Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks160 from public data
- 548
- 449
- 438
- Unbiased Mean Teacher for Cross-domain Object Detection423
A new Unbiased Mean Teacher (UMT) model for cross-domain object detection is proposed, revealing that there often exists a considerable model bias for the simple mean teacher (MT) model in cross- domain scenarios, and eliminating the model bias with several simple yet highly effective strategies.
- Domain adaptation from multiple sources via auxiliary classifiers339
A new data-dependent regularizer based on smoothness assumption into Least-Squares SVM (LS-SVM), which enforces that the target classifier shares similar decision values with the auxiliary classifiers from relevant source domains on the unlabeled patterns of the target domain.
- 338
- 306
- 254
- 245
- 243
- Constructing Self-Motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach239
This work proposes a new approach, called self-motivated pyramid curriculum domain adaptation (PyCDA), to facilitate the adaptation of semantic segmentation neural networks from synthetic source domains to real target domains and reports state-of-the-art results for the adaptation from both GTAV and SYNTHIA to Cityscapes.
- 216
- 215
- An experimental study on breast lesion detection and classification from ultrasound images using deep learning architectures179
Evaluating several existing state-of-the-art object detection and classification methods for breast lesions CAD reveals that better and more efficient detection and convolutional neural network (CNN) frameworks is one important factor for better performance of detecting and classification task of the breast lesion.
- STST: Spatial-Temporal Specialized Transformer for Skeleton-based Action Recognition147
A multi-task self-supervised learning method is proposed by providing confusing samples in different situations to improve the robustness of the model and demonstrate the improved performances and analysis of the proposed method.
- 127
- 121
- Webly-Supervised Video Recognition by Mutually Voting for Relevant Web Images and Web Video Frames104
A novel approach to mutually voting for relevant Web images and video frames, where two forces are balanced, i.e. aggressive matching and passive video frame selection is proposed and validated on three large-scale video recognition datasets.
- A survey on computer aided diagnosis for ocular diseases96
While CAD for ocular diseases has shown considerable progress over the past years, the clinical importance of fully automatic CAD systems which are able to embed clinical knowledge and integrate heterogeneous data sources still show great potential for future breakthrough.
- 95
- 95
- 92
- 85
- Detecting retinal microaneurysms and hemorrhages with robustness to the presence of blood vessels81
Improved lesion detection using the proposed approach can help in automatic detection of Diabetic Retinopathy by applying the proposed filters on patches of different sizes instead of filtering the full image.
- Optic Cup Segmentation for Glaucoma Detection Using Low-Rank Superpixel Representation73
This work presents an unsupervised approach to segment optic cups in fundus images for glaucoma detection without using any additional training images and develops an adaptive strategy for automatically choosing the only parameter in LRR and obtaining the final result for each image.
- Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report69
The target is to develop an end-to-end deep learning-based video super-resolution solutions that can achieve a realtime performance on mobile GPUs and can upscale videos to HD resolution at up to 80 FPS while demonstrating high fidelity results.
- Learning Transferable Self-Attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision68
A novel weakly supervised framework to simultaneously locate action frames as well as recognize actions in untrimmed videos, which takes advantage of the self-attention mechanism to weight each frame, such that the influence of background frames can be effectively eliminated.
- Dynamic and Static Context-Aware LSTM for Multi-agent Motion Prediction65
This paper designs a new mechanism, the Dynamic and Static Context-aware Motion Predictor (DSCMP), to integrates these rich information into the long-short-term-memory (LSTM), which captures the context of scene by inferring latent variable, which enables multimodal predictions with meaningful semantic scene layout.
- Breast Tumor Detection in Ultrasound Images Using Deep Learning64
Comprehensive experimental results clearly show that the recently proposed convolutional neural network based method, Single Shot MultiBox Detector (SSD), outperforms other methods in terms of both precision and recall.
- Domain Adversarial Reinforcement Learning for Partial Domain Adaptation60
This work proposes a domain adversarial reinforcement learning (DARL) framework to progressively select source instances to learn transferable features between domains by reducing the domain shift and employs a deep Q-learning to learn policies for an agent to make selection decisions by approximating the action-value function.
- 58
- 57
- Structure-Aware Motion Transfer with Deformable Anchor Model51
A novel structure-aware motion modeling approach, the deformable anchor model (DAM), which can automatically discover the motion structure of arbitrary objects without leveraging their prior structure information and achieves superior performance relative to existing state-of-the-art methods.
- 51
- 50
- 45
- 42
- Reconstruction Regularized Deep Metric Learning for Multi-Label Image Classification39
A novel deep metric learning method to tackle the multi-label image classification problem by attempting to explore a latent space, where images and labels are embedded via two unique deep neural networks, respectively, to capture the relationships between image features and labels.
- 38
- Hybrid constraint SVR for facial age estimation36
F fuzzy age label is firstly defined, and it is then merged into the Support Vector Regression framework together with the traditional data labels, and the new learning problem is formulated into a similar dual form with the standard SVR, which can be easily solved using existing solvers.
- Integration of artificial intelligence and multi-omics in kidney diseases35
This review discusses how AI and multi-omics can be applied and integrated, to offer opportunities to develop novel diagnostic and therapeutic means in kidney diseases.
- Multi-rater Prism: Learning self-calibrated medical image segmentation from multiple raters34
A novel neural network framework called Multi-rater Prism (MrPrism) is proposed to learn medical image segmentation from multiple labels and outperforms state-of-the-art (SOTA) methods for a wide range of medical image segmentation tasks.
- Learning Pixel-Level Distinctions for Video Highlight Detection32
An encoder-decoder network is designed to estimate the pixel-level distinction, in which the 3D convolutional neural networks are used to exploit the temporal context information, and further take advantage of the visual saliency to model the spatial distinction.
- 32
- 32
- Reproducibility of deep learning based scleral spur localisation and anterior chamber angle measurements from anterior segment optical coherence tomography images30
D LLSS achieved comparable repeatability compared with MPSS for measurement of anterior chamber angle (ACA) width between deep learning located SS (DLLSS) and manually plotted SS (MPSS), and the repeatability of ACA width was measured.
- 30
- Learning cross-domain semantic-visual relationships for transductive zero-shot learning29
The Transferrable Semantic-Visual Relation (TSVR) approach towards transductive ZSL is proposed, which redefines image recognition as predicting the similarity/dissimilarity labels for semantic-visual fusions consisting of class attributes and visual features.
- 29
- TarGAN: Generating target data with class labels for unsupervised domain adaptation28
A new unsupervised domain adaptation method named TarGAN is proposed, which can successfully disentangle the class and the style codes of the target generator and generate Target samples with given class labels based on the recent advances of Generative Adversarial Networks.
- Learning User Dependencies for Recommendation28
This paper proposes a novel recommendation method, named probabilistic relational matrix factorization (PRMF), which can automatically learn the dependencies between users to improve recommendation accuracy and proposes an alternating optimization algorithm to solve the optimization problem of PRMF.
- 25
- Cross-Domain Detection Transformer Based on Spatial-Aware and Semantic-Aware Token Alignment23
This paper takes advantage of the characteristics of cross-attention as used in the detection transformer and proposes spatial-aware token alignment (SpaTA) and semantic-aware token alignment (SemTA) strategies to guide the token alignment across domains.
- 23
- 22
- 22
- 20
- 20
- 18
- 18
- 18
- 17
- 17
- 16
- 15
- 15
- 15
- 14
- 14
- 13
- 13
- 12
- 12
- 12
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- 9
- 8
- 8
- 8
- 8
- 8
- 8
- 7
- Calibrate the Inter-Observer Segmentation Uncertainty via Diagnosis-First Principle7
Experimental results show that the proposed Diagnosis-First segmentation Framework (DiFF) can effectively calibrate the segmentation uncertainty, and thus significantly facilitate the corresponding disease diagnosis, which outperforms previous state-of-the-art multi-rater learning methods.
- High-Level Feature Guided Decoding for Semantic Segmentation7
The proposed High-Level Feature Guided Decoder achieves state-of-the-art results among methods that do not use extra training data, demonstrating its effectiveness and generalization ability.
- 7
- 7
- 7
- 6
- 6
- Large-Scale Left and Right Eye Classification in Retinal Images6
This work spends a considerable amount of efforts in manually annotating the left and right eyes from the large-scale Kaggle Diabetic Retinopathy dataset, based on the developed online labeling system, to train classification models based on convolutional neural networks to discriminate left andright eyes in fundus images.
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- Domain Adaptive Semantic Segmentation Through Structure Enhancement3
This work proposes an effective method to adapt the segmentation network trained on synthetic images to real scenarios in an unsupervised fashion and enhances the structure information of the target images at both the feature level and the output level to improve the adaptation performance for semantic segmentation.
- 2
- 2
- 2
- 2
- 2
- Efficient Discriminative Learning of Class Hierarchy for Many Class Prediction2
This paper proposes a new efficient discriminative class hierarchy learning approach that can significantly accelerate the training process of the two state-of-the-art methods for multi-class tasks while achieving comparable prediction performance in terms of both classification accuracy and testing speed.
- 1
- 1
- 1
- 1
- Learning Cross-domain Semantic-Visual Relation for Transductive Zero-Shot Learning1
This work proposes a novel approach dubbed Transferrable Semantic-Visual Relation (TSVR) to facilitate the cross-category transfer in transductive ZSL to use a domain-specific batch normalization component to reduce the domain discrepancy of semantic-visual pairs.
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Cross-Modality Anatomy Knowledge Distillation for Retinal OCT Layer Segmentation With Limited Labels–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.