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
- Yunhong WangSuggested from co-authorship
- Ling ShaoSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works144 from public data
- Normalization Techniques in Training DNNs: Methodology, Analysis and Application537
A unified picture of the main motivation behind different approaches from the perspective of optimization is provided, and a taxonomy for understanding the similarities and differences between them is presented.
- 312
- Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers292
A novel transformer-based Feature Shrinkage Pyramid Network (FSPNet), which aims to hierarchically decode locality-enhanced neighboring transformer features through progressive shrinking for camou-flaged object detection and significantly outperforms the existing 24 competitors on three challenging COD benchmark datasets under six widely-used evaluation metrics.
- Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning210
This paper proposes to transfer partial knowledge by freezing or fine-tuning particular layer(s) in the base model to control the extent of preserved transferability, and introduces an evolutionary search based method that is efficient to simultaneously locate the target layers and determine their individual learning rates.
- 210
- TokenPacker: Efficient Visual Projector for Multimodal LLM206
This work introduces TokenPacker, a novel visual projector designed to generate condensed visual tokens through a coarse-to-fine scheme, and proposes a dynamic image slicing scheme to efficiently handle high-resolution images with TokenPacker.
- 184
- stagNet: An Attentive Semantic RNN for Group Activity Recognition164
A novel attentive semantic recurrent neural network (RNN) for understanding group activities in videos, dubbed as stagNet, is proposed, based on the spatio-temporal attention and semantic graph, and adopted to attend to key persons/frames for improved performance.
- Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification162
This work proposes a novel graph-based framework, namely Multi-Granular Hypergraph (MGH), to pursue better representational capabilities by modeling spatiotemporal dependencies in terms of multiple granularities to enhance the overall video representation.
- Jointly Learning Structured Analysis Discriminative Dictionary and Analysis Multiclass Classifier160
The classification approach of the ADDL model is very efficient, because it can avoid the extra time-consuming sparse reconstruction process with trained dictionary for each new test data as most existing DL algorithms.
- 160
- Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation146
A novel activation modulation and recalibration scheme that establishes a new state-of-the-art performance on the PASCAL VOC 2012 dataset, surpassing not only current methods trained with the image-level of supervision but also some methods relying on stronger supervision, such as saliency label.
- 135
- Auto-Encoding Twin-Bottleneck Hashing133
This paper proposes an efficient and adaptive code-driven graph, which is updated by decoding in the context of an auto-encoder, and introduces into the framework twin bottlenecks that exchange crucial information collaboratively.
- Anchor-Free Person Search132
This work presents the Feature-Aligned Person Search Network (AlignPS), the first anchor-free framework to efficiently tackle this challenging task, and proposes an aligned feature aggregation module to generate more discriminative and robust feature embeddings by following a "re-id first" principle.
- 131
- Invertible Zero-Shot Recognition Flows119
The proposed Invertible Zero-shot Flow (IZF) learns factorized data embeddings with the forward pass of an invertible flow network, while the reverse pass generates data samples and theoretically extends conventional generative flows to a factorized conditional scheme.
- Semi-supervised local multi-manifold Isomap by linear embedding for feature extraction108
This paper proposes a semi-supervised local multi-manifold Isomap learning framework by linear embedding that can apply the labeled and unlabeled training samples to perform the joint learning of neighborhood preserving local nonlinear manifold features and a linear feature extractor, and evaluates SSMM-Isomap for manifold feature learning, data clustering and classification.
- TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights105
This work proposes a Ternary-Binary Network (TBN), which provides an efficient approximation to standard CNNs, and demonstrates its consistent effectiveness when applied to various CNN architectures, and provides an optimal tradeoff between memory, efficiency and performance.
- 103
- Multi-stream Deep Networks for Person to Person Violence Detection in Videos103
This paper proposes a novel framework, i.e., multi-stream deep convolutional neural networks, for person to person violence detection in videos, and develops an acceleration stream to capture the important intense information usually involved in violent actions.
- Semantics-Aware Spatial-Temporal Binaries for Cross-Modal Video Retrieval93
A novel binary representation learning framework, named Semantics-aware Spatial-temporal Binaries, which simultaneously considers spatial-tem temporal context and semantic relationships for cross-modal video retrieval and adopts an iterative optimization scheme to learn deep encoding functions with attribute-guided stochastic training.
- 89
- P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching88
A dual fully-convolutional framework is presented that maps 2D and 3D inputs into a shared latent representation space to simultaneously describe and detect keypoints and achieves state-of-the-art results for the task of indoor visual localization.
- Clip-aware expressive feature learning for video-based facial expression recognition79
A video is divided into several short clips for processing and a clip-aware emotion-rich feature learning network (CEFLNet) is proposed for robust video-based FER, aiming to encode clip-based spatio-temporal features from the clips of a video.
- 78
- ACGNet: Action Complement Graph Network for Weakly-Supervised Temporal Action Localization73
This paper enhances segment-level representations with a simple yet effective graph convolutional network, namely action complement graph network (ACGNet) that facilitates the current video segment to perceive spatial-temporal dependencies from others that potentially convey complementary clues, implicitly mitigating the negative effects caused by the two issues above.
- Learning Multi-Attention Context Graph for Group-Based Re-Identification71
A novel unified framework based on graph neural networks is proposed to simultaneously address the above two group-based re-id tasks, i.e., group re-ID and group-aware person re-ids, and a context graph with group members as its nodes to exploit dependencies among different people is constructed.
- 71
- 62
- Scalable Block-Diagonal Locality-Constrained Projective Dictionary Learning59
This work proposes a novel structured discriminative block-diagonal dictionary learning method, referred to as scalable Locality-Constrained Projective Dictionary Learning (LC-PDL), for efficient representation and classification and incorporates a locality constraint of atoms into the DL procedures to keep local information and obtain the codes of samples over each class separately.
- 55
- Highly-Economized Multi-view Binary Compression for Scalable Image Clustering54
This work introduces a novel approach named Highly-economized Scalable Image Clustering (HSIC) that radically surpasses conventional image clustering methods via binary compression and intuitively unify the binary representation learning and efficient binary cluster structure learning into a joint framework.
- 53
- 53
- 51
- 47
- GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector46
A novel end-to-end group collaborative learning network, termed GCoNet+, which can effectively and efficiently identify co-salient objects in natural scenes and outperforms the existing 12 cutting-edge models.
- 46
- Fast action retrieval from videos via feature disaggregation46
A simple and efficient hashing scheme for high-dimensional video data, called Disaggregation Hashing (DH), that exploits the correlations among different feature dimensions and outperforms the state-of-the-art methods on three realistic action datasets.
- Exploring Visual Context for Weakly Supervised Person Search45
This paper inventively considers weakly supervised person search with only bounding box annotations, and discovers three levels of context clues in unconstrained natural images that promote local and global discriminative capabilities and enhances clustering accuracy.
- DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detection43
This paper reveals that the recently developed Diffusion Model is a scalable data engine for object detection, consisting of a pre-trained diffusion model and an effective Detection-Adapter, contributing to generating scalable, diverse and generalizable detection data in a plug-and-play manner.
- AlignDet: Aligning Pre-training and Fine-tuning in Object Detection40
AlignDet is proposed, a unified pre-training framework that can be adapted to various existing detectors to alleviate discrepancies in data, model, and task between the pre-training and fine-tuning procedure in existing practices, which implicitly limit the detector’s performance, generalization ability, and convergence speed.
- 38
- Adversarial Binary Coding for Efficient Person Re-Identification36
The proposed Adversarial Binary Coding (ABC) implicitly fits the feature distribution to the expected binary one by optimizing the Wasserstein distance and seamlessly embeds the ABC into a similarity measuring deep neural network to enhance the semantic discriminability of binary codes.
- 35
- 33
- Learning Attentive and Hierarchical Representations for 3D Shape Recognition33
Experimental results clearly show that HEAR outperforms the state-of-the-art approaches on three 3D shape recognition tasks including generic 3D shape retrieval, 3D shape classification and sketch-based 3D shape retrieval.
- Efficient Person Search: An Anchor-Free Approach32
This work presents an anchor-free approach to efficiently tackling person search, and names its framework as Feature-Aligned Person Search Network (AlignPS), which achieves state-of-the-art or competitive performance on two challenging person search benchmarks, but can be also extended to other challenging searching tasks such as animal and object search.
- Few-Shot Ensemble Learning for Video Classification with SlowFast Memory Networks32
This paper introduces a family of few-shot learners based on SlowFast networks which are used to extract informative features at multiple rates, and incorporates a memory unit into each network to enable encoding and retrieving crucial information instantly.
- 32
- 30
- 29
- Embarrassingly Simple Binary Representation Learning27
This paper proposes an embarrassingly simple approach to binary representation learning, which shows that, when properly designed, even such a simple network can generate effective binary codes, by fully exploring data semantics without any held-out alternating updating steps or auxiliary models.
- Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network26
A novel transformer model that includes only the encoder is designed, thus significantly reducing the computational cost and a novel network termed Puff-Net, i.e., pure content and style feature fusion network is proposed, i.e., pure content and style feature fusion network.
- CDFormer: When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution26
This paper introduces a diffusion-based module CD Former to first learn Con-tent Degradation Prior (CDP) in both low- and high-resolution images, and then approximate the real distribution given only low-resolution information, and applies an adaptive SR network CDFormersR that effectively utilizes CDP to refine features.
- S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration25
This paper presents a novel guided learning paradigm from real-valued to distill binary networks on the final prediction distribution, to minimize the loss and obtain desirable accuracy on BNNs.
- Latent Memory-augmented Graph Transformer for Visual Storytelling23
A novel Latent Memory-augmented Graph Transformer~(LMGT), a Transformer based framework for visual story generation that learns and records highly summarized latent information as the story line from the image stream and the sentence history and introduces an augmented latent memory unit.
- RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds20
The key to the approach is a range-aware unsigned distance function together with a surface-oriented semantic segmentation module that demonstrates superior generalization capability across multiple unseen datasets, which is nearly impossible for all existing approaches.
- Low-rank analysis–synthesis dictionary learning with adaptively ordinal locality19
A discriminative low-rank analysis-synthesis dictionary learning (LR-ASDL) algorithm with the adaptively ordinal locality is proposed for object classification and clearly outperforms some analysis and synthesis dictionary learning algorithms using deep and hand-crafted features.
- Learning Deformable and Attentive Network for image restoration18
A Deformable and Attentive Network (DANet) to address the problems of image restoration and deformable convolution, which achieves state-of-the-art (SOTA) results for various IR tasks, including image denoising, JPEG artifacts removal, and real-world super resolution.
- Unified Unsupervised Salient Object Detection via Knowledge Transfer17
A Progressive Curriculum Learning-based Saliency Distilling (PCL-SD) mechanism to extract saliency cues from a pre-trained deep network, and an adapter-tuning method is devised to transfer the acquired saliency knowledge.
- 17
- A Joint Generative Model for Zero-Shot Learning17
A joint generative model to synthesize features as the replacement for unseen data to mitigate the gap between seen and unseen class data is proposed and the superiority of this framework over the state-of-the-art approaches is shown.
- Robust kernel dictionary learning using a whole sequence convergent algorithm17
A new optimization model to learn the robust kernel dictionary while isolating outliers in the training samples is proposed, essentially based on the decomposition of the reconstruction error into small dense noises and large sparse outliers.
- Uncertainty-Guided Refinement for Fine-Grained Salient Object Detection16
The uncertainty guidance learning approach to SOD is introduced, intended to enhance the model’s perception of uncertain regions and generate a highly-saturated fine-grained saliency prediction map.
- 16
- Movienet-PS: A Large-Scale Person Search Dataset in the Wild16
This paper introduces a new PS dataset, namely MovieNet-PS, based on an existing large-scale movie dataset, and proposes a novel global-local context network, which exploits scene and group context to boost the search performance.
- Deep Local Binary Coding for Person Re-Identification by Delving into the Details14
Deep Local Binary Coding significantly minimizes the accuracy gap between binary ReID methods and the state-of-the-art real-valued ones, whilst remarkably reducing query time and memory cost.
- ISmallNet: Densely Nested Network with Label Decoupling for Infrared Small Target Detection13
This work proposes iSmallNet, a multi-stream densely nested network with label decoupling for infrared small object detection, and develops an interior-boundary fusion module to integrate multi-granularity information.
- History-Enhanced Two-Stage Transformer for Aerial Vision-and-Language Navigation12
A History-Enhanced Two-Stage Transformer (HETT) framework, which integrates the two aspects through a coarse-to-fine navigation pipeline, and is designed to dynamically aggregate visual features into a structured spatial memory, enhancing comprehensive scene awareness.
- Open-Vocabulary Spatio-Temporal Action Detection12
This paper builds two benchmarks based on the existing STAD datasets and proposes a simple but effective method based on pretrained video-language models (VLM) that achieves a promising performance on novel classes.
- Automatic Detection of Tooth-Gingiva Trim Lines on Dental Surfaces12
This framework provides an automatic solution to trim line detection by making full use of raw high-resolution dental surfaces and outperform cutting-edge methods in both qualitative and quantitative evaluations.
- 12
- Layer-Wise Conditioning Analysis in Exploring the Learning Dynamics of DNNs12
This work proposes layer-wise conditioning analysis, which explores the optimization landscape with respect to each layer independently, and shows that batch normalization (BN) can stabilize the training, but sometimes result in the false impression of a local minimum, which has detrimental effects on the learning.
- 11
- 11
- Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization10
FVQ is effective, scalable, and generalizable: it attains 100% codebook usage even with a 262k-codebook, achieves state-of-the-art reconstruction performance, consistently improves with larger codebooks, higher vector channels, or longer training, and remains effective across different VQ variants.
- 10
- MACA: Memory-aided Coarse-to-fine Alignment for Text-based Person Search10
A novel TBPS framework, named Memory-Aided Coarse-to-fine Alignment (MACA), to learn an accurate and reliable alignment between the two modalities, improving the convergence and generalization ability of the model based on the learned discriminative features.
- Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection10
This paper explicitly encourages the concentration of inliers and the dispersion of virtual outliers via supervised and unsupervised contrastive losses, respectively, and adopts an easy-to-hard hierarchical augmentation strategy and performs contrastive aggregation at different depths of the network based on the strengths of data augmentation.
- Projection based weight normalization: Efficient method for optimization on oblique manifold in DNNs10
This work proposes to constrain the incoming weights of each neuron to be unit-norm, which is formulated as an optimization problem over the Oblique manifold, which has the property of regularization and collaborates well with the commonly used batch normalization technique.
- Similarity-Adaptive Latent Low-Rank Representation for Robust Data Representation10
A novel Similarity-Adaptive Latent Low-Rank Representation model that incorporates a reconstructive error minimization term over coefficients and salient features, which can clearly preserve the neighborhood information of salient features adaptively and make the coefficients coding process very efficient.
- TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification9
This work argues that both domain-specific and domain-invariant features are crucial for improving the generalization ability of reid models, and designs a novel framework, which is name two-stream adaptive learning (TAL), to simultaneously model these two kinds of information.
- CooPercept: Cooperative Perception for 3D Object Detection of Autonomous Vehicles9
This work introduces a semantic point cloud feature-level cooperative perception framework, termed CooPercept, designed to mitigate computing complexity and reduce turnaround time, and demonstrates that the proposed CooPercept model surpasses comparable perception models, achieving enhanced detection accuracy and greater detection robustness.
- 9
- RefineTAD: Learning Proposal-free Refinement for Temporal Action Detection9
This work proposes a learnable, proposal-free refinement method for fine boundary localization, named RefineTAD, and proposes an offset focusing strategy to progressively refine the predicted results of TAD models in a coarse-to-fine manner with the authors' multi-scale offsets.
- Contour Primitive of Interest Extraction Network Based on One-Shot Learning for Object-Agnostic Vision Measurement9
This work proposes the contour primitive of interest extraction network (CPieNet) based on the one-shot learning framework, featuring a designated regular contour part lying on a specified object, which provides the essential geometric information for vision measurement.
- 8
- Video Frame Interpolation with Flow Transformer7
This paper designs a Flow Transformer Block that calculates the temporal self-attention in a matched local area with the guidance of flow, making the framework suitable for interpolating frames with large motion while maintaining reasonably low complexity.
- 7
- STAR: STacked AutoRegressive Scheme for Unified Multimodal Learning6
This work introduces STAR: a STacked AutoRegressive scheme for task-progressive unified multimodal learning, which freezes the parameters of the fundamental autoregressive (AR) model and progressively stacking isomorphic AR modules to avoid cross-task interference while expanding the model's capabilities.
- 6
- 6
- Multi-Classifier Adversarial Optimization for Active Learning6
MAOAL employs task-specific decision boundaries for data alignment while selecting the most informative samples to label, and introduces a novel classifier class confusion (C3) metric, which represents the classifier discrepancy as the inter-class correlation of classifier outputs.
- 6
- 5
- Efficient Visual Recognition5
Although visual recognition has made significant progress, especially in the past several years, there is continued need for vigorous research to solve many challenging problems towards highly efficient visual recognition including achieving energy efficiency and label/ sample efficiency.
- Robust Neighborhood Preserving Low-Rank Sparse CNN Features for Classification5
This work investigates how to discover the robust low-rank and sparse CNN features and shows how these features behave for image classification, specifically for the case that the number of training data is relatively small.
- 4
- Edit3D: Elevating 3D Scene Editing with Attention-Driven Multi-Turn Interactivity4
This work proposes a multi-turn editing framework and introduces an attention-driven open-set segmentation (ADSS) technique within this framework, which allows for more precise segmentation of parts, which enhances the editing precision and minimizes interference with pixels in areas that are not being edited.
- 4
- 4
- 4
- 3
- Self-Paced Learning for Open-Set Domain Adaptation3
This work proposes a novel framework based on self-paced learning to distinguish common and unknown class samples precisely, referred to as SPLOS (self- paced learning for open-set), and generates pseudo labels and design a cross-domain mixup method tailored for OSDA scenarios.
- Generalizable Person Search on Open-world User-Generated Video Content3
This work focuses on learning domain-invariant representations for both detection and ReID by introducing a multi-task prototype-based domain-specific batch normalization, and a channel-wise ID-relevant feature decorrelation strategy.
- Lifelong Scene Text Recognizer via Expert Modules3
The lifelong scene text recognizer (LSTR) that learns STR tasks incrementally while alleviating forgetting is proposed and the incremental task prediction network (ITPN) is proposed to identify the most related task category by pulling the features of the same task closer and pushing those of different tasks farther apart.
- 3
- An End-to-End Pyramid Convolutional Neural Network for Dehazing3
Experimental results demonstrate that on both the synthesized and the natural hazy image datasets, the proposed EPD-Net achieve superior dehazed performance than other representative dehazing algorithms in terms of objective indicators such as PSNR, SSIM, running time and the subjective visual quality.
- DCN: Decoupled-Coupled Network for Text-based Person Search2
This paper first attempts to resolve the above conflicts by proposing a Decoupled Proposal Selection (DPS) strategy, inspired by the divide-and-conquer principle, and presents a Coupled Cascade Refinement (CCR) module to jointly optimize both sub-tasks in a multi-stage manner.
- 2
- Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation2
This paper proposes a Parallel Pre-trained Transformers (PPT) framework to accomplish the synthetic data-based Instance Segmentation task, and leverages the off-the-shelf pre-trained vision Transformers to alleviate the gap between natural and synthetic data.
- 2
- 2
- VITRIX-UniViTAR: Unified Vision Transformer with Native Resolution1
UniViTAR is introduced, a family of homogeneous vision foundation models tailored for unified visual modality and native resolution scenario in the era of multimodal, which achieves state-of-the-art performance on a wide variety of visual-related tasks.
- Large Models are Good Annotators for Zero-Shot Learning1
This work introduces a three-step interaction process with ChatGPT-comprising preliminary design, hierarchical refinement, and specific value determination-to generate attributes that are both category-shared and discriminative for classification, and develops a method that encodes attributes and their values as potential text pairings, leveraging CLIP's retrieval capabilities for annotation.
- Multi-Scale Reconstruction and Relation Decomposition Modeling for Group Activity Recognition1
This work proposes a novel GAR approach termed multi-scale cross-distance transformer (MSCD-Former), capable of capturing diverse actor relation contexts in multiple spatiotemporal scales, and introduces a multi-scale reconstructive learning measure (MSR-Learning) between adjacent scales of CDA-Blocks.
- 1
- 1
- 1
- Fast Dense Residual Network: Enhancing Global Dense Feature Flow for Text Recognition1
This paper proposes an efficient and effective CNN framework, i.e., Fast Dense Residual Network (FDRN), for text recognition and proposes a new fast residual dense block (f-RDB) to retain the ability of local feature fusion and local residual learning of original RDB, which can reduce the computing efforts at the same time.
- Disco4D: Towards Prior-Free Motion Representation Learning for Point Cloud Videos Via Self-Disentangled Contrastive Pre-Training–
This work proposes Disco4D, a self-disentangled pre-training to extract expressive 4D representations, to separate motion learning in the high-level latent space of the MAE bottleneck while performing geometric reconstruction in the low-level Euclidean space.
- –
- Dual-view Driver Gaze Estimation via Mutual Enhancement–
A mutual enhancement-based dual-view driver gaze estimation method, to predict both gaze directions and gaze zones based on two face images with different camera settings, which significantly outperforms state-of-the-art methods in both gaze direction estimation and gaze zone classification tasks.
- –
- Object Referring-Guided Scanpath Prediction with Perception-Enhanced Vision-Language Models–
A novel model is proposed, ScanVLA, to first exploit a Vision-Language Model (VLM) to extract and fuse inherently aligned visual and linguistic feature representations from the input image and referring expression and adopt a frozen Segmentation LoRA as an auxiliary component to help localize the referred object more precisely.
- PRISM: Preference-Guided Semantic Reasoning with Vision-Language Models for Object Goal Navigation–
PRISM is introduced, a preference-guided semantic reasoning and mapping framework that integrates vision-language models (VLMs) into the navigation loop to support efficient semantic object search.
- –
- –
- –
- –
- –
- –
- –
- –
- SIDE: Self-supervised Intermediate Domain Exploration for Source-free Domain Adaptation–
Self-supervised intermediate domain exploration (SIDE) is proposed that effectively bridges the domain gap with an intermediate domain, where samples are cyclically filtered out in a self- supervised fashion and an inter-domain gap transition module is developed to mitigate possible distribution mismatches between the source and target data.
- –
- Boosting Open-Set Domain Adaptation with Threshold Self-Tuning and Cross-Domain Mixup–
A novel threshold self- tuning and cross-domain mixup (TSCM) method that considers multiple criteria instead of only the confidence and uses the threshold generated by itself to separate common and unknown classes in the target domain.
- –
- –
- PACE: Predictive and Contrastive Embedding for Unsupervised Action Segmentation–
PACE is proposed, a unified UAS framework leveraging both predictability and similarity information for more accurate action segmentation that achieves up to 26.9% improvements in F1-score over the state of the art.
- Exploring Learning Dynamics of DNNs via Layerwise Conditioning Analysis–
This work shows that batch normalization (BN) can adjust the magnitude of the layer activations/gradients, and thus stabilizes the training, and experimentally observes that BN can improve the layer-wise conditioning of the optimization problem.
- –
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 2026-10-14. 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.