The FAIR Universe – HiggsML Uncertainty Challenge focused on measuring the physical properties of elementary particles with imperfect simulators. Participants were required to compute and report confidence intervals for a parameter of interest regarding the Higgs boson while accounting for various systematic (epistemic) uncertainties. The dataset is a tabular dataset of 28 features and 280 million instances. Each instance represents a simulated proton-proton collision as observed at CERN’s Large Hadron Collider in Geneva, Switzerland. The features of these simulations were chosen to capture key characteristics of different types of particles. These include primary attributes, such as the energy and three-dimensional momentum of the particles, as well as derived attributes, which are calculated from the primary ones using domain-specific knowledge. Additionally, a label feature designates each instance’s type of proton-proton collision, distinguishing the Higgs boson events of interest from three background sources. As outlined in this paper, the permanent dataset release allows long-term benchmarking of new techniques. The leading submissions, including Contrastive Normalising Flows and Density Ratios estimation through classification, are described. Our challenge has brought together the physics and machine learning communities to advance our understanding and methodologies in handling systematic uncertainties within AI techniques.

Bayesian optimization (BO) is a promising approach for hyperparameter optimization of deep neural networks (DNNs), where each model training can take minutes to hours. In BO, a computationally cheap surrogate model is employed to learn the relationship between parameter configurations and their performance such as accuracy. Parallel BO methods often adopt single manager/multiple workers strategies to evaluate multiple hyperparameter configurations simultaneously. Despite significant hyperparameter evaluation time, the overhead in such centralized schemes prevents these methods to scale on a large number of workers. We present an asynchronous-decentralized BO, wherein each worker runs a sequential BO and asynchronously communicates its results through shared storage. We scale our method without loss of computational efficiency with above 95% of worker's utilization to 1,920 parallel workers (full production queue of the Polaris supercomputer) and demonstrate improvement in model accuracy as well as faster convergence on the CANDLE benchmark from the Exascale computing project.

Hyperparameter optimization (HPO) is crucial for fine-tuning machine learning models, but it can be computationally expensive.To reduce costs, Multi-fidelity HPO (MF-HPO) leverages intermediate accuracy levels in the learning process and discards low-performing models early on.We conducted a comparison of various representative MF-HPO methods against a simple baseline on classical benchmark data.The baseline involved discarding all models except the Top-K after training for only one epoch, followed by further training to select the best model.Surprisingly, this baseline achieved similar results to its counterparts, while requiring an order of magnitude less computation.Upon analyzing the learning curves of the benchmark data, we observed a few dominant learning curves, which explained the success of our baseline.This suggests that researchers should (1) always use the suggested baseline in benchmarks and (2) broaden the diversity of MF-HPO benchmarks to include more complex cases.

It has become mainstream in computer vision and other machine learning domains to reuse backbone networks pretrained on large datasets as preprocessors. Typically, the last layer is replaced by a shallow learning machine of sorts; the newly-added classification head and (optionally) deeper layers are fine-tuned on a new task. Due to its strong performance and simplicity, a common pre-trained backbone network is ResNet152. However, ResNet152 is relatively large and induces inference latency. In many cases, a compact and efficient backbone with similar performance would be preferable over a larger, slower one. This paper investigates techniques to reuse a pre-trained backbone with the objective of creating a smaller and faster model. Starting from a large ResNet152 backbone pre-trained on ImageNet, we first reduce it from 51 blocks to 5 blocks, reducing its number of parameters and FLOPs by more than 6 times, without significant performance degradation. Then, we split the model after 3 blocks into several branches, while preserving the same number of parameters and FLOPs, to create an ensemble of sub-networks to improve performance. Our experiments on a large benchmark of 40 image classification datasets from various domains suggest that our techniques match the performance (if not better) of “classical backbone fine-tuning” while achieving a smaller model size and faster inference speed.

CodaLab Competitions is an open source web platform designed to help data scientists and research teams to crowd-source the resolution of machine learning problems through the organization of competitions, also called challenges or contests. CodaLab Competitions provides useful features such as multiple phases, results and code submissions, multi-score leaderboards, and jobs running inside Docker containers. The platform is very flexible and can handle large scale experiments, by allowing organizers to upload large datasets and provide their own CPU or GPU compute workers.

We address the problem of selecting a winning algorithm in a challenge or benchmark.While evaluations of algorithms carried out by third party organizers eliminate the inventor-evaluator bias, little attention has been paid to the risk of over-fitting the winner's selection by the organizers.In this paper, we carry out an empirical evaluation using the results of several challenges and benchmarks, evidencing this phenomenon.We show that a heuristic commonly used by organizers consisting of pre-filtering participants using a trial run, reduces over-fitting.We formalize this method and derive a semi-empirical formula to determine the optimal number of top k participants to retain from the trial run.

Deep neural networks are powerful predictors for a variety of tasks. However, they do not capture uncertainty directly. Using neural network ensembles to quantify uncertainty is competitive with approaches based on Bayesian neural networks while benefiting from better computational scalability. However, building ensembles of neural networks is a challenging task because, in addition to choosing the right neural architecture or hyperparameters for each member of the ensemble, there is an added cost of training each model. To address this issue, we propose AutoDEUQ, an automated approach for generating an ensemble of deep neural networks. Our approach leverages joint neural architecture and hyperparameter search to generate ensembles. We use the law of total variance to decompose the predictive variance of deep ensembles into aleatoric (data) and epistemic (model) uncertainties. We show that AutoDEUQ outperforms probabilistic backpropagation, Monte Carlo dropout, deep ensemble, distribution-free ensembles, and hyper ensemble methods on a number of regression benchmarks.

Meta-Iearning has been widely studied and implemented in many Automated Machine Learning systems to improve the process of selecting and training Machine Learning models for new tasks, by leveraging expertise acquired on previously observed tasks. We design a novel meta-learning challenge aiming at learning-to-learn from one of the most essential model evaluation data, the learning curve. It consists of multiple model evaluations collected during the process of training. A meta-learner is expected to apply a learned policy to learning curves of partially trained models on the task at hand, to rapidly find the best task solution, without training all potential models to convergence. This implies learning the exploration-exploitation trade-off. Our challenge is split into two phases: a development phase and a final test phase. In each phase, a meta-learner is meta-trained and meta-tested on validation learning curves (development phase) or test learning curves (final test phase). During meta-training, the meta-learner is allowed to learn from the provided learning curves in any possible way. In meta-testing, we borrowed the common Reinforcement Learning setting in which an agent (a meta-learner) learns by interacting with an environment storing pre-computed learning curves. A meta-learner must pay a cost (corresponding to the actual training and testing time) to reveal learning curve information progressively. The meta-learner is evaluated and ranked based on the average area under its learning curves. This challenge was accepted as part of the official selection of WCCI 2022 competitions.

We introduce Meta-Album, an image classification meta-dataset designed to facilitate few-shot learning, transfer learning, meta-learning, among other tasks. It includes 40 open datasets, each having at least 20 classes with 40 examples per class, with verified licences. They stem from diverse domains, such as ecology (fauna and flora), manufacturing (textures, vehicles), human actions, and optical character recognition, featuring various image scales (microscopic, human scales, remote sensing). All datasets are preprocessed, annotated, and formatted uniformly, and come in 3 versions (Micro $\subset$ Mini $\subset$ Extended) to match users’ computational resources. We showcase the utility of the first 30 datasets on few-shot learning problems. The other 10 will be released shortly after. Meta-Album is already more diverse and larger (in number of datasets) than similar efforts, and we are committed to keep enlarging it via a series of competitions. As competitions terminate, their test data are released, thus creating a rolling benchmark, available through OpenML.org. Our website https://meta-album.github.io/ contains the source code of challenge winning methods, baseline methods, data loaders, and instructions for contributing either new datasets or algorithms to our expandable meta-dataset.

A new causal discovery method, Structural Agnostic Modeling (SAM), is presented in this paper. Leveraging both conditional independencies and distributional asymmetries, SAM aims to find the underlying causal structure from observational data. The approach is based on a game between different players estimating each variable distribution conditionally to the others as a neural net, and an adversary aimed at discriminating the generated data against the original data. A learning criterion combining distribution estimation, sparsity and acyclicity constraints is used to enforce the optimization of the graph structure and parameters through stochastic gradient descent. SAM is extensively experimentally validated on synthetic and real data.

Explainability and interpretability are two critical aspects of decision support systems. Despite their importance, it is only recently that researchers are starting to explore these aspects. This paper provides an introduction to explainability and interpretability in the context of apparent personality recognition. To the best of our knowledge, this is the first effort in this direction. We describe a challenge we organized on explainability in first impressions analysis from video. We analyze in detail the newly introduced data set, evaluation protocol, proposed solutions and summarize the results of the challenge. We investigate the issue of bias in detail. Finally, derived from our study, we outline research opportunities that we foresee will be relevant in this area in the near future.

Personality analysis has been widely studied in psychology, neuropsychology, and signal processing fields, among others. From the past few years, it also became an attractive research area in visual computing. From the computational point of view, by far speech and text have been the most considered cues of information for analyzing personality. However, recently there has been an increasing interest from the computer vision community in analyzing personality from visual data. Recent computer vision approaches are able to accurately analyze human faces, body postures and behaviors, and use these information to inferapparentpersonality traits. Because of the overwhelming research interest in this topic, and of the potential impact that this sort of methods could have in society, we present in this paper an up-to-date review of existing vision-based approaches for apparent personality trait recognition. We describe seminal and cutting edge works on the subject, discussing and comparing their distinctive features and limitations. Future venues of research in the field are identified and discussed. Furthermore, aspects on the subjectivity in data labeling/evaluation, as well as current datasets and challenges organized to push the research on the field are reviewed.

The ChaLearn large-scale gesture recognition challenge has run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than 200 teams around the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. It describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. In this article, we discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition and provide a detailed analysis of the current methods for large-scale isolated and continuous gesture recognition. In addition to the recognition rate and mean Jaccard index (MJI) as evaluation metrics used in previous challenges, we introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) method, determining video division points based on skeleton points. Experiments show that the proposed Bi-LSTM outperforms state-of-the-art methods with an absolute improvement of 8.1% (from 0.8917 to 0.9639) of CSR.

Access to medical data is often restricted due to privacy laws e.g.HIPAA and GDPR.We address the viability of substituting real data with synthetic data to protect privacy while maintaining utility.Medical data records are fundamentally longitudinal, with one patient having multiple health events influenced by covariates like gender, age etc. Synthesis of medical data, hence, falls under time-series generative modeling.We demonstrate methods to measure synthetic medical time-series quality on datasets from previously published synthetic data research.We deploy four time-series metrics to quantify resemblance in synthetic and real covariate plots while comparing baseline data generation methods.

Machine learning progress relies on algorithm benchmarks.We study the problem of declaring a winner, or ranking "candidate" algorithms, based on results obtained by "judges" (scores on various tasks).Inspired by social science and game theory on fair elections, we compare various ranking functions, ranging from simple score averaging to Condorcet methods.We devise novel empirical criteria to assess the quality of ranking functions, including the generalization to new tasks and the stability under judge or candidate perturbation.We conduct an empirical comparison on the results of 5 competitions and benchmarks (one artificially generated).While prior theoretical analyses indicate that no single ranking function satisfies all desired properties, our empirical study reveals that the classical "average rank" method fares well.However, some pairwise comparison methods can get better empirical results. 35

This paper presents the design and analysis of a data science competition on a problem of time series regression from aeronautics data. For the purpose of performing predictive maintenance, aviation companies seek to create aircraft “numerical twins”, which are programs capable of accurately predicting strains at strategic positions in various body parts of the aircraft. Given a number of input parameters (sensor data) recorded in sequence during the flight, the competition participants had to predict output values (gauges), also recorded sequentially during test flights, but not recorded during regular flights. The competition data included hundreds of complete flights. It was a code submission competition with complete blind testing of algorithms. The results indicate that such a problem can be effectively solved with gradient boosted trees, after preprocessing and feature engineering. Deep learning methods did not prove as efficient.

Developing high-performing predictive models for large tabular data sets is a challenging task. Neural architecture search (NAS) is an AutoML approach that generates and evaluates multiple neural networks with different architectures concurrently to automatically discover an high performing model. A key issue in NAS, particularly for large data sets, is the large computation time required to evaluate each generated architecture. While data-parallel training has the potential to address this issue, a straightforward approach can result in significant loss of accuracy. To that end, we develop AgEBO-Tabular, which combines Aging Evolution (AE) to search over neural architectures and asynchronous Bayesian optimization (BO) to search over hyperparameters to adapt data-parallel training. We evaluate the efficacy of our approach on two large predictive modeling tabular data sets from the Exascale Computing Project-CANcer Distributed Learning Environment (ECP-CANDLE).

BACKGROUND: Quantification of tumor heterogeneity is essential to better understand cancer progression and to adapt therapeutic treatments to patient specificities. Bioinformatic tools to assess the different cell populations from single-omic datasets as bulk transcriptome or methylome samples have been recently developed, including reference-based and reference-free methods. Improved methods using multi-omic datasets are yet to be developed in the future and the community would need systematic tools to perform a comparative evaluation of these algorithms on controlled data. RESULTS: We present DECONbench, a standardized unbiased benchmarking resource, applied to the evaluation of computational methods quantifying cell-type heterogeneity in cancer. DECONbench includes gold standard simulated benchmark datasets, consisting of transcriptome and methylome profiles mimicking pancreatic adenocarcinoma molecular heterogeneity, and a set of baseline deconvolution methods (reference-free algorithms inferring cell-type proportions). DECONbench performs a systematic performance evaluation of each new methodological contribution and provides the possibility to publicly share source code and scoring. CONCLUSION: DECONbench allows continuous submission of new methods in a user-friendly fashion, each novel contribution being automatically compared to the reference baseline methods, which enables crowdsourced benchmarking. DECONbench is designed to serve as a reference platform for the benchmarking of deconvolution methods in the evaluation of cancer heterogeneity. We believe it will contribute to leverage the benchmarking practices in the biomedical and life science communities. DECONbench is hosted on the open source Codalab competition platform. It is freely available at: https://competitions.codalab.org/competitions/27453 .

This paper reports the results and post-challenge analyses of ChaLearn's AutoDL challenge series, which helped sorting out a profusion of AutoML solutions for Deep Learning (DL) that had been introduced in a variety of settings, but lacked fair comparisons. All input data modalities (time series, images, videos, text, tabular) were formatted as tensors and all tasks were multi-label classification problems. Code submissions were executed on hidden tasks, with limited time and computational resources, pushing solutions that get results quickly. In this setting, DL methods dominated, though popular Neural Architecture Search (NAS) was impractical. Solutions relied on fine-tuned pre-trained networks, with architectures matching data modality. Post-challenge tests did not reveal improvements beyond the imposed time limit. While no component is particularly original or novel, a high level modular organization emerged featuring a "meta-learner", "data ingestor", "model selector", "model/learner", and "evaluator". This modularity enabled ablation studies, which revealed the importance of (off-platform) meta-learning, ensembling, and efficient data management. Experiments on heterogeneous module combinations further confirm the (local) optimality of the winning solutions. Our challenge legacy includes an ever-lasting benchmark (http://autodl.chalearn.org), the open-sourced code of the winners, and a free "AutoDL self-service."

The tutorial focuses on two major themes of recent advances in recommender systems: Part A: Recommendations in a Marketplace: Multi-sided marketplaces are steadily emerging as valuable ecosystems in many applications (e.g. Amazon, AirBnb, Uber), wherein the platforms have customers not only on the demand side (e.g. users), but also on the supply side (e.g. retailer). This tutorial focuses on designing search & recommendation frameworks that power such multi-stakeholder platforms. We discuss multi-objective ranking/recommendation techniques, discuss different ways in which stakeholders specify their objectives, highlight user specific characteristics (e.g. user receptivity) which could be leveraged when developing joint optimization modules and finally present a number of real world case-studies of such multi-stakeholder platforms.

This paper introduces Deep Statistical Solvers (DSS), a new class of trainable solvers for optimization problems, arising e.g., from system simulations. The key idea is to learn a solver that generalizes to a given distribution of problem instances. This is achieved by directly using as loss the objective function of the problem, as opposed to most previous Machine Learning based approaches, which mimic the solutions attained by an existing solver. Though both types of approaches outperform classical solvers with respect to speed for a given accuracy, a distinctive advantage of DSS is that they can be trained without a training set of sample solutions. Focusing on use cases of systems of interacting and interchangeable entities (e.g. molecular dynamics, power systems, discretized PDEs), the proposed approach is instantiated within a class of Graph Neural Networks. Under sufficient conditions, we prove that the corresponding set of functions contains approximations to any arbitrary precision of the actual solution of the optimization problem. The proposed approach is experimentally validated on large linear problems, demonstrating super-generalisation properties; And on AC power grid simulations, on which the predictions of the trained model have a correlation higher than 99.99% with the outputs of the classical Newton-Raphson method (known for its accuracy), while being 2 to 3 orders of magnitude faster.

The papers in this special issue comprise all aspects of computer vision and pattern recognition devoted to image and video inpainting, including related tasks like denoising, debluring, sampling, super-resolutkon enhancement, restoration, hallucination, etc. The special issue was associated to the 2018 Chalearn Looking at People Satellite ECCV Workshop1 and the 2018 ChaLearn Challenges on Image and Video Inpainting.

We propose a neural network architecture that emulates the behavior of a physics solver that solves electricity differential equations to compute electricity flow in power grids (so-called "load flow"). Load flow computation is a well studied and understood problem, but current methods (based on Newton-Raphson) are slow. With increasing usage expectations of the current infrastructure, it is important to find methods to accelerate computations. One avenue we are pursuing in this paper is to use proxies based on "graph neural networks". In contrast with previous neural network approaches, which could only handle fixed grid topologies, our novel graph-based method, trained on data from power grids of a given size, generalizes to larger or smaller ones. We experimentally demonstrate viability of the method on randomly connected artificial grids of size 30 nodes. We achieve better accuracy than the DC-approximation (a standard benchmark linearizing physical equations) on random power grids whose size range from 10 nodes to 110 nodes. Our neural network learns to solve the load flow problem without overfitting to a specific instance of the problem.

To attain its ultimate discovery goals, the luminosity of the Large Hadron Collider at CERN will increase so the amount of additional collisions will reach a level of 200 interaction per bunch crossing, a factor 7 w.r.t the current (2017) luminosity. This will be a challenge for the ATLAS and CMS experiments, in particular for track reconstruction algorithms. In terms of software, the increased combinatorial complexity will have to harnessed without any increase in budget. To engage the Computer Science community to contribute new ideas, we organized a Tracking Machine Learning challenge (TrackML) running on the Kaggle platform from March to June 2018, building on the experience of the successful Higgs Machine Learning challenge in 2014. The data were generated using [ACTS], an open source accurate tracking simulator, featuring a typical all silicon LHC tracking detector, with 10 layers of cylinders and disks. Simulated physics events (Pythia ttbar) overlaid with 200 additional collisions yield typically 10000 tracks (100000 hits) per event. The first lessons from the Accuracy phase of the challenge will be discussed.

We address the problem of maintaining high voltage power transmission networks in security at all time. This requires that power flowing through all lines remain below a certain nominal thermal limit above which lines might melt, break or cause other damages. Current practices include enforcing the deterministic “N-1” reliability criterion, namely anticipating exceeding of thermal limit for any eventual single line disconnection (whatever its cause may be) by running a slow, but accurate, physical grid simulator. New conceptual frameworks are calling for a probabilistic risk based security criterion and are in need of new methods to assess the risk. To tackle this difficult assessment, we address in this paper the problem of rapidly ranking higher order contingencies including all pairs of line disconnections, to better prioritize simulations. We present a novel method based on neural networks, which ranks “N-1” and “N-2” contingencies in decreasing order of presumed severity. We demonstrate on a classical benchmark problem that the residual risk of contingencies decreases dramatically compared to considering solely all “N-1” cases, at no additional computational cost. We evaluate that our method scales up to power grids of the size of the French high voltage power grid (over 1000 power lines).

The International Joint Conference on Neural Networks (IJCNN) was held in Anchorage (Alaska) in May 2017. This top conference in the field of neural networks included many tracks and special sessions. In particular, a special session on Machine Learning Methods Neural Networks applied to Vision and Robotics (MLMVR) was organized by the authors receiving a large volume of excellent contributions. Only a small set of outstanding papers presented at this special session were invited to submit extended versions of their work. After a rigorous revision process, four of these papers were accepted.

Neural Information Processing Systems (NIPS) is a top-tier annual conference in machine learning. The 2016 edition of the conference comprised more than 2,400 paper submissions, 3,000 reviewers, and 8,000 attendees. This represents a growth of nearly 40% in terms of submissions, 96% in terms of reviewers, and over 100% in terms of attendees as compared to the previous year. The massive scale as well as rapid growth of the conference calls for a thorough quality assessment of the peer-review process and novel means of improvement. In this paper, we analyze several aspects of the data collected during the review process, including an experiment investigating the efficacy of collecting ordinal rankings from reviewers. We make a number of key observations, provide suggestions that may be useful for subsequent conferences, and discuss open problems towards the goal of improving peer review.

The papers in this special section examine the concept of automated face analysis (AFA). AFA has received special attention from the computer vision and pattern recognition communities. Research progress often gives the impression that problems such as face recognition and face detection are solved, at least for some scenarios. Several aspects of face analysis remain open problems, including the implementation of large scale face recognition/detection methods for in the wild images, emotion recognition, micro-expression analysis, and others. The community keeps making rapid progress on these topics, with continual improvement of current methods and creation of new ones that push the state-of-the-art. Applications are countless, including security and video surveillance, human computer/robot interaction, communication, entertainment, and commerce, while having an important social impact in assistive technologies for education and health. The importance of face analysis, together with the vast amount of work on the subject and the latest developments in the field, motivated us to organize a special section on this theme. The scope of the compilation comprises all aspects of face analysis from a computer vision perspective. Including, but not limited to: recognition, detection, alignment, reconstruction of faces, pose estimation of faces, gaze analysis, age, emotion, gender, and facial attributes estimation, and applications among others.

The papers in this special section focus on personality analysis. Automatic analysis of videos to characterize human behavior has become an active area of research with applications in affective computing, human-machine interfaces, gaming, security, marketing, and health, just to mention a few. Research advances in multimedia information processing, computer vision and pattern recognition have lead to established methodologies that are able to successfully recognize consciously executed actions, or intended movements (e.g., gestures, actions, interactions with objects and other people). However, recently there has been much progress in terms of computational approaches to characterize sub-conscious behaviors, which may be revealing aptitudes or competence, hidden intentions, and personality traits. Much remains to be done still, but it is essential nowadays to have a compilation of cutting edge work in this direction to identify potential opportunities and challenges involved. In this line, we edited a special issue on automatic methods for apparent personality analysis. Personality refers to individual differences in characteristic patterns of thinking, feeling and behaving.

People form first impressions about the personalities of unfamiliar individuals even after very brief interactions with them. In this study we present and evaluate several models that mimic this automatic social behavior. Specifically, we present several models trained on a large dataset of short YouTube video blog posts for predicting apparent Big Five personality traits of people and whether they seem suitable to be recommended to a job interview. Along with presenting our audiovisual approach and results that won the third place in the ChaLearn First Impressions Challenge, we investigate modeling in different modalities including audio only, visual only, language only, audiovisual, and combination of audiovisual and language. Our results demonstrate that the best performance could be obtained using a fusion of all data modalities. Finally, in order to promote explainability in machine learning and to provide an example for the upcoming ChaLearn challenges, we present a simple approach for explaining the predictions for job interview recommendations.

After decades of research, the real (biological) age estimation from a single face image reached maturity thanks to the availability of large public face databases and impressive accuracies achieved by recently proposed methods. The estimation of “apparent age” is a related task concerning the age perceived by human observers. Significant advances have been also made in this new research direction with the recent Looking At People challenges. In this paper we make several contributions to age estimation research. (i) We introduce APPA-REAL, a large face image database with both real and apparent age annotations. (ii)We study the relationship between real and apparent age. (iii) We develop a residual age regression method to further improve the performance. (iv) We show that real age estimation can be successfully tackled as an apparent age estimation followed by an apparent to real age residual regression. (v) We graphically reveal the facial regions on which the CNN focuses in order to perform apparent and real age estimation tasks.

The interest in action and gesture recognition has grown considerably in the last years. In this paper, we present a survey on current deep learning methodologies for action and gesture recognition in image sequences. We introduce a taxonomy that summarizes important aspects of deep learning for approaching both tasks. We review the details of the proposed architectures, fusion strategies, main datasets, and competitions. We summarize and discuss the main works proposed so far with particular interest on how they treat the temporal dimension of data, discussing their main features and identify opportunities and challenges for future research.

This paper reviews and discusses research advances on “explainable machine learning” in computer vision. We focus on a particular area of the “Looking at People” (LAP) thematic domain: first impressions and personality analysis. Our aim is to make the computational intelligence and computer vision communities aware of the importance of developing explanatory mechanisms for computer-assisted decision making applications, such as automating recruitment. Judgments based on personality traits are being made routinely by human resource departments to evaluate the candidates' capacity of social insertion and their potential of career growth. However, inferring personality traits and, in general, the process by which we humans form a first impression of people, is highly subjective and may be biased. Previous studies have demonstrated that learning machines can learn to mimic human decisions. In this paper, we go one step further and formulate the problem of explaining the decisions of the models as a means of identifying what visual aspects are important, understanding how they relate to decisions suggested, and possibly gaining insight into undesirable negative biases. We design a new challenge on explainability of learning machines for first impressions analysis. We describe the setting, scenario, evaluation metrics and preliminary outcomes of the competition. To the best of our knowledge this is the first effort in terms of challenges for explainability in computer vision. In addition our challenge design comprises several other quantitative and qualitative elements of novelty, including a “coopetition” setting, which combines competition and collaboration.

This paper reviews the historic of ChaLearn Looking at People (LAP) events. We started in 2011 (with the release of the first Kinect device) to run challenges related to human action/activity and gesture recognition. Since then we have regularly organized events in a series of competitions covering all aspects of visual analysis of humans. So far we have organized more than 10 international challenges and events in this field. This paper reviews associated events, and introduces the ChaLearn LAP platform where public resources (including code, data and preprints of papers) related to the organized events are available. We also provide a discussion on our main findings and perspectives of ChaLearn LAP activities.

This paper provides an overview of the Joint Contest on Multimedia Challenges Beyond Visual Analysis. We organized an academic competition that focused on four problems that require effective processing of multimodal information in order to be solved. Two tracks were devoted to gesture spotting and recognition from RGB-D video, two fundamental problems for human computer interaction. Another track was devoted to a second round of the first impressions challenge of which the goal was to develop methods to recognize personality traits from short video clips. For this second round we adopted a novel collaborative-competitive (i.e., coopetition) setting. The fourth track was dedicated to the problem of video recommendation for improving user experience. The challenge was open for about 45 days, and received outstanding participation: almost 200 participants registered to the contest, and 20 teams sent predictions in the final stage. The main goals of the challenge were fulfilled: the state of the art was advanced considerably in the four tracks, with novel solutions to the proposed problems (mostly relying on deep learning). However, further research is still required. The data of the four tracks will be available to allow researchers to keep making progress in the four tracks.

This paper surveys the state of the art on multimodal gesture recognition and introduces the JMLR special topic on gesture recognition 2011-2015. We began right at the start of the \kinect revolution when inexpensive infrared cameras providing image depth recordings became available. We published papers using this technology and other more conventional methods, including regular video cameras, to record data, thus providing a good overview of uses of machine learning and computer vision using multimodal data in this area of application. Notably, we organized a series of challenges and made available several datasets we recorded for that purpose, including tens of thousands of videos, which are available to conduct further research. We also overview recent state of the art works on gesture recognition based on a proposed taxonomy for gesture recognition, discussing challenges and future lines of research.

Following previous series on Looking at People (LAP) challenges [1], [2], [3], in 2015 ChaLearn runs two new competitions within the field of Looking at People: age and cultural event recognition in still images. We propose the first crowd-sourcing application to collect and label data about apparent age of people instead of the real age. In terms of cultural event recognition, tens of categories have to be recognized. This involves scene understanding and human analysis. This paper summarizes both challenges and data, providing some initial baselines. The results of the first round of the competition were presented at ChaLearn LAP 2015 IJCNN special session on computer vision and robotics http://www.dtic.ua.es/~jgarcia/IJCNN2015. Details of the ChaLearn LAP competitions can be found at http://gesture.chalearn.org/.

ChaLearn is organizing the Automatic Machine Learning (AutoML) contest for IJCNN 2015, which challenges participants to solve classification and regression problems without any human intervention. Participants' code is automatically run on the contest servers to train and test learning machines. However, there is no obligation to submit code; half of the prizes can be won by submitting prediction results only. Datasets of progressively increasing difficulty are introduced throughout the six rounds of the challenge. (Participants can enter the competition in any round.) The rounds alternate phases in which learners are tested on datasets participants have not seen, and phases in which participants have limited time to tweak their algorithms on those datasets to improve performance. This challenge will push the state of the art in fully automatic machine learning on a wide range of real-world problems. The platform will remain available beyond the termination of the challenge.

We are organizing a challenge to reverse engineer the structure of neuronal networks from patterns of activity recorded with calcium fluorescence imaging. Unraveling the brain structure at the neuronal level at a large scale is an important step in brain science, with many ramifications in the comprehension of animal and human intelligence and learning capabilities, as well as understanding and curing neuronal diseases and injuries. However, uncovering the anatomy of the brain by disentangling the neural wiring with its very fine and intertwined dendrites and axons, making both local and far reaching synapses, is a very arduous task: traditional methods of axonal tracing are tedious, difficult, and time consuming. This challenge proposes to approach the problem from a different angle, by reconstructing the effective connectivity of a neuronal network from observations of neuronal activity of thousands of neurons, which can be obtained with state-of-the-art fluorescence calcium imaging. To evaluate the effectiveness of proposed algorithms, we will use data obtained with a realistic simulator of real neurons for which we have ground truth of the neuronal connections. We produced simulated calcium imaging data, taking into account a model of fluorescence and light scattering. The task of the participants is to reconstruct a network of 1000 neurons from time series of neuronal activities obtained with this model. This challenge is part of the official selection of the WCCI 2014 competition program.

In this paper, we propose a novel approach called class-specific maximization of mutual information (CSMMI) using a submodular method, which aims at learning a compact and discriminative dictionary for each class. Unlike traditional dictionary-based algorithms, which typically learn a shared dictionary for all of the classes, we unify the intraclass and interclass mutual information (MI) into an single objective function to optimize class-specific dictionary. The objective function has two aims: 1) maximizing the MI between dictionary items within a specific class (intrinsic structure) and 2) minimizing the MI between the dictionary items in a given class and those of the other classes (extrinsic structure). We significantly reduce the computational complexity of CSMMI by introducing an novel submodular method, which is one of the important contributions of this paper. This paper also contributes a state-of-the-art end-to-end system for action and gesture recognition incorporating CSMMI, with feature extraction, learning initial dictionary per each class by sparse coding, CSMMI via submodularity, and classification based on reconstruction errors. We performed extensive experiments on synthetic data and eight benchmark data sets. Our experimental results show that CSMMI outperforms shared dictionary methods and that our end-to-end system is competitive with other state-of-the-art approaches.

We organized a Grand Challenge and Workshop on Multi-Modal Gesture Recognition.

The recognition of continuous natural gestures is a complex and challenging problem due to the multi-modal nature of involved visual cues (e.g. fingers and lips movements, subtle facial expressions, body pose, etc.), as well as technical limitations such as spatial and temporal resolution and unreliable depth cues. In order to promote the research advance on this field, we organized a challenge on multi-modal gesture recognition. We made available a large video database of 13,858 gestures from a lexicon of 20 Italian gesture categories recorded with a Kinect™ camera, providing the audio, skeletal model, user mask, RGB and depth images. The focus of the challenge was on user independent multiple gesture learning. There are no resting positions and the gestures are performed in continuous sequences lasting 1-2 minutes, containing between 8 and 20 gesture instances in each sequence. As a result, the dataset contains around 1.720.800 frames. In addition to the 20 main gesture categories, "distracter" gestures are included, meaning that additional audio and gestures out of the vocabulary are included. The final evaluation of the challenge was defined in terms of the Levenshtein edit distance, where the goal was to indicate the real order of gestures within the sequence. 54 international teams participated in the challenge, and outstanding results were obtained by the first ranked participants.

We organized a data mining challenge in “unsupervised and transfer learning” (the UTL challenge), in collaboration with the DARPA Deep Learning program. The goal of this year's challenge was to learn good data representations that can be re-used across tasks by building models that capture regularities of the input space. The representations provided by the participants were evaluated by the organizers on supervised learning “target tasks”, which were unknown to the participants. In a first phase of the challenge, the competitors were given only unlabeled data to learn their data representation. In a second phase of the challenge, the competitors were also provided with a limited amount of labeled data from “source tasks”, distinct from the “target tasks”. We made available large datasets from various application domains: handwriting recognition, image recognition, video processing, text processing, and ecology. The results indicate that learned data representation yield results significantly better than what can be achieved with raw data or data preprocessed with standard normalizations and functional transforms. The UTL challenge is part of the IJCNN 2011 competition program1. The website of the challenge remains open for submission of new methods beyond the termination of the challenge as a resource for students and researchers2.

We organized a data mining challenge on “active learning” for IJCNN/WCCI 2010, addressing machine learning problems where labeling data is expensive, but large amounts of unlabeled data are available at low cost. Examples include handwriting and speech recognition, document classification, vision tasks, drug design using recombinant molecules and protein engineering. Such problems might be tackled from different angles: learning from unlabeled data or active learning. In the former case, the algorithms must satisfy themselves with the limited amount of labeled data and capitalize on the unlabeled data with semi-supervised learning methods. Several challenges have addressed this problem in the past. In the latter case, the algorithms may place a limited number of queries to get new sample labels. The goal in that case is to optimize the queries and the problem is referred to as active learning. While the problem of active learning is of great importance, organizing a challenge in that area is non trivial. This is the problem we have addressed, and we describe our approach in this paper. The “active learning” challenge is part of the WCCI 2010 competition program (http://www.wcci2010. org/competition-program). The website of the challenge remains open for submission of new methods beyond the termination of the challenge as a resource for students and researchers (http://clopinet.com/al).

"When everything fails, ask for additional domain knowledge" is the current motto of machine learning. Therefore, assessing the real added value of prior/domain knowledge is a both deep and practical question. Most commercial data mining programs accept data pre-formatted as a table, each example being encoded as a fixed set of features. Is it worth spending time engineering elaborate features incorporating domain knowledge and/or designing ad hoc algorithms? Or else, can off-the-shelf programs working on simple features encoding the raw data without much domain knowledge do as well or better than skilled data analysts? To answer these questions, we organized a challenge for IJCNN 2007. The participants were allowed to compete in two tracks: The "prior knowledge" (PK) track, for which they had access to the original raw data representation and as much knowledge as possible about the data, and the "agnostic learning" (AL) track for which they were forced to use data pre-formatted as a table with dummy features. The AL vs. PK challenge Web site remains open: http://www.agnostic.inf.ethz.ch/.

A major challenge for machine learning algorithms in real world applications is to predict their performance. We have approached this question by organizing a challenge in performance prediction for WCCI 2006. The class of problems addressed are classification problems encountered in pattern recognition (classification of images, speech recognition), medical diagnosis, marketing (customer categorization), text categorization (filtering of spam). Over 100 participants have been trying to build the best possible classifier from training data and guess their generalization error on a large unlabeled test set. The challenge scores indicate that cross-validation yields good results both for model selection and performance prediction. Alternative model selection strategies were also sometimes employed with success. The challenge web site keeps open for post-challenge submissions: http://www.modelselect.inf.ethz.ch/.

The NIPS 2003 workshops included a feature selection competi- tion organized by the authors. We provided participants with five datasets from different application domains and called for classifica- tion results using a minimal number of features. The competition took place over a period of 13 weeks and attracted 78 research groups. Participants were asked to make on-line submissions on the validation and test sets, with performance on the validation set being presented immediately to the participant and performance on the test set presented to the participants at the workshop. In total 1863 entries were made on the validation sets during the development period and 135 entries on all test sets for the final competition. The winners used a combination of Bayesian neu- ral networks with ARD priors and Dirichlet diffusion trees. Other top entries used a variety of methods for feature selection, which combined filters and/or wrapper or embedded methods using Ran- dom Forests, kernel methods, or neural networks as a classification engine. The results of the benchmark (including the predictions made by the participants and the features they selected) and the scoring software are publicly available. The benchmark is available at www.nipsfsc.ecs.soton.ac.uk for post-challenge submissions to stimulate further research. 1 Introduction Recently, the quality of research in Machine Learning has been raised by the sus- tained data sharing efforts of the community. Data repositories include the well known UCI Machine Learning repository [13], and dozens of other sites [10]. Yet, this has not diminished the importance of organized competitions. In fact, the proliferation of datasets combined with the creativity of researchers in designing experiments makes it hardly possible to compare one paper with another [12]. A number of large conferences have regularly organized competitions (e.g. KDD, CAMDA, ICDAR, TREC, ICPR, and CASP). The NIPS workshops offer an ideal forum for organizing such competitions. In 2003, we organized a competition on the theme of feature selection, the results of which were presented at a workshop on feature extraction, which attracted 98 participants. We are presently preparing a book combining tutorial chapters and papers from the proceedings of that work- shop [9]. In this paper, we present to the NIPS community a concise summary of our challenge design and the findings of the result analysis. 2 Benchmark design We formatted five datasets (Table 1) from various application domains. All datasets are two-class classification problems. The data were split into three subsets: a training set, a validation set, and a test set. All three subsets were made available at the beginning of the benchmark, on September 8, 2003. The class labels for the validation set and the test set were withheld. The identity of the datasets and of the features (some of which were random features artificially generated) were kept secret. The participants could submit prediction results on the validation set and get their performance results and ranking on-line for a period of 12 weeks. By December 1st, 2003, which marked the end of the development period, the participants had to turn in their results on the test set. Immediately after that, the validation set labels were revealed. On December 8th, 2003, the participants could make submissions of test set predictions, after having trained on both the training and the validation set. Some details on the benchmark design are provided in this Section.

We address the problem of determining what size test set guarantees statistically significant results in a character recognition task, as a function of the expected error rate. We provide a statistical analysis showing that if, for example, the expected character error rate is around 1 percent, then, with a test set of at least 10,000 statistically independent handwritten characters (which could be obtained by taking 100 characters from each of 100 different writers), we guarantee, with 95 percent confidence, that: (1) the expected value of the character error rate is not worse than 1.25 E, where E is the empirical character error rate of the best recognizer, calculated on the test set; and (2) a difference of 0.3 E between the error rates of two recognizers is significant. We developed this framework with character recognition applications in mind, but it applies as well to speech recognition and to other pattern recognition problems.

We describe a linguistic postprocessor for character recognizers. The central module of our system is a trainable variable memory length Markov model (VLMM) that predicts the next character given a variable length window of past characters. The overall system is composed of several finite state automata, including the main VLMM and a proper noun VLMM. The best model reported in the literature (Brown et al., 1992) achieves 1.75 bits per character on the Brown corpus. On that same corpus, our model, trained on 10 times less data, reaches 2.19 bits per character and is 200 times smaller (/spl sime/160,000 parameters). The model was designed for handwriting recognition applications but could also be used for other OCR problems and speech recognition.

Presents a writer independent system for on-line handwriting recognition which can handle both cursive script and hand-print. The pen trajectory is recorded by a touch sensitive pad, such as those used by note-pad computers. The input to the system contains the pen trajectory information, encoded as a time-ordered sequence of feature vectors. Features include X and Y coordinates, pen-lifts, speed, direction and curvature of the pen trajectory. A time delay neural network with local connections and shared weights is used to estimate a posteriori probabilities for characters in a word. A hidden Markov model segments the word into characters in a way which optimizes the global word score, taking a dictionary into account. A geometrical normalization scheme and a fast but efficient dictionary search are also presented. Trained on 20000 unconstrained cursive words from 59 writers and using a 25000 word dictionary the authors reached a 89% character and 80% word recognition rate on test data from a disjoint set of writers.>

This paper compares the performance of several classifier algorithms on a standard database of handwritten digits. We consider not only raw accuracy, but also training time, recognition time, and memory requirements. When available, we report measurements of the fraction of patterns that must be rejected so that the remaining patterns have misclassification rates less than a given threshold.

We report the status of the UNIPEN project of data exchange and recognizer benchmarks started two years ago at the initiative of the International Association of Pattern Recognition (Technical Committee 11). The purpose of the project is to propose and implement solutions to the growing need of handwriting samples for online handwriting recognizers used by pen-based computers. Researchers from several companies and universities have agreed on a data format, a platform of data exchange and a protocol for recognizer benchmarks. The online handwriting data of concern may include handprint and cursive from various alphabets (including Latin and Chinese), signatures and pen gestures. These data will be compiled and distributed by the Linguistic Data Consortium. The benchmarks will be arbitrated the US National Institute of Standards and Technologies. We give a brief introduction to the UNIPEN format. We explain the protocol of data exchange and benchmarks.

The authors have designed a writer-adaptable character recognition system for online characters entered on a touch terminal. It is based on a Time Delay Neural Network (TDNN) that is pre-trained on examples from many writers to recognize digits and uppercase letters. The TDNN without its last layer serves as a preprocessor for an optimal hyperplane classifier that can be easily retrained to peculiar writing styles. This combination allows for fast writer-dependent learning of new letters and symbols. The system is memory and speed efficient.>

This paper describes the development of an algorithm for verification of signatures written on a touch-sensitive pad. The signature verification algorithm is based on an artificial neural network. The novel network presented here, called a “Siamese” time delay neural network, consists of two identical networks joined at their output. During training the network learns to measure the similarity between pairs of signatures. When used for verification, only one half of the Siamese network is evaluated. The output of this half network is the feature vector for the input signature. Verification consists of comparing this feature vector with a stored feature vector for the signer. Signatures closer than a chosen threshold to this stored representation are accepted, all other signatures are rejected as forgeries. System performance is illustrated with experiments performed in the laboratory.

A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented. The technique is applicable to a wide variety of the classification functions, including Perceptrons, polynomials, and Radial Basis Functions. The effective number of parameters is adjusted automatically to match the complexity of the problem. The solution is expressed as a linear combination of supporting patterns. These are the subset of training patterns that are closest to the decision boundary. Bounds on the generalization performance based on the leave-one-out method and the VC-dimension are given. Experimental results on optical character recognition problems demonstrate the good generalization obtained when compared with other learning algorithms.

Achieving good performance in statistical pattern recognition requires matching the capacity of the classifier to the amount of training data. If the classifier has too many adjustable parameters (large capacity), it is likely to learn the training data without difficulty, but will probably not generalize properly to patterns that do not belong to the training set. Conversely, if the capacity of the classifier is not large enough, it might not be able to learn the task at all. In between, there is an optimal classifier capacity which ensures the best expected generalization for a given amount of training data. The method of structural risk minimization (SRM) refers to tuning the capacity of the classifier to the available amount of training data. This paper illustrates the method of SRM with several examples of algorithms. Experiments confirm theoretical predictions of performance improvement in application to handwritten digit recognition.>

A method for computer-aided cleaning of undesirable patterns in large training databases has been developed. The method uses the trainable classifier itself, to point out patterns that are suspicious, and should be checked by the human supervisor. While suspicious patterns that are meaningless or mislabeled are considered garbage, and removed from the database, the remaining patterns, like ambiguous or atypical, represent valid patterns that are hard to learn and should be kept in the database. By using the method of pattern cleaning, combined with an emphasizing scheme applied on the patterns that are hard to learn, the error rate on the test set has been reduced by half, in the case of the database of handwritten lowercase characters entered on a touch terminal. The classifier is based on a time delay neural network (TDNN).>

Among the many applications that have been proposed for neural networks, character recognition has been one of the most successful. Compared to other methods used in pattern recognition, the advantage of neural networks is that they offer a lot of flexibility to the designer, i.e. expert knowledge can be introduced into the architecture to reduce the number of parameters determined by training by examples. In this paper, a general introduction to neural network architectures and learning algorithms commonly used for pattern recognition problems is given. The design of a neural network character recognizer for on-line recognition of handwritten characters is then described in detail.

Hardware architectures for character recognition are discussed, and choices for possible circuits are outlined. An advanced (and working) reconfigurable neural-net chip that mixes analog and digital processing is described. It is found that different approaches to image recognition often lead to neural-net architectures that have limited connectivity and repeated use of the same set of weights. This architecture is ideal for time-multiplexing (a combined parallel-series processing) on hardware systems that would be too small to evaluate the entire network in parallel. To make this process efficient, a chip needs to have shift registers to format the input data and additional registers to store intermediate results. Within this framework, it is possible to design chips that have broad utility, large connection capacity, and high speed. This was demonstrated by a new chip with 32000 reconfigurable connections