unlabeled data. To mitigate potentially incorrect pseudo labels, recent frameworks mostly set a fixed confidence threshold to discard uncertain samp…
View article: Radio sources segmentation and classification with deep learning
Radio sources segmentation and classification with deep learning Open
Modern large radio continuum surveys have high sensitivity and resolution, and can resolve previously undetected extended and diffuse emissions, which brings great challenges for the detection and morphological classification of extended s…
View article: Radio Sources Segmentation and Classification with Deep Learning
Radio Sources Segmentation and Classification with Deep Learning Open
Modern large radio continuum surveys have high sensitivity and resolution, and can resolve previously undetected extended and diffuse emissions, which brings great challenges for the detection and morphological classification of extended s…
View article: Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models
Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models Open
Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an appropr…
View article: Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation
Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation Open
Semi-supervised semantic segmentation (SSS) has recently gained increasing research interest as it can reduce the requirement for large-scale fully-annotated training data. The current methods often suffer from the confirmation bias from t…
View article: Application Environment of Ethnic Art Elements in Multi-type Film Making
Application Environment of Ethnic Art Elements in Multi-type Film Making Open
As one of the unique national elements, national art elements are worthy of reference and application in film art creation.The film makers apply the characteristic national art elements to the film making process.It can not only improve th…