Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks177 from public data
- Pre-Trained Image Processing Transformer2,345
To maximally excavate the capability of transformer, the IPT model is presented to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs and the contrastive learning is introduced for well adapting to different image processing tasks.
- Learning from Multiple Teacher Networks496
This paper presents a method to train a thin deep network by incorporating multiple teacher networks not only in output layer by averaging the softened outputs from different networks, but also in the intermediate layers by imposing a constraint about the dissimilarity among examples.
- Data-Free Learning of Student Networks453
A novel framework for training efficient deep neural networks by exploiting generative adversarial networks (GANs) is proposed, where the pre-trained teacher networks are regarded as a fixed discriminator and the generator is utilized for derivating training samples which can obtain the maximum response on the discriminator.
- Multi-View Intact Space Learning395
This paper proposes the Multi-view Intact Space Learning (MISL) algorithm, which integrates the encoded complementary information in multiple views to discover a latent intact representation of the data and derives the generalization error bound based on multi-view stability and Rademacher complexity.
- CARS: Continuous Evolution for Efficient Neural Architecture Search275
This work develops an efficient continuous evolutionary approach for searching neural networks that provides a series of networks with the number of parameters ranging from 3.7M to 5.1M under mobile settings and surpasses those produced by the state-of-the-art methods on the benchmark ImageNet dataset.
- Revisiting Perspective Information for Efficient Crowd Counting252
A perspective-aware convolutional neural network (PACNN) is proposed for efficient crowd counting, which integrates the perspective information into density regression to provide additional knowledge of the person scale change in an image.
- Tensor Canonical Correlation Analysis for Multi-View Dimension Reduction250
TCCA is developed, which straightforwardly yet naturally generalizes CCA to handle the data of an arbitrary number of views by analyzing the covariance tensor of the different views, and proves that the main problem of multi-view canonical correlation maximization is equivalent to finding the best rank-1 approximation of the data covariance Tensor.
- AdderNet: Do We Really Need Multiplications in Deep Learning?240
This paper develops a special back-propagation approach for AdderNets by investigating the full-precision gradient, and proposes an adaptive learning rate strategy to enhance the training procedure of Ad DerNets according to the magnitude of each neuron's gradient.
- CNNpack: packing convolutional neural networks in the frequency domain198
This work presents an effective CNN compression approach in the frequency domain, which focuses not only on smaller weights but on all the weights and their underlying connections, and relax the computational burden of convolution operations in CNNs by linearly combining the convolution responses of discrete cosine transform (DCT) bases.
- 185
- 183
- Source-Free Domain Adaptation via Distribution Estimation175
This work proposes a novel framework called SFDA-DE to address SFDA task via source Distribution Estimation, which achieves state-of-the-art performance on multiple DA benchmarks, and even outperforms traditional DA methods which require plenty of source data.
- Multiview Matrix Completion for Multilabel Image Classification160
Experimental evaluation on two real-world data sets demonstrate the effectiveness of MVMC for transductive (semisupervised) multilabel image classification, and show that MVMC can exploit complementary properties of different features and output-consistent labels for improved multilabe image classification.
- Robust Extreme Multi-label Learning138
This paper explores and exploits an additional sparse component to handle tail labels behaving as outliers, in order to make the classical low-rank principle in multi-label learning valid and increase the scalability of the proposed algorithm.
- Hire-MLP: Vision MLP via Hierarchical Rearrangement128
Hire-MLP is presented, a simple yet competitive vision MLP architecture via Hierarchical rearrangement, which contains two levels of rearrangements to enable information communication between different regions and capture global context by circularly shifting all tokens along spatial directions.
- Decomposition-Based Transfer Distance Metric Learning for Image Classification118
This paper considers the transfer learning setting by exploiting the large quantity of side information from certain related, but different source tasks to help with target metric learning (with only a little side information), and proposes a decomposition-based transfer DML (DTDML).
- 117
- 115
- Manifold Regularized Dynamic Network Pruning114
A new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks (dubbed as ManiDP) is proposed, which shows better performance in terms of both accuracy and computational cost compared to the state-of-the-art methods.
- Large Margin Multi-Modal Multi-Task Feature Extraction for Image Classification106
A novel large margin multi- modal multi-task feature extraction (LM3FE) framework for handling multi-modal features for image classification that utilizes the complementarity of different modalities to further help reduce feature redundancy in each modality.
- Cost-Sensitive Feature Selection by Optimizing F-Measures105
An effective feature selection algorithm that explores the class imbalance issue by optimizing F-measures and selects features corresponding to the best F-measure, which will fully represent the properties of all classes.
- 93
- Distilling Portable Generative Adversarial Networks for Image Translation89
Qualitative and quantitative analysis by conducting experiments on benchmark datasets demonstrate that the proposed method can learn portable generative models with strong performance.
- 89
- 87
- Local Rademacher Complexity for Multi-Label Learning82
This work analyzes the local Rademacher complexity of empirical risk minimization-based multi-label learning algorithms, and proposes a new conditional singular value thresholding algorithm that has a sharper generalization error bound.
- Adversarial Learning of Portable Student Networks76
This work utilizes the generative adversarial network (GAN) to learn the student network and demonstrates that the proposed method is capable of learning well-performed portable networks, which is superior to the state-of-the-art methods.
- A Semi-Supervised Assessor of Neural Architectures75
This paper employs an auto-encoder to discover meaningful representations of neural architectures and introduces a graph convolutional neural network to predict the performance of architectures based on the learned representations and their relation modeled by the graph.
- 73
- Multi-Positive and Unlabeled Learning69
A one-step method that directly enables multi-class model to be trained using the given input multi- class data and that predicts the label based on the model decision is proposed.
- 61
- Indexing billions of images for sketch-based retrieval59
A compact shape code is developed to represent each image/sketch by projecting the Chamfer features to a linear subspace followed by a non-linear source coding and the compact shape codes are further used for fast reranking.
- The role of attractiveness in web image search58
Experimental results on three large-scale web image search datasets demonstrate that the incorporation of attractiveness can bring more satisfaction to 80% of the users for ranking/reranking search results and 30.5% index coverage improvement for index selection, compared to the conventional relevance based approaches.
- 54
- On Positive-Unlabeled Classification in GAN54
A new Positive-Unlabeled GAN is derived that can achieve comparable or even better performance than those sophisticated discriminator stabilization methods and theoretically discusses the global optimality the proposed model will achieve and the equivalent optimization goal.
- Learning Versatile Filters for Efficient Convolutional Neural Networks51
Experimental results on benchmark datasets and neural networks demonstrate that CNNs constructed with versatile filters are able to achieve comparable accuracy as that of original filters, but require less memory and FLOPs.
- Vector-Valued Multi-View Semi-Supervsed Learning for Multi-Label Image Classification51
The proposed multi-view vector-valued manifold regularization (MV$^3$MR) methodology for image classification exploits the complementary properties of different features, and discovers the intrinsic local geometry of the compact support shared by different features under the theme of manifoldRegularization.
- Deblurring Low-Light Images with Events49
A unified two-stage framework along with a motion-aware neural network tailored to it is proposed, reconstructing the sharp image under the guidance of high-fidelity motion clues extracted from events robustly, and experimental results show the method achieves state-of-the-art performance on both synthetic and real-world images.
- Towards Evolutionary Compression46
This paper presents an evolutionary method to automatically eliminate redundant convolution filters, representing each compressed network as a binary individual of specific fitness, which has the original network structure and can be directly deployed in any off-the-shelf deep learning libraries.
- 45
- Large-margin Weakly Supervised Dimensionality Reduction45
Theoretical analysis demonstrates that the proposed large margin optimization criteria can strengthen and improve the robustness and generalization performance of preference learning algorithms on the obtained low-dimensional subspace.
- The Tianwen-1 Guidance, Navigation, and Control for Mars Entry, Descent, and Landing43
The Tianwen-1 EDL GNC system design is outlined by introducing the GNC requirements followed by presenting the G NC system architecture and algorithms to meet such requirements.
- 41
- 40
- 39
- Pre-Trained Multi-View Word Embedding Using Two-Side Neural Network39
A two-side multimodal neural network is proposed to learn a robust word embedding from multiple data sources including free text, user search queries and search click-through data and outperforms state-of-the-art word embeddedding algorithm with each individual source.
- Robust Student Network Learning38
This paper makes the student network produce more confident predictions with the help of the teacher network, and analyzes the lower bound of the perturbation that will destroy the confidence of theStudent network.
- 37
- Reinforced Multi-Label Image Classification by Exploring Curriculum36
A reinforced multi-label image classification approach imitating human behavior to label image from easy to complex is proposed, which allows a reinforcement learning agent to sequentially predict labels by fully exploiting image feature and previously predicted labels.
- 33
- Reborn Filters: Pruning Convolutional Neural Networks with Limited Data33
This paper proposes to use all original filters to directly develop new compact filters, named reborn filters, so that all useful structure priors in the original filters can be well preserved into the pruned networks, alleviating the performance drop accordingly.
- 33
- 32
- Learning With Single-Teacher Multi-Student29
A new learning problem defined as "Single-Teacher Multi-Student" (STMS) problem, which investigates how to learn a series of student models from a single teacher (complex and universal) model, is studied and a gated support vector machine (gSVM) is proposed as a solution.
- Privileged Multi-label Learning29
This paper suggests that for each individual label, it cannot only be implicitly connected with other labels via the low-rank constraint over label predictors, but also its performance on examples can receive the explicit comments from other labels together acting as an Oracle teacher.
- 27
- UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging27
This paper reformulates the modulo image unwrapping problem into a series of binary labeling problems and proposes a modulo edge-aware model, named as UnModNet, to iteratively estimate the binary rollover masks of the modulo image for unwrapping.
- Exploiting visual word co-occurrence for image retrieval27
Thorough experimental results suggest that the constructed visual word co-occurrence table outperforms the state-of-the-art, especially when the vocabulary size is comparatively small, and the method is not much more costly than the BOVW model.
- 26
- A logic of knowing why26
A logical framework of “knowing why” inspired by the existing formal studies on why-questions, scientific explanation, and justification logic is proposed and the Kyi operator is introduced into the language of epistemic logic to express “agent i knows why″.
- 25
- 25
- 24
- 24
- 23
- 22
- 22
- 21
- Theory and implementation of a very high throughput true random number generator in field programmable gate array21
A new entropy extraction mechanism based on sampling phase jitter in ring oscillators to make a high throughput true random number generator in a field programmable gate array (FPGA) practical and confirms that the new method can provide high-speed high-quality random bit sequences for a variety of embedded applications.
- 20
- Design and implementation of the modified signed digit multiplication routine on a ternary optical computer20
The modified signed digit (MSD) multiplication routine is established based on the MSD system and the carry-free adder and is good at dealing with large-value data and high-precision arithmetic, but also maintains lower power consumption and fewer calculating delays.
- HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens19
An hourglass-inspired approach (HourNAS) for extremely fast NAS to identify the vital blocks and make them the priority in the architecture search, which outperforms the state-of-the-art methods.
- 19
- Toward Ultra‐High‐Capacity Meta‐Optics Storage: 3D Data Cube Encrypted via Arbitrary Spatial Coordinates18
A 3D data encryption cube storage strategy is proposed and experimentally demonstrated, based on arbitrary holographic coordinate definition within the Fresnel region, enabled by an on‐chip meta‐device, offering a promising pathway toward high‐capacity, high‐security optical storage and 3D holographic applications.
- IFME18
This paper presents a framework named IFME (Information Filtering by Multiple Examples) in a digital library environment to help users identify the literature related to their interests by leveraging the Positive Unlabeled learning (PU learning).
- Query difficulty estimation for image retrieval17
A query difficulty estimation approach by analyzing the top ranked images obtained by ad hoc retrieval models that seamlessly integrate the language model based clarity score, the spatial consistency of local descriptors and the appearance consistency of global features.
- 16
- 15
- Entry vehicle control system design for the Tianwen-1 mission15
The key aspects of designing attitude controllers for each phase of the GNC system design are introduced and flight results are presented and analyzed.
- A comprehensive study on learning to rank for content-based image retrieval15
This paper introduces some scalable visual-based ranking features for learning to rank in content-based image retrieval (CBIR) by adopting several well performed ad hoc ranking models to generate the bag-of-visual-words- based ranking features.
- Collaborative learning for image and video annotation15
This paper assumes that visually similar concepts should share resembled detectors, and proposes Multi-Granularity Boosting strategy, where each granularity corresponds to a specific balance between collaboration and discrimination for Collaborative Learning.
- Cost-Sensitive Feature Selection via F-Measure Optimization Reduction14
This paper presents a novel cost-sensitive feature selection (CSFS) method which optimizes F-measure instead of accuracy to take class imbalance issue into account, and proves the efficiency and significance of the method.
- 13
- 13
- MagicBrush13
The MagicBrush system enables users to draw a color sketch as a query to find images, and develops a user-friendly interface to allow users to easily "paint out" their colorful visual expectations.
- 13
- Learning to Deblur Polarized Images12
A polarized image deblurring pipeline to solve the problem in a polarization-aware manner by adopting a divide-and-conquer strategy to explicitly decompose the problem into two less ill-posed sub-problems, and design a two-stage neural network to handle the two sub-problems respectively.
- Training object detectors from few weakly-labeled and many unlabeled images12
This work studies the problem of training an object detector from one or few clean images with image-level labels and a larger set of completely unlabeled images, and uses a standard weakly-supervised pipeline to train a student model from image- level pseudo-labels generated on the unlabeling set by a teacher model, bootstrapped by region-level similarities to clean labeled images.
- 12
- 12
- Large-margin multi-view Gaussian process11
A probabilistic explanation is provided by Gaussian process to embed multiple features into the shared low-dimensional subspace, which derives a strong discriminative ability from the large-margin principle, and thus, the subsequent classification task can be effectively accomplished.
- Difficulty guided image retrieval using linear multiview embedding11
This paper proposes a linear multiview embedding algorithm which learns a linear transformation from a small set of data and can effectively infer the subspace features of new data and suggest the effectiveness of the proposed difficulty guided retrieval system with LME.
- Color Correction and Compression for Multi-view Video Using H.264 Features11
By discarding most of the chrominance information before encoding and restoring them when decoding, this novel scheme can greatly improve the compression rate without much loss in visual quality, while at the same time produce color images with similar appearance to reference without correction.
- Visual navigation with fast landmark selection based on error analysis for asteroid descent stage10
A new navigation method is proposed, which integrates absolute and relative visual information for quality improvement, and a fast landmark selection method for efficiency purposes, and the numerical results demonstrate the advancement of the proposed methods in quality and efficiency.
- Tianwen-1 Entry, Descent, and Landing Guidance, Navigation, and Control System Design and Validation9
The Tianwen-1 EDL GNC system design is presented, including the GNC architecture, scheme, and algorithm; additionally, the system is validated through experimental tests, numerical simulations, and actual flight results from telemetry data.
- Learning to rerank images with enhanced spatial verification9
This work combines features representing images from different perspectives with RankSVM to obtain a reranking model to refine the initial ranking list and defines an efficient similarity measurement with the order consistency between inlier sequences.
- Query expansion by spatial co-occurrence for image retrieval9
A novel query expansion method called Spatial Co-occurrence Query Expansion (SCQE) is proposed, by utilizing the spatial co-occurring information of visual words mined from the database images to boost the retrieval performance.
- 9
- Fast and Efficient Basis Selection Methods for Embedded Wavelet Packet Image Coding9
This paper proposes two rate-unrelated basis selection criteria for embedded image coding based on the idea of maximizing variance of each subband, and shows that, with the same subband coding scheme, the proposed method achieve better coding performance than that of previous selection criteria.
- 9
- 8
- A Survey on Visualization of Complex Network8
Many real-world domains can be represented as complex networks, which exploit human visual processing, and are more prone to cognition of the structure of such complex networks than the computational representation.
- Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras7
An efficient spatio-temporal interactive reconstruction network is proposed to jointly perform inter-frame feature alignment and intra-frame feature filtering in a coarse-to-fine manner and introduces a symmetric interactive attention block and a multi-motion field estimation block to further enhance the interaction capability of the overall network.
- Fast SVM Trained by Divide-and-Conquer Anchors7
This paper proposes to choose the representative points which are noted as anchors obtained from non-negative matrix factorization in a divide-and-conquer framework, and use the anchors to train an approximate SVM, and shows that the solving the DCA-SVM can yield an approximate solution close to the primal SVM.
- 7
- Multi-view Multi-task Feature Extraction for Web Image Classification7
A novel multi-View multi-task feature extraction (MVMTFE) framework for handling multi-view features for image classification that not only handles correlated and noisy features, but also utilizes the complementarity of different views to further help reduce feature redundancy in each view.
- 7
- 7
- 6
- 6
- 6
- 6
- 5
- Multiscale Entropy Analysis of Page Views: A Case Study of Wikipedia5
The results suggest that the sampleEntropies estimated by the sMSE algorithm are feasible for analyzing the temporal variations of complexity for certain topics, whereas the regular variations of estimated sample entropies of different selected topics can’t simply be accepted as is.
- 5
- Exploring Spatial Correlation for Visual Object Retrieval5
Thorough experimental results suggest that this method outperforms the state of the art without adding much additional cost to the BOVW model and proposes two methods of co-occurrence weighting similarity measure for image ranking: Co-Cosine and Co-TFIDF.
- Query Difficulty Guided Image Retrieval System5
This paper presents a query difficulty estimation guided image retrieval system that initially estimates the difficulty of a given query image by analyzing both the query image and the retrieved top ranked images.
- 5
- 5
- 4
- 4
- 4
- Automatic Translation of Clinical Trial Eligibility Criteria into Formal Queries3
This paper develops a semantic annotation process that can capture many types of clinical trial criteria, and builds a prototype system based on state-of-the-art NLP tools such as Word2Vec, Stanford NLP tools, and the MetaMap Tagger.
- Fast Compressive Phase Retrieval under Bounded Noise3
This work gives a provable algorithm that is robust to any bounded yet unstructured deterministic noise, that requires roughly O(t) measurements and runs in O(tn*log (1/epsilon)) time.
- Research on the Real-Time Multiple Face Detection, Tracking and Recognition Based on Video3
An automatic face tracking and recognition system, which can track multiple faces real-timely and recognize the identity, and a fusion algorithm based on Adaboost face detection algorithm and Active Shape Model is presented.
- 3
- A Collaborative Filtering Recommendation System by Unifying User Similarity and Item Similarity3
A new similarity measurement was given and a new collaborative filtering algorithm named UICF was presented for recommendation, which chooses the users as nearest neighbors which have the similar rating feature for the items with the same type of the special item, instead of for all the items.
- Shared feature extraction for semi-supervised image classification3
A manifold regularized MTL (MRMTL) algorithm is proposed to discover the latent shared subspace by treating the high-dimensional image space as a sub-manifold embedded in an ambient space and suggests that MRMTL can properly extract the common features for image representation and thus improve the generalization performance of the image classification models.
- 3
- A Link-based Method for Name Disambiguation and its Application3
The research presents an algorithm that is applicable to name disambiguation of Chinese literature digital library that makes an attribute similarity analysis and detects the reference-entity relationship by considering the links of co-authorship network and the collective relations among the co- authorship network.
- 3
- 3
- 2
- Task-Oriented Age of Information for Remote Inference with Hybrid Language Models2
This study proposes a novel remote inference system comprising a user, a sensor, and an edge server that integrates both model types alongside a decision maker and proves that the optimal control policy follows a threshold-based structure.
- 2
- 2
- 2
- 1
- 1
- 1
- Regional Wave Spectra Prediction Method Based on Deep Learning1
This study proposes a model combining CNN and xLSTM for rapid gridded wave spectrum prediction over the Bohai and Yellow Seas domain and shows strong performance in spectrum prediction and provides a valuable approach for regional wave spectrum modeling.
- 1
- 1
- 1
- 1
- Manifold Learning Method for Large Scale Dataset Based on Gradient Descent1
The gradient descent was utilized to search the low-dimensional embedding and replaced the eigenvalue decomposition of a large sparse matrix of LLE (Linear Locally Embedding) algorithm, which performed well and the time complexity is lower than before and storage memory is declined obviously.
- Ranking Model Adaptation for1
A regularization based algorithm called ranking adaptation SVM (RA-SVM), through which an existing ranking model is adapted to a new domain, so that the amount of labeled data and the training cost is reduced while the performance is still guaranteed.
- Formal Specification for Compiler Based Test Case Generation of Embedded Real-Time System1
A compiler based automatically test case generation framework is proposed firstly, and then a novel language call RCBL is introduced to specify the testing requirements that describe the relationship of source code and testing requirements for the embedded real-time system.
- 1
- 1
- 1
- –
- An efficient graph-transformer operator for learning physical dynamics with manifolds embedding–
An efficient graph-transformer operator, named PhysGTO, is shown for learning physical dynamics through explicit manifold embeddings in both physical and latent spaces, showing strong flexibility, scalability, and generalization across diverse physical systems.
- –
- A GPU-based mipmapping method for water surface visualization–
This method utilized uniform mesh and Fractal Perlin noise to model water surface and Mipmapping technology was enforced to the surface textures, which adjust the resolution with respect to the distance from the viewpoint and reduce the computing cost.
- –
- Task-based user profiling for query refinement (TOQUE)–
TASK-BASED USER PROFILING for QUERY REFINEMENT (TOQUE) is reported to have shown promising results in terms of conversion efficiency and applicability to various industrial processes.
- The Implementation of Xilinx FPGAs’ Interconnection Module–
More FPGA time-division multiplexing interconnection module is achieved to meet the communication needs as many as 2000 more signal.
- –
- User Profiling for Query Refinement Submission Type: Completed Research Paper–
This paper proposes a novel framework of user profiling -- modeling the user’s interests at the task level for query refinement to improve the ranking of the refined queries, and thus, ultimately improve theranking of the relevant search results.
- User Profiling for Query Refinement–
This paper proposes a novel framework of user profiling -modeling the user’s interests at the task level for query refinement to improve the ranking of the refined queries, and thus, ultimately improve theranking of the relevant search results.
- Task-Based User Profiling for Personalized Query Refinement.–
Experimental results showed that the task-based user-profiling method contributes to an increased precision of search results, and it produced more accurate refined queries, thereby resulting in shorter search sessions.
- Encoding Scheme Selecting Algorithm of Character Two-Dimensional Barcode–
Based on the international standard "look-ahead test" algorithm in Data Matrix 2D code, the principle of multistage decision and the method of mixed character count are used to archieve a kind of look-ahead algorithm for character two-dimensional barcode scheme selection.
- –
- Patch Alignment for Graph Embedding–
This paper presents locally linear embedding (LLE), which uses linear coefficients, which reconstruct a given example by its neighbors, to represent the local geometry, and then seeks a low-dimensional embedding, in which these coefficients are still suitable for reconstruction.
- Memory Optimization Algorithm and Analysis Based on Block Architecture–
This paper combines Distribution method of Tiantian Liu et al to set up a corresponding mathematical model which complexity is analyzed and puts forward a memory optimization algorithm based on block architecture which is analyzed through the concrete example.
- NTIZATION VIA SPATIAL NEIGHBORHO–
Experimental results on image retrieval dataset demonstrate the proposed spatial correlation information to boost feature quantization method is capable of improving the efficien of visual word assignment.
- –
- –
- WDM driver program for digital film image decoding board according with DCI specification–
The experimental results shows that the driver program can control the circuit board to decode in real time the DCI specified film image sequences whose maximum data rate reaches the upper limit of 250 M Bits/sec suggested by DCI specification.
- Design of LXI Bus Module for Multi-Frequency HF Ground Wave Radar Based on Linux–
A general LXI bus module based on ARM is presented in this paper and can be employed for multi-frequency HF ground wave radar (HF GWR) and meets the needs of HF GWR measurement.
- Automatic Summarization Method Based on Extracting Sentences from Local Topics–
This paper proposes a new method for automatic summarization of Chinese text based on extracting sentences from subtopics by analyzing semantic structure of the documents in advance and shows that the method is effective.
- –
- –
- An efficient parallel architecture for MPEG-4 zerotree encoder–
Under the architecture, a parallel processing of multi bit-planes is fulfilled through a preprocess until and multi-encoding units, which ensures sufficiently that efficient encoding in each bit-plane is performed independently.
- –
- –
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 2026-10-15. 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.