Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Jitendra MalikSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works333 from public data
- Microsoft COCO: Common Objects in Context56,192
A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.
- Feature Pyramid Networks for Object Detection28,993
This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
- Shape matching and object recognition using shape contexts6,951
A novel approach to measuring similarity between shapes and exploiting it for object recognition by treating recognition in a nearest-neighbor classification framework as the problem of finding the stored prototype shape that is maximally similar to that in the image.
- Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization5,549
This paper presents a simple yet effective approach that for the first time enables arbitrary style transfer in real-time, comparable to the fastest existing approach, without the restriction to a pre-defined set of styles.
- Class-Balanced Loss Based on Effective Number of Samples3,490
This work designs a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss and introduces a novel theoretical framework to measure data overlap by associating with each sample a small neighboring region rather than a single point.
- DOTA: A Large-Scale Dataset for Object Detection in Aerial Images3,264
A large-scale Dataset for Object deTection in Aerial images (DOTA) is introduced and state-of-the-art object detection algorithms on DOTA are evaluated, demonstrating that DOTA well represents real Earth Vision applications and are quite challenging.
- 2,849
- Multimodal Unsupervised Image-to-Image Translation2,788
A Multimodal Unsupervised Image-to-image Translation (MUNIT) framework that assumes that the image representation can be decomposed into a content code that is domain-invariant, and a style code that captures domain-specific properties.
- 2,207
- 2,100
- 2,020
- 2,001
- Blobworld: image segmentation using expectation-maximization and its application to image querying1,655
Results indicating that querying for images using Blobworld produces higher precision than does querying using color and texture histograms of the entire image in cases where the image contains distinctive objects are presented.
- 1,635
- 1,529
- Caltech-UCSD Birds 2001,422
Caltech-UCSD Birds 200 (CUB-200) is a challenging image dataset annotated with 200 bird species to enable the study of subordinate categorization, which is not possible with other popular datasets that focus on basic level categories.
- Contour and Texture Analysis for Image Segmentation1,377
This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture, and introduces a gating operator based on the texturedness of the neighborhood at a pixel to facilitate cue combination.
- Integral Channel Features1,350
It is demonstrated that when designed properly, integral channel features not only outperform other features including histogram of oriented gradient (HOG), they also result in fast detectors when coupled with cascade classifiers.
- 1,317
- Residual networks behave like ensembles of relatively shallow networks1,174
This work proposes a novel interpretation of residual networks showing that they can be seen as a collection of many paths of differing length, and reveals one of the key characteristics that seem to enable the training of very deep networks: Residual networks avoid the vanishing gradient problem by introducing short paths which can carry gradient throughout the extent of veryDeep networks.
- Blobworld: A System for Region-Based Image Indexing and Retrieval955
This work indexes the blob descriptions using a lower-rank approximation to the high-dimensional distance to make large-scale retrieval feasible, and shows encouraging results for both querying and indexing.
- The multidimensional wisdom of crowds920
A method for estimating the underlying value of each image from (noisy) annotations provided by multiple annotators, based on a model of the image formation and annotation process, which predicts ground truth labels on both synthetic and real data more accurately than state of the art methods.
- PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows864
A principled probabilistic framework to generate 3D point clouds by modeling them as a distribution of distributions with the invertibility of normalizing flows enables the computation of the likelihood during training and allows the model to train in the variational inference framework.
- Detecting Oriented Text in Natural Images by Linking Segments775
SegLink, an oriented text detection method to decompose text into two locally detectable elements, namely segments and links, achieves an f-measure of 75.0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin.
- 773
- 745
- Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges714
The expanded large-scale DOTA dataset, the extensive baselines, the code library and the challenges can facilitate the designs of robust algorithms and reproducible research on the problem of object detection in aerial images.
- The Fastest Pedestrian Detector in the West682
A technique to avoid constructing such a finely sampled image pyramid without sacrificing performance is proposed, and for a broad family of features, including gradient histograms, the feature responses computed at a single scale can be used to approximate feature responses at nearby scales.
- Shape Context: A New Descriptor for Shape Matching and Object Recognition675
It is demonstrated that shape contexts greatly simplify recovery of correspondences between points of two given shapes, and is used in a nearest-neighbor classifier for recognition of hand written digits as well as 3D objects, using exactly the same distance function.
- Spatiotemporal Contrastive Video Representation Learning600
This work proposes a temporally consistent spatial augmentation method to impose strong spatial augmentations on each frame of the video while maintaining the temporal consistency across frames, and proposes a sampling-based temporal augmentation methods to avoid overly enforcing invariance on clips that are distant in time.
- Context based object categorization: A critical survey587
This work addresses the problem of incorporating different types of contextual information for robust object categorization in computer vision by reviewing different ways of using contextual information in the field of object categorization, and considering the most common levels of extraction of context.
- A Metric Learning Reality Check579
Flaws in the experimental methodology of numerous metric learning papers are found, and it is shown that the actual improvements over time have been marginal at best.
- 574
- 559
- Collaborative Metric Learning555
The proposed algorithm outperforms state-of-the-art collaborative filtering algorithms on a wide range of recommendation tasks and uncovers the underlying spectrum of users' fine-grained preferences.
- Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning542
This work proposes a measure to estimate domain similarity via Earth Mover's Distance and demonstrates that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure.
- 534
- Word Spotting in the Wild533
It is argued that the appearance of words in the wild spans this range of difficulties and a new word recognition approach based on state-of-the-art methods from generic object recognition is proposed, in which object categories are considered to be the words themselves.
- Learning from Noisy Large-Scale Datasets with Minimal Supervision517
An approach to effectively use millions of images with noisy annotations in conjunction with a small subset of cleanly-annotated images to learn powerful image representations and is particularly effective for a large number of classes with wide range of noise in annotations.
- 507
- Visual Recognition with Humans in the Loop500
The results demonstrate that incorporating user input drives up recognition accuracy to levels that are good enough for practical applications, while at the same time, computer vision reduces the amount of human interaction required.
- Stacked Generative Adversarial Networks470
A novel generative model named Stacked Generative Adversarial Networks (SGAN), which is trained to invert the hierarchical representations of a bottom-up discriminative network, which is able to generate images of much higher quality than GANs without stacking.
- 465
- Higher order learning with graphs463
It is shown that various formulations of the semi-supervised and the unsupervised learning problem on hypergraphs result in the same graph theoretic problem and can be analyzed using existing tools.
- 460
- 458
- 430
- Convolutional Networks with Adaptive Inference Graphs423
This work proposes convolutional networks with adaptive inference graphs (ConvNet-AIG) that adaptively define their network topology conditioned on the input image that shows a higher robustness than ResNets, complementing other known defense mechanisms.
- Generative Adversarial Perturbations421
Novel generative models for creating adversarial examples, slightly perturbed images resembling natural images but maliciously crafted to fool pre-trained models, obviating the need for hand-crafting attack methods for each task are proposed.
- 375
- Learning Gradient Fields for Shape Generation353
This work generates point clouds by performing stochastic gradient ascent on an unnormalized probability density, thereby moving sampled points toward the high-likelihood regions and allowing for extraction of a high-quality implicit surface.
- 343
- 339
- Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences335
The proposed framework is capable of learning semantic information about visual style and is able to generate outfits of clothes, with items from different categories, that go well together, to answer questions like 'What outfit goes well with this pair of shoes?'
- 331
- 329
- 322
- Enhancing Adversarial Example Transferability With an Intermediate Level Attack312
The Intermediate Level Attack (ILA) is introduced, which attempts to fine-tune an existing adversarial example for greater black-box transferability by increasing its perturbation on a pre-specified layer of the source model, improving upon state-of-the-art methods.
- The Plant Pathology Challenge 2020 data set to classify foliar disease of apples300
This data set will contribute toward development and deployment of machine learning–based automated plant disease classification algorithms to ultimately realize fast and accurate disease detection.
- 289
- 284
- ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)256
This report introduces RCTW, a new competition that focuses on Chinese text reading with a large-scale dataset with over 12,000 annotated images and calls for more future research on the Chinese textReading problem.
- Approximate Thin Plate Spline Mappings256
A third approximation method based on a classic matrix completion technique that allows for principal warp analysis as a by-product is described and a significant improvement over the naive method is demonstrated.
- Fine-Grained Categorization and Dataset Bootstrapping Using Deep Metric Learning with Humans in the Loop241
Experimental evaluations show significant performance gain using dataset bootstrapping and demonstrate state-of-the-art results achieved by the proposed deep metric learning methods.
- 239
- Unbiased offline recommender evaluation for missing-not-at-random implicit feedback237
This paper investigates evaluation bias of AOA and develops an unbiased and practical offline evaluator for implicit MNAR datasets using the Inverse-Propensity-Scoring (IPS) technique, and shows that popularity bias is widely manifested in item presentation and interaction.
- Finding pictures of objects in large collections of images233
The approach to object recognition is described, which is structured around a sequence of increasingly specialized grouping activities that assemble coherent regions of image that can be shown to satisfy increasingly stringent constraints.
- Occluded Video Instance Segmentation: A Benchmark229
A simple plug-and-play module that performs temporal feature calibration to complement missing object cues caused by occlusion is presented, and a remarkable AP improvement on the OVIS dataset is obtained.
- Generalized Non-metric Multidimensional Scaling.229
It is argued that this setting is more natural in some experimental settings and proposed algorithm based on convex optimization techniques to solve the non-metric multidimensional scaling problem in which only a set of order relations of the form dij < dkl are provided is provided.
- 228
- Structured importance sampling of environment maps224
This work introduces structured importance sampling, a new technique for efficiently rendering scenes illuminated by distant natural illumination given in an environment map, and presents a novel hierarchical stratification algorithm that uses the authors' metric to automatically stratify the environment map into regular strata.
- 208
- End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection204
A new framework based on differentiable Change of Representation (CoR) modules that allow the entire PL pipeline to be trained end-to-end and is compatible with most state-of-the-art networks for both tasks and in combination with PointRCNN improves over PL consistently across all benchmarks.
- 200
- 200
- 191
- 191
- 188
- Practical Global Optimization for Multiview Geometry188
A practical method for finding the provably globally optimal solution to numerous problems in projective geometry including multiview triangulation, camera resectioning and homography estimation that relies on recent developments in fractional programming and the theory of convex underestimators.
- 182
- Yum-Me179
Yum-me is proposed, a personalized nutrient-based meal recommender system designed to meet individuals’ nutritional expectations, dietary restrictions, and fine-grained food preferences, and a novel online learning framework that learns food preference from itemwise and pairwise image comparisons.
- On Feature Normalization and Data Augmentation168
This paper proposes Moment Exchange, an implicit data augmentation method that encourages the model to utilize the moment information also for recognition models, and replaces the moments of the learned features of one training image by those of another, and also interpolate the target labels to extract training signal from the moments.
- 168
- Learning to Evaluate Image Captioning166
This work proposes a novel learning based discriminative evaluation metric that is directly trained to distinguish between human and machine-generated captions and proposes a data augmentation scheme to explicitly incorporate pathological transformations as negative examples during training.
- BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography162
A large-scale dataset of contemporary artwork from Behance, a website containing millions of portfolios from professional and commercial artists, is collected and annotated with rich attribute labels for content, emotions, and artistic media to teach machines how to categorize images in ways that are valuable to humans.
- 161
- Boosted Convolutional Neural Networks158
This work proposes a novel algorithm to incorporate boosting weights into the deep learning architecture based on least squares objective function and shows that it is possible to use networks of different structures within the proposed boosting framework and BoostCNN is able to select the best network structure in each iteration.
- Multiple Component Learning for Object Detection152
The method, Multiple Component Learning (mcl), automatically learns individual component classifiers and combines these into an overall classifier, and unlike methods that are not part-based, mcl is quite robust to occlusions.
- 146
- Cloud motion and stability estimation for intra-hour solar forecasting145
The VOF forecast with a fixed smoothness parameter was found to be superior to image persistence forecast for all forecast horizons for almost all days and outperform CCM forecast with an average error reduction of 39%, 21%, 19%, and 19% for 0, 5, 10, and 15 min forecasts respectively.
- 145
- DualSDF: Semantic Shape Manipulation Using a Two-Level Representation139
This work proposes DualSDF, a representation expressing shapes at two levels of granularity, one capturing fine details and the other representing an abstracted proxy shape using simple and semantically consistent shape primitives, to achieve a tight coupling between the two representations.
- GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds138
GANcraft is presented, an unsupervised neural rendering framework for generating photorealistic images of large 3D block worlds such as those created in Minecraft, and allows user control over both scene semantics and output style.
- Spectral Partitioning with Indefinite Kernels Using the Nyström Extension137
A modification to Nystrom-NCut is presented that does not require W to be positive definite, and a proof that the Gaussian-weighted chi-squared kernel is positive definite is provided, which has thus far only been conjectured.
- Vision-based real estate price estimation134
This paper develops a method for estimating the luxury level of real estate photos using deep convolutional neural networks on a large dataset of photos of home interiors and exteriors, and develops a novel framework for automated value assessment using the above photos.
- 132
- Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset131
This work proposes a novel Attribute-Mask RCNN model to jointly perform instance segmentation and localized attribute recognition, and provides a novel evaluation metric for the task.
- 125
- 116
- 115
- What Went Where114
This work presents a novel framework for motion segmentation that combines the concepts of layer-based methods and featurebased motion estimation and achieves a dense, piecewise smooth assignment of pixels to motion layers using a fast approximate graphcut algorithm based on a Markov random field formulation.
- Transfer learning in computer vision tasks: Remember where you come from112
The experimental protocol put forward the versatility of a regularizer that is easy to implement and to operate that is eventually recommend as the new baseline for future approaches to transfer learning relying on fine-tuning.
- Residual Networks are Exponential Ensembles of Relatively Shallow Networks.111
This work introduces a novel interpretation of residual networks showing they are exponential ensembles, and suggests that in addition to describing neural networks in terms of width and depth, there is a third dimension: multiplicity, the size of the implicit ensemble.
- Weakly Supervised Object Localization with Stable Segmentations107
This paper introduces the challenging Landmarks-18 dataset, a collection of photographs of famous landmarks from around the world, and proposes a new object recognition system called MILSS, which shows highly competitive object categorization results on the Caltech dataset.
- Simultaneous Learning and Alignment: Multi-Instance and Multi-Pose Learning ?107
A unified boosting framework for simultaneous learn- ing and alignment is presented and a novel boosting algorithm for Multiple Pose Learning (mpl) is presented, where the goal is to simultaneously split data into groups and train classifiers for each.
- 107
- 102
- 100
- 96
- 94
- The iMaterialist Fashion Attribute Dataset93
This work contributes to the community a new dataset called iMaterialist Fashion Attribute (iFashion-Attribute), constructed from over one million fashion images with a label space that includes 8 groups of 228 fine-grained attributes in total, which is the first known million-scale multi-label and fine- grained image dataset.
- 93
- Cost-Effective HITs for Relative Similarity Comparisons85
This work explores an alternative method for collecting triplets and analyzes its financial cost, collection speed, and worker happiness as a function of the final embedding quality, and proposes best practices for creating cost effective human intelligence tasks for collecting doublets.
- The iNaturalist Challenge 2017 Dataset84
The iNaturalist Challenge 2017 dataset is presented - an image classification benchmark consisting of 675,000 images with over 5,000 different species of plants and animals, which features many visually similar species, captured in a wide variety of situations, from all over the world.
- Learning to Match Aerial Images with Deep Attentive Architectures84
This paper proposes a data-driven, deep learning-based approach that sidesteps local correspondence by framing the problem as a classification task, and demonstrates that local correspondences can still be useful.
- The Ignorant Led by the Blind: A Hybrid Human–Machine Vision System for Fine-Grained Categorization83
The formalism shows how to incorporate many different types of computer vision algorithms into a human-in-the-loop framework, including standard multiclass methods, part-based methods, and localized multiclass and attribute methods.
- 79
- Learning to Detect and Match Keypoints with Deep Architectures78
A novel approach for learning to detect and describe keypoints from images leveraging deep architectures is presented and a large-scale dataset of patches with matching multiscale keypoints is collected to allow for a learning based approach.
- 77
- Non-isometric manifold learning77
This work takes a novel view of nonlinear manifold learning, and presents an extension of a recent algorithm, Locally Smooth Manifold Learning (LSML), which has good generalization properties.
- Neural Naturalist: Generating Fine-Grained Image Comparisons75
A new model is proposed called Neural Naturalist that uses a joint image encoding and comparative module to generate comparative language, and the results indicate promising potential for neural models to explain differences in visual embedding space using natural language.
- 75
- EdgeSonic73
Preliminary experiments show that the combination of local edge gradient sonification and distance-to-edge sonification are effective for understanding basic line drawings and a significant improvement in image understanding with the introduction of proper user training.
- 73
- 71
- Context Matters: Refining Object Detection in Video with Recurrent Neural Networks65
A new framework for improving object detection in videos that captures temporal context and encourages consistency of predictions is presented, which incorporates strong supervision of target frames, weak-supervision on context frames, and regularization via a smoothness penalty.
- Learning Single-View 3D Reconstruction with Limited Pose Supervision63
A unified framework is presented that can combine both types of supervision: a small amount of camera pose annotations are used to enforce pose-invariance and view-point consistency, and unlabeled images combined with an adversarial loss are use to enforce the realism of rendered, generated models.
- Locally Uniform Comparison Image Descriptor61
Locally Uniform Comparison Image Descriptor (LUCID), a simple description method based on linear time permutation distances between the ordering of RGB values of two image patches, which is computable in linear time with respect to the number of pixels and does not require floating point computation.
- 60
- 60
- 59
- Can we still avoid automatic face detection?59
In this work, ways to evade face detection on Facebook are found, and it is shown that in general, state-of-the-art detectors can often find faces even if the subject wears occluding clothing or if the uploader damages the photo to prevent faces from being detected.
- Learning to Traverse Image Manifolds59
Applications of the proposed LSML technique include embedding with a natural out-of-sample extension and tasks such as tangent distance estimation, frame rate up-conversion, video compression and motion transfer.
- On Refractive Optical Flow57
A novel generalization of the optical flow equation to the case of refraction is presented, and a method for recovering the refractive structure of an object from a video sequence acquired as the background behind the refracting object moves is described.
- 55
- 55
- Crowd Research54
Crowd Research is presented, a crowdsourcing technique that coordinates open-ended research through an iterative cycle of open contribution, synchronous collaboration, and peer assessment, and introduces a decentralized credit system.
- 54
- 54
- Recognition of Images in Large Databases Using a Learning Framework52
A "blob world" representation is defined which provides a transition from the raw pixel data to a small set of localized coherent regions in color and texture space which is utilized to extract a probabilistic interpretation of the scene.
- Intentonomy: a Dataset and Study towards Human Intent Understanding51
This paper introduces an intent dataset, Intentonomy, comprising 14K images covering a wide range of everyday scenes, and systematically studies whether, and to what extent, commonly used visual information, i.e., object and context, contribute to human motive understanding.
- A Feature-based Approach for Dense Segmentation and Estimation of Large Disparity Motion51
A novel framework for motion segmentation that combines the concepts of layer-based methods and feature-based motion estimation is presented, and a dense, piecewise smooth assignment of pixels to motion layers is achieved using a fast approximate graphcut algorithm based on a Markov random field formulation.
- Rethinking Few-shot 3D Point Cloud Semantic Segmentation50
This paper revisits few-shot 3D point cloud semantic segmentation (FS-PCS), with a focus on two significant is-sues in the state-of-the-art: foreground leakage and sparse point distribution, and proposes a novel FS-PCS model based on correlation optimization, referred to as Correlation Optimization Segmentation (COSeg).
- Efficient Large-Scale Structured Learning48
An algorithm, SVM-IS, for structured SVM learning that is computationally scalable to very large datasets and complex structural representations and allows problem-specific structural knowledge to be exploited for faster optimization by integrating with a user-defined importance sampling function.
- Multiple Instance Learning with Manifold Bags46
It is argued that in many applications of MIL the bags are better modeled as low dimensional manifolds in high dimensional feature space, and it is shown that the geometric structure of such manifold bags affects PAC-learnability.
- 45
- Deep Fundamental Matrix Estimation Without Correspondences43
Novel neural network architectures are proposed to estimate fundamental matrices in an end-to-end manner without relying on point correspondences to achieve competitive performance with traditional methods without the need for extracting correspondences.
- An algorithm competition for automatic species identification from herbarium specimens42
This work submitted its Herbarium 2019 data set to the Fine‐Grained Visual Categorization sub‐competition (FGVC6) hosted on the Kaggle platform to encourage the development of an automatic species identification algorithm.
- 41
- From Bikers to Surfers: Visual Recognition of Urban Tribes38
This paper presents a probabilistic analysis of the response of the immune system to the presence of Tournaisian infectious disease, which has the potential to infect other immune systems with similar defences.
- The Herbarium 2021 Half–Earth Challenge Dataset and Machine Learning Competition37
The Herbarium 2021 Half–Earth dataset is introduced: the largest and most diverse dataset of herbarium specimen images, to date, for automatic taxon recognition.
- PlateClick: Bootstrapping Food Preferences Through an Adaptive Visual Interface37
PlateClick is a novel system that bootstraps food preference using a simple, visual quiz-based user interface that outperforms other baselines by a significant margin, and the learning process can be completed in less than one minute.
- 37
- Finding boundaries in natural images: A new method using point descriptors and area completion37
An approach to image segmentation for natural scenes containing image texture is developed which consists of a novel means of describing points in natural images and an associated distance function for comparing these descriptors.
- 36
- 33
- 30
- 29
- 28
- 27
- 26
- 26
- 25
- 25
- 25
- 24
- 24
- 24
- 23
- 23
- 23
- 22
- 21
- 21
- 20
- 20
- 17
- 17
- 17
- 16
- 16
- 16
- 16
- 16
- 15
- 15
- 15
- 14
- 14
- 14
- 13
- 13
- 12
- 11
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- 10
- RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding9
AVENEA (Retrieval-Augmented Visual culturE uNdErstAnding), a new benchmark designed to advance visual culture understanding through retrieval, focusing on two tasks: culture-focused visual question answering (cVQA) and culture-informed image captioning (cIC).
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.