Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks158 from public data
- 3,013
- Distractor-Aware Siamese Networks for Visual Object Tracking1,530
This paper focuses on learning distractor-aware Siamese networks for accurate and long-term tracking, and extends the proposed approach for long- term tracking by introducing a simple yet effective local-to-global search region strategy.
- The Sixth Visual Object Tracking VOT2018 Challenge Results804
The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative; results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years.
- 458
- OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction423
OccFormer, a dual-path transformer network to effectively process the 3D volume for semantic occupancy prediction, achieves a long-range, dynamic, and efficient encoding of the camera-generated 3D voxel features.
- WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition375
A distributed framework is developed to train face recognition models efficiently without tampering with the performance, and comprehensive baselines are established on a rich-attribute test set under FRUITS-100ms/500ms/1000ms protocol.
- MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer338
MonoViT is a brand-new framework combining the global reasoning enabled by ViT models with the flexibility of self-supervised monocular depth estimation, yielding depth prediction at a higher level of detail and accuracy, allowing MonoViT to achieve state-of-the-art performance on the established KITTI dataset.
- OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception321
In the OpenOccupancy benchmark, the large-scale nuScenes dataset is extended with dense semantic occupancy annotations and the Cascade Occupancy Network (CONet) is proposed to refine the coarse prediction, which relatively enhances the performance by ∼30% than the baseline.
- End-to-End Flow Correlation Tracking with Spatial-Temporal Attention314
The FlowTrack is proposed, which focuses on making use of the rich flow information in consecutive frames to improve the feature representation and the tracking accuracy and is the first work to jointly train flow and tracking task in deep learning framework.
- DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving310
The proposed DriveDreamer is the first world model established from real-world driving scenarios, harnessing the powerful diffusion model to construct a comprehensive representation of the complex environment and introduces a two-stage training pipeline.
- 294
- Attention-Guided Unified Network for Panoptic Segmentation293
The underlying relationship between FG objects and BG contents is revealed, in particular, FG objects provide complementary cues to assist BG understanding, and the Attention-guided Unified Network (AUNet) is named, a unified framework with two branches for FG and BG segmentation simultaneously.
- BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving291
The multi-task BEVerse outperforms existing single-task methods on 3D object detection, semantic map construction, and motion prediction and favors in significantly improved efficiency.
- The Devil Is in the Details: Delving Into Unbiased Data Processing for Human Pose Estimation284
The Unbiased Data Processing (UDP) for human pose estimation can be achieved by combining the two together and not only boosts the performance of existing methods by a large margin but also plays a important role in result reproducing and future exploration.
- CompletionFormer: Depth Completion with Convolutions and Vision Transformers201
A Joint Convolutional Attention and Transformer block (JCAT), which deeply couples the convolutional attention layer and Vision Transformer into one block, as the basic unit to construct the depth completion model in a pyramidal structure, which outperforms state-of-the-art CNNs-based methods on the outdoor KITTI Depth Completion benchmark and indoor NYUv2 dataset.
- CAFE: Learning to Condense Dataset by Aligning Features165
This paper proposes a novel scheme to Condense dataset by Aligning FEatures (CAFE), which explicitly attempts to preserve the real-feature distribution as well as the discriminant power of the resulting synthetic set, lending itself to strong generalization capability to various architectures.
- MVSTER: Epipolar Transformer for Efficient Multi-View Stereo148
MVSTER uses a detachable monocular depth estimator to enhance 2D semantics and uses cross-attention to construct data-dependent 3D associations along epipolar line and is built in a cascade structure, where entropy-regularized optimal transport is leveraged to propagate finer depth estimations in each stage.
- DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation145
DriveDreamer4D is the first to utilize video generation models for improving 4D reconstruction in driving scenarios and significantly enhances generation quality under novel trajectory views, achieving a relative improvement in FID compared to PVG, S3Gaussian, and Deformable-GS.
- DriveWorld: 4D Pre-Trained Scene Understanding via World Models for Autonomous Driving129
This paper proposes a Memory State-Space Model for spatiotemporal modelling, which consists of a Dynamic Memory Bank module for learning temporal-aware latent dynamics to predict future changes and a Static Scene Propagation module for learning spatial-aware latent statics to offer comprehensive scene contexts.
- SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation112
This paper proposes a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras, and adopts the two-frame structure-from-motion to extract scale-aware pseudo depths to pretrain the models.
- 111
- ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration100
ReconDreamer is introduced, which enhances driving scene reconstruction through incremental integration of world model knowledge through incremental integration of world model knowledge and is the first method to effectively render in large maneuvers.
- 100
- WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens98
This work introduces WorldDreamer, a pioneering world model to foster a comprehensive comprehension of general world physics and motions, which significantly enhances the capabilities of video generation and showcases versatility in executing tasks such as text-to-video conversion, image-tovideo synthesis, and video editing.
- End-to-end Video-level Representation Learning for Action Recognition97
This paper builds upon two-stream ConvNets and proposes Deep networks with Temporal Pyramid Pooling (DTPP), an end-to-end video-level representation learning approach, to address problems of partial observation training and single temporal scale modeling in action recognition.
- UCT: Learning Unified Convolutional Networks for Real-Time Visual Tracking80
The UCT treats feature extractor and tracking process (ridge regression) both as convolution operation and trains them jointly, enabling learned CNN features are tightly coupled to tracking process and results in superior tracking performance, while maintaining real-time speed.
- 69
- 66
- 59
- 57
- 51
- DiffBEV: Conditional Diffusion Model for Bird's Eye View Perception50
This work proposes an end-to-end framework, named DiffBEV, to exploit the potential of diffusion model to generate a more comprehensive BEV representation and is the first to apply diffusion model to BEV perception.
- Structure-Aware Face Clustering on a Large-Scale Graph with 107Nodes46
The proposed STructure-AwaRe Face Clustering (STAR-FC) method is the first to train on very large-scale graph with 20M nodes, and achieve superior inference results on 12M testing data.
- EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation45
This work presents EgoVid-5M, the first high-quality dataset specifically curated for egocentric video generation, and introduces EgoDreamer, which is capable of generating egocentric videos driven simultaneously by action descriptions and kinematic control signals.
- OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline43
This paper develops a flexible and efficient stereo matching codebase, called OpenStereo, which includes training and inference codes of more than 10 network models, making it, to the knowledge, the most complete stereo matching toolbox available.
- 43
- Convolutional relation network for skeleton-based action recognition42
A dilation group-specific convolution module is proposed to aggregate relation messages of all the unit pairs on the skeleton graphs and achieves competitive performance on two large scale datasets, NTU RGB+D and Kinetics.
- State-Aware Re-Identification Feature for Multi-Target Multi-Camera Tracking42
In this framework, the occlusion status and orientation information are utilized in Re-ID model with human pose information considered and the tracklet association using the proposed fused tracking feature is adopted to handle the fragment problem.
- 39
- Introspective Deep Metric Learning35
This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images, and proposes an introspective similarity metric to make similarity judgments between images considering both their semantic differences and ambiguities.
- 35
- Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark34
The Autonomous-driving StreAming Perception (ASAP) benchmark is proposed, which is the first benchmark to evaluate the online performance of vision-centric perception in autonomous driving and establishes baselines for camera-based streaming 3D detection, which consistently enhance the streaming performance across various hardware.
- The 3rd Anti-UAV Workshop & Challenge: Methods and Results32
A brief summary of the 3rd Anti-UAV Workshop&Challenge is provided including brief introductions to the top three methods in each track including brief introduction to the bottom three methods.
- Evidential Detection and Tracking Collaboration: New Problem, Benchmark and Algorithm for Robust Anti-UAV System32
Extensive experiments show the method outperforms SOTA approaches and validate the ability of AntiUAV600 to enhance UAV perception performance due to its large scale and complexity.
- ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction30
ReconDreamer-RL is proposed, a framework designed to integrate video diffusion priors into scene reconstruction to aid reinforcement learning, thereby enhancing end-to-end autonomous driving training and narrows the sim2real gap for closed-loop evaluation and reinforcement learning.
- 29
- 29
- 28
- An Efficient Optical Flow Based Motion Detection Method for Non-stationary Scenes28
The experimental results show that the method adapts itself to different situations and outperforms the state-of-the-art realtime methods, indicating the advantages of the optical flow based method.
- Gait Recognition in the Wild: A Large-Scale Benchmark and NAS-Based Baseline27
The proposed GREW benchmark proves to be essential for both training and evaluating gait recognizers in unconstrained scenarios, and the Single Path One-Shot neural architecture search with uniform sampling for Gait recognition is proposed, named SPOSGait, which is the first NAS-based gait recognition model.
- A negative correlation ensemble transfer learning method for fault diagnosis based on convolutional neural network27
A new negative correlation ensemble transfer learning method (NCTE) is proposed, and results show that NCTE has achieved a good results compared with other machine learning and deep learning method.
- 27
- 27
- 26
- 25
- 25
- HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation24
The proposed HumanDreamer is a decoupled human video generation framework that first generates diverse poses from text prompts and then leverages these poses to generate human-motion videos, and can facilitate other downstream tasks, such as pose sequence prediction and 2D-3D motion lifting.
- Invertible encryption network for optical image cryptosystem24
An invertible encryption network (IENet) is firstly proposed for optical image cryptosystem, which applies a novel learning way to optical image encryption for the first time, to the best of the authors' knowledge.
- 24
- 23
- HFT: Lifting Perspective Representations via Hybrid Feature Transformation21
A novel framework with a Hybrid Feature Transformation module (HFT) is proposed, which decouple the feature maps produced by HFT for estimating the layout of outdoor scenes in BEV and design a mutual learning scheme to augment hybrid transformation by applying feature mimicking.
- 21
- 21
- 21
- Medical image encryption based on biometric keys and lower–upper decomposition with partial pivoting19
The iris is used for medical image encryption, which improves the security of the encryption scheme and the combination of asymmetric optical encryption and three-dimensional Lorenz chaos improves the key space and solves the linear problem based on double-random phase encoding.
- 18
- Understanding common human driving semantics for autonomous vehicles17
This study designed and conducted two electroencephalography experiments for comparing the cerebral activities of human linguistics and driving understanding and proposed a neural-informed, semantics-driven framework to understand common human driving behavior in a brain-inspired manner.
- 17
- DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion16
DriveGen3D enable the generation of long driving videos and corresponding 3D scenes, achieving state-of-the-art results while maintaining efficiency.
- 16
- 16
- Motion control in saccade and smooth pursuit for bionic eye based on three-dimensional coordinates15
It is verified that saccade and smooth pursuit of bionic eye based on three-dimensional coordinates are feasible and the accuracy of 3D coordinates is improved.
- Load shuffling algorithms for split-platform AS/RS15
This paper addresses the issue of load shuffling on a new type of AS/RS, which have separate and independent mechanisms for horizontal and vertical movements, and presents the shuffling algorithms, and analyzes the required shuffling time and retrieval time.
- HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration14
This work introduces \textbf{HumanDreamer-X}, a novel framework that integrates multi-view human generation and reconstruction into a unified pipeline, which significantly enhances the geometric consistency and visual fidelity of the reconstructed 3D models.
- EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer14
Embodied Manipulation Media Adaptation (EMMA) is a framework for augmenting VLA policies that combines a generative data engine with an effective training pipeline and proposes AdaMix, a training strategy that adaptively weights samples according to policy performance to emphasize challenging samples.
- SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation14
A novel multi-person pose estimation framework, SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (SIMPLE), which enables SIMPLE to mimic the pose knowledge from the high-performance top-down pipeline, which significantly promotes SIMPLE's accuracy while maintaining its high efficiency during inference.
- A Novel 3D Vector Decomposition for Color-Image Encryption13
The proposed Cryptosystem accomplishes improved security by reducing the single-channel attack risk in individual color-image encryption and avoiding the vulnerable channel in sequential color- image encryption as well as reduced the amount of data of transform-based cryptosystem by avoiding the complex output.
- WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Exploration12
WonderFree is proposed, the first model that enables users to interactively generate 3D worlds with the freedom to explore from arbitrary angles and directions and ConsistView, a multi-view joint restoration mechanism that simultaneously restores multiple perspectives while maintaining spatiotemporal coherence.
- FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders12
A novel framework FaceMAE, where the face privacy and recognition performance are considered simultaneously, is proposed, which consistently reduces at least 50% error rate on LFW, CFP-FP and AgeDB.
- 12
- Adaptive Trajectory Tracking of Wheeled Mobile Robots Based on a Fish-eye Camera12
This paper presents a novel adaptive trajectory tracking control method, which can precisely control wheeled mobile robots only using an uncalibrated fish-eye camera fixed on the ceiling using the Barbalat lemma.
- 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
- 10
- 10
- 9
- DREAM+: Efficient Dataset Distillation by Bidirectional Representative Matching9
A novel matching strategy called Dataset Distillation by Bidirectional REpresentAtive Matching (DREAM+), which selects representative original images for bidirectional matching, is proposed, which significantly reduces the number of distillation iterations by more than 15 times without affecting performance.
- Refinement of Boundary Regression Using Uncertainty in Temporal Action Localization9
A Gaussian model is constructed for predicting the uncertainty variance of the boundary and improved state-of-the-art mAP@0.5 value and gains on both THUMOS14 and ActivityNet v1.3 datasets.
- 8
- Token-Label Alignment for Vision Transformers8
A token-label alignment method to trace the correspondence between transformed tokens and the original tokens to maintain a label for each to-ken, which improves the performance of ViTs on image classification, semantic segmentation, objective detection, and transfer learning tasks.
- 8
- DIAMONDNET: SHIP DETECTION IN REMOTE SENSING IMAGES BY EXTRACTING AND CLUSTERING KEYPOINTS IN A DIAMOND8
This work comes up with a novel ship detection framework based on the keypoint extraction technique that uses a convolutional neural network to detect ship keypoints and then cluster the keypoints into groups, where each group is composed of keypoints belonging to the same ship.
- Edge-Driven Multiple Trajectory Attention Model for Vehicle Routing Problems7
This work proposes a novel Edge-Driven Multiple Trajectory Attention Model (E-MTAM), built upon the encoder–decoder architecture, incorporating an edge-driven multi-head attention (EDMHA) block within the encoder to better utilize edge information.
- SSM-based detection of rice seedling deficiency7
A rice seedling deficiency detection method based on a state space model, aiming to improve detection precision for small seedlings, offering a novel and efficient solution for detecting missing seedlings in rice fields.
- 7
- SkatingVerse: A large‐scale benchmark for comprehensive evaluation on human action understanding7
SkatingVerse significantly helps the training and evaluation of HAU methods, the performance of existing HAU methods has much room to improve, and SkatingVerse helps to reduce such gaps, and unifying relevant tasks in HAU through a uniform dataset can facilitate more practical applications.
- Clinical application of endobronchial ultrasonography-guided transbronchial needle aspiration biopsy—a single center, large sample, real-world study7
EBUS-TBNA has good diagnostic value for different mediastinal and central pulmonary space-occupying lesions diseases, with highest sensitivity for tumors.
- Selection of Observation Position and Orientation in Visual Servoing with Eye-in-vehicle Configuration for Manipulator7
A mobile robot system with pan-tilt camera is designed, which calculates the observation position based on an observation and then moves there and simulation and experimental results are provided to validate the effectiveness of the proposed method.
- 7
- 6
- Adjacent-view Transformers for Supervised Surround-view Depth Estimation6
An Adjacent-View Transformer for Supervised Surround-view Depth estimation (AVT-SSDepth) is proposed, to jointly predict the depth maps across multiple surrounding cameras and achieves superior performance over existing state-of-the-art methods on both DDAD and nuScenes datasets.
- 6
- 6
- 6
- Identity-Enhanced Network for Facial Expression Recognition6
A novel identity-enhanced network (IDEnNet) is presented to eliminate the negative impact of identity factor and focus on recognizing facial expressions, and achieves the best or comparable state-of-the-art on all three datasets.
- Sonar image denoising based on Noise2Void self-supervised learning5
Noise2Void demonstrates comparable or even superior performance to conventional methods in denoising, regardless of whether the noise is speckle or Gaussian in nature.
- FOV Constraint Region Analysis and Path Planning for Mobile Robot with Observability to Multiple Feature Points5
A novel method for a mobile robot equipped with a pan-tilt camera to keep all points on objects in its view when it is moving based on FOV constraint region analysis and path planning is proposed.
- 5
- Novel fully convolutional network for cryptanalysis of cryptosystem by equal modulus decomposition5
A novel fully convolutional network model, which is an end-to-end deep learning method, to attack the EMD-based cryptosystem and can retrieve plaintext after inputting many ciphertext-plaintext pairs and optimizing parameters.
- 5
- 5
- Resolution Adaptative Network for Cryptanalysis of Asymmetric Cryptosystems4
A resolution adaptative network is proposed to attack the asymmetric optical cryptosystems, which solves the issue of requiring a lot of experiments to change the network structure and parameters for effectively attacking to ciphertexts with different resolutions.
- Value of 3.0T magnetic resonance imaging in the diagnosis of retroperitoneal tumors4
The diagnostic value of 3.0T MR for differentiating benign from malignant primary retroperitoneal tumors (RPTs) could be made through comprehensive analysis of combined diagnostic indices.
- 4
- DetRF: Detachable Novel Views Synthesis of Dynamic Scenes Using Backdrop-Driven Neural Radiance Fields3
This work employs a neural representation to capture the scene distribution in the static background and a 6D-input NeRF to represent dynamic objects, respectively, and offers high-quality view synthesis and a 3D solution to detach the background from the entire dynamic scene, which is called DetRF.
- WIP: Auditing Artist Style Pirate in Text-to-image Generation Models3
A new paradigm, called StyleAuditor, for artistic style auditing, which identifies if a suspect model has been fine-tuned using a specific artist’s artwork by analyzing style-related features and queries a trained discriminator to gain the auditing decisions.
- Efficacy and safety of Sanfeng Tongqiao Diwan in the treatment of upper airway cough syndrome: a randomized, double-blind, placebo-controlled clinical study3
The results of this trial represent rigorous clinical evidence for the application of Sanfeng Tongqiao Diwan in the treatment of upper airway cough syndrome and further support a new option in UACS treatment.
- Detachable Novel Views Synthesis of Dynamic Scenes Using Distribution-Driven Neural Radiance Fields3
The approach employs a neural representation to capture the scene distribution in the static background and a 6D-input NeRF to represent dynamic objects, respectively and outperforms previous methods in rendering texture details and motion areas while also producing a clean static background.
- 3
- 3
- Watch Where You Move: Region-Aware Dynamic Aggregation and Excitation for Gait Recognition2
A Region-aware Dynamic Aggregation and Excitation framework (GaitRDAE) that automatically searches for motion regions, assigns adaptive temporal scales and applies corresponding attention, and achieves state-of-the-art performance on several benchmark datasets.
- ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows2
This work contributes CS-54k, a high-quality corpus of scientific Q&A pairs in computer science, built from 14k CC-licensed papers, and derives two complementary subsets: CS-4k, a carefully curated benchmark for evaluating AI's ability to assist scientific research, and CS-50k, a large-scale training dataset.
- 2
- An Alternative Rural Housing Management Tool Empowered by a Bayesian Neural Classifier2
An efficient Bayesian classifier for house safety and habitability risk evaluations is constructed, enabling people with none-civil-engineering backgrounds to make judgements comparable with experts so that house risk levels can be checked regularly at low costs.
- 2
- 2
- 2
- Smooth-optimal Adaptive Trajectory Tracking Using an Uncalibrated Fish-eye Camera2
This paper presents a two-stage smooth-optimal trajectory tracking strategy that can be directly determined in an uncalibrated fish-eye image, and has a good performance in both tracking accuracy and motion smoothness.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- How to Train Your Robust Human Pose Estimator: Pay Attention to the Constraint Cue.1
The proposed occlusion augmentation with customized training schedules implicitly force the neural network focus on the constraint cue by dropping appearance information within keypoint-aware strategy and makes a remarkable improvement on more challenging CrowdPose dataset.
- 1
- XMask3D++: Cross-Modal Mask Reasoning for Open Vocabulary 3D Segmentation–
This work developed a mask generator based on the denoising UNet from a pre-trained diffusion model, leveraging its capability for precise textual control over dense pixel representations and enhancing the open-world adaptability of the generated masks, and introduces a 2D-to-3D mask adaptation module to improve the quality of back-projected 3D masks.
- –
- Multi-Path Collaborative Reasoning via Reinforcement Learning–
This work proposes Multi-Path Perception Policy Optimization (M3PO), a novel reinforcement learning framework that explicitly injects collective insights into the reasoning process and allows each trajectory to refine its reasoning with peer feedback, thereby cultivating more reliable multi-step reasoning patterns.
- –
- –
- –
- –
- –
- Construction of Cooking Heat transfer Model and Prediction of Temperature based on Machine Learning–
Two deep learning models, MDTN and LSTM, were used to learn the variation of the container temperature during heating and the results conformed to the laws of physics.
- –
- –
- Predicting the Power Consumption and Operating Rate of Enterprises in Major Public Events–
A novel long and short-term memory-based attentional algorithm to accurately predict the power consumption and corresponding operating rate of enterprises in major public events is proposed and optimize the proposed end-to-end deep learning model by standard stochastic gradient descent (SGD) algorithms.
- –
- –
- –
- A PSEUDO-SPLICING ALGORITHM FOR PARTIAL FINGERPRINT RECOGNITION BASED ON SIFT–
An algorithm to evaluate the quality of partial finger print by calculating the invalid blocks of fingerprint image and the result shows that the evaluation algorithm can effectively filter out low-quality fingerprints.
- Deep Neural Network Based Frame Reconstruction for Optimized Video Coding–
Techniques in the same vein effectively optimizing frame reconstruction through the use of the Deep Neural Networks (DNN) to further improve coding performance are described.
- –
- –
- The Features and Principles of Research Learning Evaluation–
Research learning evaluation is quite different from that of traditional learning, it is comprehensive, practical and scientific.
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 2026-10-12. 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.