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
- Babak Nadjar AraabiSuggested from co-authorship
- Laurent IttiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works193 from public data
- 1,953
- 1,935
- Enhanced-alignment Measure for Binary Foreground Map Evaluation1,716
This paper takes a detailed look at current binary FM evaluation measures and proposes a novel and effective E-measure (Enhanced-alignment measure), jointly capturing image-level statistics and local pixel matching information, which demonstrates the superiority of this measure over the available measures on 4 popular datasets via 5 meta-measures.
- Deeply Supervised Salient Object Detection with Short Connections1,458
This paper proposes a new salient object detection method by introducing short connections to the skip-layer structures within the HED architecture, which takes full advantage of multi-level and multi-scale features extracted from FCNs, providing more advanced representations at each layer, a property that is critically needed to perform segment detection.
- Pros and cons of GAN evaluation measures1,003
More than 19 quantitative and 4 qualitative measures for evaluating generative models with a particular emphasis on GAN-derived models are reviewed and critically discussed.
- 1Salient Object Detection: A Survey848
A comprehensive review of recent progress in salient object detection is provided and this field is situate among other closely related areas such as generic scene segmentation, object proposal generation, and saliency for fixation prediction.
- 651
- 535
- 508
- 461
- 450
- Salient Object Detection: A Benchmark416
This work analyzes benchmark datasets and scoring techniques and provides a quantitative comparison of 35 state-of-the-art saliency detection models to identify the scenes where models or humans fail to detect the most salient object.
- BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network402
This paper proposes a bifurcated backbone strategy (BBS) to split the multi-level features of RGB-D salient object detection into teacher and student features, and utilizes a depth-enhanced module (DEM) to excavate informative parts of depth cues from the channel and spatial views.
- Pros and cons of GAN evaluation measures: New developments393
New dimensions that are becoming important in assessing models (e.g. bias and fairness) are described and the connection between GAN evaluation and deepfakes is discussed, which are important areas of concern in the machine learning community today and progress in GAN Evaluation can help mitigate them.
- 387
- Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground347
This work identifies a serious design bias of existing SOD datasets which assumes that each image contains at least one clearly outstanding salient object in low clutter, and proposes a new high quality dataset and updates the previous saliency benchmark.
- 330
- Revisiting Video Saliency: A Large-Scale Benchmark and a New Model311
This work introduces a new benchmark for predicting human eye movements during dynamic scene free-viewing, and proposes a novel video saliency model that augments the CNN-LSTM network architecture with an attention mechanism to enable fast, end-to-end saliency learning.
- 286
- Defending Yarbus: Eye movements reveal observers' task267
Yarbus's idea that human eye-movement patterns are modulated top down by different task demands is supported by the data and continues to be an inspiration for future computational and experimental eye- Movement research.
- 250
- Cross-View Image Synthesis Using Conditional GANs231
This paper attempts to solve the novel problem of cross-view image synthesis, aerial to street-view and vice versa, using conditional generative adversarial networks (cGAN), and proposes two new architectures called Crossview Fork (X-Fork) and Crossview Sequential (x-Seq).
- A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'217
The effects of fitting a distribution or a model to the data, followed by repeated sampling from it, and the effects of fitting a distribution or a model to the data, followed by repeated sampling from it are investigated.
- 216
- 212
- 205
- Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2199
A quantitative comparison of three popular systems including Stable Diffusion, Midjourney, and DALL-E 2 in their ability to generate photorealistic faces in the wild finds that Stable diffusion generates better faces than the other systems, according to the FID score.
- 182
- What stands out in a scene? A study of human explicit saliency judgment173
It is concluded that fixations agree with saliency judgments, and classic bottom-up saliency models explain both, and computational models specifically designed for fixation prediction slightly outperform models designed for salient object detection over both types of data.
- What is a Salient Object? A Dataset and a Baseline Model for Salient Object Detection172
This work takes an in-depth look at the problem of salient object detection by studying the relationship between where people look in scenes and what they choose as the most salient object when they are explicitly asked, and suggests that themost salient object is the one that attracts the highest fraction of fixations.
- Bifurcated Backbone Strategy for RGB-D Salient Object Detection167
This paper uses the inherent multi-modal and multi-level nature of RGB-D salient object detection to devise a novel Bifurcated Backbone Strategy Network (BBS-Net), which significantly outperforms 18 state-of-the-art (SOTA) models on eight challenging datasets under five evaluation measures.
- Where Should Saliency Models Look Next?160
It is argued that to continue to approach human-level performance, saliency models will need to discover higher-level concepts in images: text, objects of gaze and action, locations of motion, and expected locations of people in images.
- 156
- A Review of Co-Saliency Detection Algorithms134
This article provides an overview of some related computer vision works, a comprehensive review of the fundamentals, challenges, and applications of co-saliency detection, and summarizes and categorizes the major algorithms in this research area.
- 133
- 133
- 114
- 110
- Analysis of Hand Segmentation in the Wild103
This work fine-tune RefineNet, a leading semantic segmentation method, for hand segmentation and finds that it does much better than the best contenders and explores whether conditional random fields can help refine generated hand segmentations.
- Paying Attention to Descriptions Generated by Image Captioning Models85
The agreement between bottom-up saliency-based visual attention and object referrals in scene description constructs is studied and the properties of human-written descriptions and machine-generated ones are investigated.
- Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features79
A framework that estimates the saliency of a given image using an ensemble of extreme learners, each trained on an image similar to the input image, and measured in terms of the mean of predicted saliency value by the ensembles members.
- Cross-view image synthesis using geometry-guided conditional GANs72
This paper addresses the problem of generating images across two drastically different views, namely ground (street) and aerial (overhead) views and resorts to homography as a guide to map the images between the views based on the common field of view to preserve the details in the input image.
- Online learning of task-driven object-based visual attention control72
A biologically-motivated computational model for learning task-driven and object-based visual attention control in interactive environments and is evaluated on visual navigation tasks, where obtained results lend support to the applicability and usefulness of the developed method for robotics.
- 71
- Bayesian optimization explains human active search71
It is confirmed that Gaussian Processes provide a general and unified theoretical account to explain passive and active function learning and search in humans and predicts human performance and searched locations better.
- 67
- Ego2Top: Matching Viewers in Egocentric and Top-View Videos66
This work proposes a framework to identify the egocentric viewers in the top-view video, modeling each view (egocentric or top) by a graph, and examines the effect of different parameters such as the number of egOCentric viewers and visual features.
- 64
- 61
- 60
- 60
- 59
- Human Attention in Image Captioning: Dataset and Analysis58
By integrating the soft attention model with image saliency, the model can significantly improve the model’s performance on Flickr30k and MSCOCO benchmarks and indicate a large gap between humans and machines in regards to top-down attention.
- 58
- Complementary effects of gaze direction and early saliency in guiding fixations during free viewing57
The results highlight that gaze direction is a strong attentional cue in guiding eye movements, complementing low-level saliency cues, and derived from both face and eyes of actors in the scene, and should be considered in constructing more predictive visual attention models in the future.
- Computational Modeling of Top-down Visual Attention in Interactive Environments55
The proposed models of top-down visual guidance considering task influences estimate the state of a human subject performing a task, and map that state to an eye position, and use Bayesian Networks to combine all the multi-modal factors in a unified framework.
- Augmented saliency model using automatic 3D head pose detection and learned gaze following in natural scenes54
This work extends the engineering and scientific applications of saliency models and helps better understand mechanisms of visual attention.
- Cost-sensitive learning of top-down modulation for attentional control54
A biologically-inspired model of visual attention known as basic saliency model, which is biased for object detection, is revised by implementing a new scale-wise surround inhibition, which allows achieving maximum object detection rate for real time tasks when maximum processing time is limited.
- Video Summarization Via Actionness Ranking53
A method to incorporate actionness data to explicitly regulate a learning algorithm that is trained for summary generation is developed, demonstrating an evident advantage compared to state-of-the-art summarization methods.
- Saliency Prediction in the Deep Learning Era: An Empirical Investigation.53
A large number of image and video saliency models are reviewed and compared over two image benchmarks and two large scale video datasets and factors that contribute to the gap between models and humans are identified.
- Improving Sequential Determinantal Point Processes for Supervised Video Summarization52
A new probabilistic distribution is designed such that, when it is integrated into SeqDPP, the resulting model accepts user input about the expected length of the summary, and significantly extend a popular video summarization dataset.
- Scene classification with a sparse set of salient regions51
The results prove that efficient scene classification, in terms of reducing the complexity of feature extraction is possible without a significant drop in performance.
- Saliency Revisited: Analysis of Mouse Movements Versus Fixations50
This paper revisits visual saliency prediction by evaluating the recent advancements in this field such as crowd-sourced mouse tracking-based databases and contextual annotations and proposes an evaluation methodology that allows accounting for contextual factors such as text, faces, and object attributes.
- Understanding and Visualizing Deep Visual Saliency Models48
This article analyzes the representations learned by individual neurons located at the intermediate layers of deep saliency models to study how the learned representations depend on the task, and fine-tune the same network using the same image set but for two different tasks: saliency prediction versus scene classification.
- Robust Handwritten Character Recognition with Features Inspired by Visual Ventral Stream48
This paper focuses on the applicability of the features inspired by the visual ventral stream for handwritten character recognition, and an analysis is conducted to evaluate the robustness of this approach to orientation, scale and translation distortions.
- Reconciling Saliency and Object Center-Bias Hypotheses in Explaining Free-Viewing Fixations47
A simple combined model of low-level saliency and object center bias that outperforms each individual component significantly over the authors' data, as well as on the Object and Semantic Images and Eye-tracking data set by Xu et al.
- SaliencyRank: Two-stage manifold ranking for salient object detection45
This work proposes a novel graph based ranking method to detect and segment the most salient object in a scene according to its relationship to image border (background) regions, i.e., the background feature.
- Combining Heterogeneous Classifiers for Network Intrusion Detection45
A combining classification approach for intrusion detection using four base classifiers ANN, SVM, kNN and decision trees is proposed using three combination strategies: majority voting, Bayesian averaging and a belief measure.
- An Unsupervised Game-Theoretic Approach to Saliency Detection44
A novel unsupervised game-theoretic salient object detection algorithm that does not require labeled training data and an iterative random walk algorithm to combine saliency maps produced by the Saliency Game using different features is proposed.
- 39
- Negative results in computer vision: A perspective38
What makes negative results important, how they should be disseminated and incentivized, and what lessons can be learned from cognitive vision research in this regard are addressed.
- 37
- 35
- A New Ensemble Adversarial Attack Powered by Long-Term Gradient Memories34
Experiments indicate that the proposed Serial-Mini-Batch-Ensemble-Attack outperforms state-of-the-art ensemble attacks over multiple pixel-to-pixel vision tasks including image translation and salient region prediction.
- Egocentric Meets Top-View34
This study addresses two basic yet challenging questions about having a set of egocentric videos and a top-view surveillance video, and evaluates the capability of the proposed approaches in terms of jointly addressing the temporal alignment and assignment tasks.
- A New Global Optimization Algorithm Inspired by Parliamentary Political Competitions33
A new numerical optimization algorithm inspired by political competitions during parliamentary head elections is proposed, which tries to simulate the intra and inter group competitions in trying to take the control of the parliament.
- 31
- 29
- Integrating Egocentric Videos in Top-View Surveillance Videos: Joint Identification and Temporal Alignment29
This paper proposes a unified framework to jointly solve all three problems of identification and temporal alignment of egocentric and top-view surveillance cameras, and evaluates the efficacy of the proposed approach on a publicly available dataset containing a variety of videos recorded in different scenarios.
- 28
- Multiple-target tracking in human and machine vision28
This paper reviews MTT studies in neuroscience and biologically inspired MTT methods in computer vision and discusses the ways in which they can be seen as complementary.
- Joint salient object detection and existence prediction28
This paper proposes a supervised learning approach for jointly addressing the salient object detection and existence prediction problems and adopts the structural SVM framework, which forms the two problems jointly in a single integrated objective function.
- Visual Weather Temperature Prediction27
This paper studies ambient temperature estimation based on deep neural networks in two scenarios a) estimating temperature of a single outdoor image, and b) predicting temperature of the last image in an image sequence using only image data.
- 27
- Invariance analysis of modified C2 features: case study—handwritten digit recognition26
This study shows that using features proposed by the modified model results in higher handwritten digit recognition rates compared with the original model over English and Farsi handwritten digit datasets, and demonstrates higher invariance of the modified models to various image distortions.
- 26
- 25
- Joint Learning of Audio–Visual Saliency Prediction and Sound Source Localization on Multi-face Videos24
This paper introduces a large-scale database of multi-face video in visual-audio condition, and finds that sound influences human attention, and conversely attention offers a cue to determine sound source on multi-face video.
- An Object-Based Bayesian Framework for Top-Down Visual Attention24
A Dynamic Bayesian Network (DBN) is described that infers probability distributions over attended objects and spatial locations directly from observed data that is more effective in employing and reasoning over spatio-temporal visual data.
- Three Birds One Stone: A Unified Framework for Salient Object Segmentation, Edge Detection and Skeleton Extraction.24
This paper introduces a horizontal cascade, each component of which is densely connected to the outputs of previous component, which allows for effectively exploiting features across different levels hierarchically to effectively address the multiple pixel-wise binary regression tasks.
- 23
- 23
- Multi-stream dynamic video Summarization22
A robust framework is presented that identifies a diverse set of important events among moving cameras that often are not capturing the same scene, and selects the most representative view at each event to be included in a universal summary, deeming it scalable and generic.
- An exocentric look at egocentric actions and vice versa22
The results demonstrate the possibility of transferring action information across the two domains and suggest new directions in relating first and third person vision for other tasks.
- 20
- 18
- Vanishing point attracts gaze in free-viewing and visual search tasks18
The hypothesis that vanishing point, similar to face, text (Cerf, Frady, & Koch, 2009), and gaze direction Borji, Parks, & Itti, 2014) guides attention in free-viewing and visual search tasks is supported.
- Fast Hand gesture recognition based on saliency maps: An application to interactive robotic marionette playing18
A tuned saliency-based model of visual attention is used to find potential hand regions in video frames and an improved Characteristic Loci feature extraction method is introduced and used to code obtained hand movement.
- 17
- A compact deep architecture for real-time saliency prediction16
A compact yet fast model for real-time saliency prediction using a modified U-net architecture, a novel fully connected layer, and central difference convolutional layers that facilitates the implicit capturing of the location-dependent information.
- 16
- 16
- Deep Audio-Visual Saliency: Baseline Model and Data15
This paper introduces a conceptually simple and effective Deep Audio-Visual Embedding for dynamic saliency prediction dubbed “DAVE” and demonstrates that audio-visual saliency model outperforms the video saliency models.
- Optimal attentional modulation of a neural population13
A unified framework that encompasses top-down attention and neural populations in the contexts of optimal population coding or biasing of visual search is described, shedding light onto the ongoing debate on whether attention modulates neural response gain, tuning width, and/or preferred feature.
- 11
- 11
- Fixation prediction with a combined model of bottom-up saliency and vanishing point11
A combined model of traditional saliency and a vanishing point channel is constructed and it is shown that this model outperforms state of the art saliency models using three scores on the authors' dataset.
- 10
- 10
- 9
- 8
- Egocentric Height Estimation8
A method of estimating the height of an egocentric camera without any calibration or reference points is proposed and a framework inspired by two stream networks comprising of two Convolutional Neural Networks, one based on spatial information, and onebased on information given by optical flow in a frame is introduced.
- 8
- 8
- 7
- 7
- GazeGAN: A Generative Adversarial Saliency Model based on Invariance Analysis of Human Gaze During Scene Free Viewing.7
A novel saliency model based on generative adversarial network (dubbed GazeGAN) is introduced, which combines classic skip connections with a novel center-surround connection in order to leverage multi level features, and a histogram loss based on Alternative Chi Square Distance (ACS HistLoss) is proposed to refine the saliency map in terms of luminance distribution.
- Color Image Segmentation with CLPSO-based Fuzzy7
The aim here is to automatically produce a fuzzy system for color classification and image segmentation with least number of rules and minimum error rate and less computational load than other methods like ANFIS, because it generates a smaller number of fuzzy rules.
- How good are deep models in understanding the generated images?6
It is concluded that a) deep models struggle to understand the generated content, and may do better after fine-tuning, and b) there is a large distribution shift between the generated images and the real photographs.
- 6
- 6
- EgoTransfer: Transferring Motion Across Egocentric and Exocentric Domains using Deep Neural Networks6
- 6
- 5
- A Synchronized Multi-Modal Attention-Caption Dataset and Analysis.5
A novel multi-modal dataset consisting of eye movements and verbal descriptions recorded synchronously over images is presented, revealing that human attention behaviour in free-viewing is different than image description as humans tend to fixate on a greater variety of regions under the latter task.
- 5
- Complementary datasets to COCO for object detection4
Two complementary datasets to COCO are introduced and some models are evaluated, used to test the generalization ability of object detectors and the source of errors are evaluated.
- 4
- Shape Defense4
It is shown that a) edge information can also benefit other adversarial training methods, and b) CNNs trained on edge-augmented inputs are more robust against natural image corruptions such as motion blur, impulse noise and JPEG compression, than CNNstrained solely on RGB images.
- Introduction to the Issue on Perception-Driven 360° Video Processing4
This special section examines perception driven 360 degrees video processing applications and covers such topics as perception models, VQA metrics, and compression/streaming techniques for 360° video/image.
- 4
- Bottom-Up Attention, Models of4
This chapter examines the recent progress in saliency prediction and proposed several avenues for future research in terms finer-grained analysis of deep saliency models, evaluation measures, datasets, annotation methods, cognitive studies, and new applications.
- Leverage eye-movement data for saliency modeling: Invariance Analysis and a Robust New Model4
A novel saliency model based on generative adversarial network (dubbed GazeGAN) is introduced, which combines classic skip connections with a novel center-surround connection in order to leverage multi level features, and a histogram loss based on Alternative Chi Square Distance (ACS HistLoss) is proposed to refine the saliency map in terms of luminance distribution.
- 4
- Special issue on recent advances in saliency models, applications and evaluations4
New datasets, metrics, benchmarks and behavioral studies are expected to comprehensively evaluate and fairly compare the performance of state-of-the-art saliency models, as well as to shape the future research directions.
- Recent progress in computational modeling of human visual attention4
A link between corneal epithelial wound healing and expression of DNMT-1 and DNMT-3b, proposing DNA methylation as one of the underlying regulatory mechanism.
- 4
- 3
- SplitMixer: Fat Trimmed From MLP-like Models3
It is shown, both theoretically and experimentally, that SplitMixer performs on par with the state-of-the-art MLP-like models while having a significantly lower number of parameters and FLOPS, and it is hoped that the results spark further research towards finding more efficient vision architectures and facilitate the development of MLP -like models.
- 3
- 3
- Multi-View Egocentric Video Summarization3
This work presents a supervised-learning framework that identifies a diverse set of important events among dynamically moving cameras that often are not capturing the same scene, and selects the most representative view at each event to be included in the universal summary.
- A new look at clustering through the lens of deep convolutional neural networks3
The main takeaway lesson from this study is that mechanisms of human vision, particularly the hierarchal organization of the visual ventral stream should be taken into account in clustering algorithms to reach human level clustering performance.
- Can Saliency Information Benefit Image Captioning Models3
The agreement between bottom-up saliency-based visual attention and object referrals in scene description constructs is studied and the properties of human-written descriptions and machine-generated ones are investigated.
- 3
- 3
- Key-Value Transformer2
An evaluation of the key-value formulation (KV), which generates symmetric attention maps, along with an asymmetric version that incorporates a 2D positional encoding into the attention matrix, discovered that the KV transformer occasionally outperforms the QKV transformer.
- CNNs and Transformers Perceive Hybrid Images Similar to Humans2
The results provide yet another evidence in support of the hypothesis that Convolutional Neural Networks (CNNs) and Transformers are good at modeling the feedforward sweep of information in the ventral stream of visual cortex.
- A New Kind of Adversarial Example2
This work considers the opposite which is adversarial examples that can fool a human but not a model, and proposes a proposed attack, dubbed NKE, which is more efficient since it uses gradient descent instead of evolutionary algorithms.
- Is current research on adversarial robustness addressing the right problem?2
The current formulation of the adversarial robustness problem serves short term goals, and needs to be revised for us to achieve bigger gains, and the bound on perturbation has created a somewhat contrived setting and need to be relaxed.
- 2
- 2
- 2
- 2
- Offline Learning of Top-down Object based Attention Control2
An algorithm is proposed for offline learning of top-down object based visual attention control by biasing the basic saliency based model of visual attention by finding a set of parameters for detecting specific objects.
- 1
- Camouflaged in Patterns: Designing Robust and User-Friendly CAPTCHA Challenges via Texture Blending1
This work exploits a lesser-known vulnerability in deep learning vision models, namely their difficulty in recognizing objects when texture conflicts with shape or context, to introduce a novel CAPTCHA challenge design strategy using texture blending.
- 1
- 1
- 1
- Addressing a fundamental limitation in deep vision models: lack of spatial attention1
A significant limitation in current deep learning models, particularly vision models, is highlighted and two solutions that could pave the way for the next generation of more efficient vision models are proposed.
- FLORIDA: Fake-looking Real Images Dataset1
A dataset of 510 genuine images that exhibit a fake appearance is curated and an assessment using two AI models is conducted, showing that two models exhibited subpar performance when applied to the dataset.
- 1
- Understanding Perceptual and Conceptual Fluency at a Large Scale1
A dataset of 543,758 logo designs spanning 39 industrial categories and 216 countries is created and estimation methods based on training DCNNs to extract and evaluate two independent constructs for designs: perceptual distinctiveness and ambiguity in meaning.
- 1
- 1
- A New Method for Synthetic Face Generation Using Spline Curves1
A new parametric method for generating synthetic faces is proposed and two experiments are designed to show that the set of generated synthetic faces match very well with their equivalent real faces.
- Evolving Weighting Functions for Query Expansion Based on Relevance Feedback1
A new method for query expansion using genetic programming (GP) is proposed to enhance the retrieval performance of text information retrieval systems and shows a higher performance in comparison with original and probabilistically expanded method.
- Learning Object-based Attention Control1
Top-down attention is learned through ordered selection of objects by maximizing the expected reward of the agent in this study, and a saliency-based model of visual attention is devised to consider processing costs of feature channels and image resolutions.
- –
- –
- A New Kind of Adversarial Example: Measuring the Human-Model Gap, and Its Relationship to OOD Detection–
This work studies the opposite of an imperceptible perturbation to fool a model: a large, clearly visible perturbation that causes the model to keep its original, correct prediction, even though a human would no longer recognize the image.
- –
- –
- –
- –
- –
- Sensitivity of Average Precision to Bounding Box Perturbations–
This work quantifies the sensitivity of AP to bounding box perturbations and shows that AP is very sensitive to small translations, explaining why achieving higher mAP becomes increasingly harder as models get better.
- –
- Logits are predictive of network type–
It is shown that it is possible to predict which deep network has generated a given logit vector with accuracy well above chance, and there is little transfer when applying a classifier to the same networks but with different sets of weights.
- –
- –
- –
- –
- –
- –
- –
- –
- Egocentric Meets Surveillance.–
This effort formalizes the problem in a way which handles and also estimates the unknown relative time-delays between the egocentric videos and the top-view video, and formulate the problem as a spectral graph matching instance, and jointly seek the optimal assignments and relativeTime-Delays of the videos.
- –
- –
- A Visual Attention Model for Omnidirectional Images–
A model of visual attention is proposed which uses some properties of omnidirectional images to modify the saliency- based model ofVisual attention for these kinds of images which suffer from large amounts of non linear deformations and distortions.
- A new synthetic face generation method for gender discrimination–
A new parametric method for generating synthetic faces is proposed in this study which could be used for psychophysics studies on face perception and two separate programs, one in Delphi 2005 programming environment and another in MATLAB® is developed to sample real faces and generate synthetic faces respectively.
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.