A mixture of CNNs improves adult content recognition.
problem Recognizing and restricting inappropriate images like pornography.
method A weighted sum of multiple CNN models trained using OLS.
result The proposed model outperforms single and average models.
A new method transcribes complex structured images like musical scores.
problem Transcribing content from images with complex internal structure.
method Hierarchical Spotlight Transcribing Network (STN) framework with two-stage approach.
result Demonstrated effectiveness through experiments on various structural image datasets.
Patch ranking improves CNN performance by focusing on object content, not location.
problem CNNs lack rotation and translation invariance, limiting model capacity.
method Patch ranking before convolution and pooling to encode invariance.
result Patch ranking module improves CNN performance on various tasks.
A fusion approach combines audio and video features for emotion recognition.
problem Continuous emotion recognition using both visual and auditory modalities.
method Pre-trained CNN features from video frames and minimalistic auditory descriptors. Fusion at feature or prediction level. SVR for prediction.
result Improves CCCs of 0.749 and 0.565 for arousal and valence respectively.
Although highly correlated, speech and speaker recognition have been regarded as two independent tasks and studied by two communities. This is certainly not the way that people behave: we decipher both speech content and speaker traits at the same time. This paper presents a unified model to perform speech and speaker …
Face recognition system trained with noisy labels.
problem Label noise in training deep learning classifiers.
method Review and apply recent methods to manage noisy annotations.
result Improved performance of face recognition system with noisy labels.
New datasets improve fairness research by revealing UCI Adult's limitations.
problem Limitations of UCI Adult dataset in fairness research.
method Reconstructed a superset of UCI Adult data from US Census sources.
result New datasets reveal trade-offs between fairness criteria and performance.
AI predicts dementia onset from emotional face evaluations.
problem Early detection of dementia in aging societies.
method Behavioral responses analysis and AI regression.
result Encouraging AI-based prediction results for MoCA scores.
Deep learning identifies unique walking patterns from pressure data.
problem Tackling the challenge of accurately identifying individuals based on their walking style.
method Used deep learning, specifically convolutional neural networks (CNNs), to analyze the center-of-pressure trajectory of 36 adults walking on a treadmill.
result CNNs achieved 99.9% accuracy in classifying 2,250 segments and 100% accuracy in fine-tuning a subset of 4,500 segments, suggesting unique pressure patterns for each person.
Model predicts cannabis use disorder risk for adolescents and young adults.
problem Predicting cannabis use disorder progression in adolescents and young adults.
method Bayesian machine learning model trained on longitudinal data.
result Model provides personalized risk assessment with AUC of 0.68-0.75 and E/O ratio of 0.95-1.
Enhances hand gesture recognition with separate networks and shared features.
problem Improving recognition accuracy of unimodal 3D-CNNs for dynamic hand gestures.
method Separate networks for each modality, collaborative learning, spatiotemporal semantic alignment loss, focal regularization.
result Improves test time recognition accuracy and state-of-the-art performance.
A deep historical LSTM model improves tennis shot recognition from RGB videos.
problem Improving action recognition from RGB video input for sports analysis.
method Convolutional Neural Network (CNN) and Weighted Long Short-Term Memory (LSTM) for 3D tennis shot recognition.
result The method achieves better performance than state-of-the-art baselines for tennis shot recognition.
The paper examines bias in ML models using the Adult dataset.
problem Understanding and mitigating bias in machine learning models.
method Mathematical framework for fair learning, Disparate Impact index, and evaluation of bias reduction methods.
result Some common bias reduction methods are ineffective.
SoulMate links short texts through multi-aspect embeddings.
problem Linking authors of noisy, ambiguous short texts.
method Neural network-based temporal-textual framework generating author subgraphs.
result Higher performance in linking short-text authors compared to competitors.
Eye tracking measures ADHD-related working memory deficits.
problem Diagnosing ADHD in adults requires reliable measures of working memory capacity.
method Eye tracking technology and machine learning applied to a working memory task.
result Machine learning generated features unique to ADHD.
Paper proposes MDER model to extract ML methods and datasets from papers.
problem Lack of focus on methods and datasets in literature analysis.
method Proposes MDER model for entity recognition of methods and datasets.
result Demonstrates preliminary performance of MDER model.
Enhanced feature extraction pipeline boosts music genre recognition.
problem Improving music genre classification accuracy.
method Extended feature engineering pipeline with multiple stages and feedback loops.
result The method significantly improves classification performance on the GTZAN dataset.
FUNSD dataset tackles noisy scanned forms, offering comprehensive annotations.
problem Extracting and structuring textual content from noisy scanned documents.
method Comprehensive dataset with real, fully annotated forms, including text detection, OCR, layout analysis, and entity linking.
result First publicly available dataset for form understanding, addressing challenges in noisy scanned documents.
Model learns disentangled, interpretable representations from sequential data without supervision.
problem Learning disentangled and interpretable representations from sequential data without supervision.
method Factorized hierarchical variational autoencoder with multi-scale priors.
result Model outperforms i-vector baseline in speaker verification and reduces word error rate by 35% in mismatched scenarios.
Novel bio-inspired masking for robust speech emotion recognition.
problem Noise degradation in speech emotion recognition.
method Cochlear cepstrogram-based contrastive learning with temporal and frequency masking.
result Improved speech emotion recognition performance on K-EmoCon benchmark.
End-to-end framework for static image generation from dynamic content.
problem Generating static images from dynamic content with occluded backgrounds.
method Conditional GAN for static image generation, convolutional network for dynamic object detection.
result Generated static images are realistic and can be used for augmented reality and robot localization.
Automated method selects eye tracking variables for categorization tasks.
problem Limited duration of infant cooperation and biases in handpicked eye tracking variables.
method Automated selection of eye tracking variables using statistical techniques.
result Same eye tracking variables classify category learners from non-learners in adults and infants with high accuracy.
This work disentangles speech and non-speech components from found data.
problem Building robust acoustic models from found data with non-standard variations.
method Latent Stochastic Models and Multinode Latent Space Variational Autoencoders (VAE).
result Speech and music can be separated in the latent space of a VAE, independent of the language.
Study uses machine learning to predict income levels, achieving 88.16% accuracy.
problem Predicting income levels to reduce economic inequality.
method Used Gradient Boosting Classifier Model on UCI Adult Dataset.
result Achieved 88.16% accuracy in predicting income categories.
With the rapid development of social media sharing, people often need to manage the growing volume of multimedia data such as large scale video classification and annotation, especially to organize those videos containing human activities. Recently, manifold regularized semi-supervised learning (SSL), which explores th…
HASP enhances mobile security against ASR by adding imperceptible noise.
problem Security leakage from ASR on mobile devices.
method Adversarial noise to perturb WER and enhance security.
result HASP reduces WER by 84.55% and speeds up data processing.
Deep learning model detects phishing emails with H-LSTMs and attention.
problem Detecting phishing content in textual data.
method Hierarchical LSTMs and supervised attention mechanisms.
result Effective model for anti-phishing.
Study reveals biases in facial landmark detection methods for dementia patients.
problem Challenges in facial landmark detection for older adults with dementia.
method Evaluation of seven facial landmark detection methods on frontal, profile, and various face regions.
result Significant performance differences between dementia patients and non-patients, and biases across face regions.
A neural network tackles emotion recognition, attribution, and summarization.
problem Sparsity of emotional expressions in videos.
method Bi-stream Emotion Attribution-Classification Network (BEAC-Net) with two networks: attribution and classification.
result Superior performance on emotion attribution, recognition, and summarization tasks.
Anti-transfer learning prevents misleading representations for speech tasks.
problem Misleading representations learned from orthogonal tasks in speech processing.
method Penalizes similarity between activations of a network and another trained on an orthogonal task.
result Improves classification accuracy and invariance to the orthogonal task.
Sparse coding is a common approach to learning local features for object recognition. Recently, there has been an increasing interest in learning features from spatio-temporal, binocular, or other multi-observation data, where the goal is to encode the relationship between images rather than the content of a single ima…
Study uses ML to predict cancer patient mortality from FN onset.
problem Predicting mortality in cancer patients with FN to improve survival.
method Multi-domain machine learning models using HCUP data.
result Clinical diagnoses have highest predictive power for FN mortality.
Model predicts cognitive health risks based on smartphone usage patterns.
problem Identifying cognitive health risks through smartphone usage.
method Structured models of smartphone interactions analyzed over 12 weeks.
result AUROC of 0.79 in discriminating between healthy and symptomatic subjects.
XceptionTime improves hand gesture recognition accuracy using novel deep learning.
problem Improving hand gesture recognition from sparse sEMG signals.
method Depthwise separable convolutions, adaptive pooling, non-linear normalization.
result Significantly improved accuracy (5.71% improvement) in hand gesture recognition.
New model improves illustration classification using transfer learning.
problem Improving image classification for artistic depictions.
method Transfer learning from VGG19 pre-trained on natural images, learning new features for illustrations.
result Optimized network achieves 86.61% top-1 and 97.21% top-5 precision on illustration dataset.
Single auto-encoder learns cross-domain image translation.
problem Cross-domain image-to-image translation using a single encoder-decoder architecture.
method Single auto-encoder with independent domain and content encodings.
result Cross-domain mapping achieved without separate encoders.
In some speaker recognition scenarios we find conversations recorded simultaneously over multiple channels. That is the case of the interviews in the NIST SRE dataset. To take advantage of that, we propose a modification of the PLDA model that considers two different inter-session variability terms. The first term is t…
Computer graphics techniques improve art pricing by measuring painting effort.
problem Traditional art pricing models lack measures for conceptual and painting efforts.
method Applied image recognition to measure line and color variances as proxies for effort.
result Painting effort (line and color variances) significantly positively correlates with sales price.
Many important forms of data are stored digitally in XML format. Errors can occur in the textual content of the data in the fields of the XML. Fixing these errors manually is time-consuming and expensive, especially for large amounts of data. There is increasing interest in the research, development, and use of automat…
This research improves emotion detection from speech, enhancing CCC by 30%.
problem Improving emotion detection from speech for categorical emotions.
method Used LSTM and TC-LSTM networks, trained with multiple datasets and robust features.
result Improved CCC for valence by 30% compared to baseline.
New model learns content and transformation separately from data.
problem Learning disentangled representations from data without explicit labels.
method Group-based variational autoencoders, assuming content and transformation groups.
result Model learns generalizable content representations from unseen data.
This paper explores deep learning in music generation, from history to current techniques.
problem Creating music automatically using deep learning.
method Analysis of historical and recent deep learning music generation systems.
result Deep learning can learn musical styles and generate music samples.
This paper discusses sentiment analysis on social media text.
problem Detecting sentiments in short text messages for applications like mental health monitoring.
method Combines concepts from Natural Language Processing and Machine Learning.
result Explains techniques used in sentiment analysis of textual data.
Study shows online learning algorithms incentivize low-quality content, proposing new algorithms to improve quality.
problem Online learning algorithms in content recommender systems incentivize producers to create low-quality content.
method Analyzed the game between producers and content quality, designed new learning algorithms to incentivize high effort and quality.
result New algorithms incentivize producers to invest high effort and achieve high user welfare, improving content quality.
Paper extends ICA to ISA with auxiliary variables for better speech representation learning.
problem Learning unsupervised speech representations with independent subspaces.
method Theoretical framework of nonlinear ISA with auxiliary variables.
result Proposes an algorithm to learn speech representations with independent subspaces.
Proposes a model to optimize feedback for content creators on social media.
problem Nurturing content creation on social media platforms.
method Modeling feedback distribution to incentivize creators and optimize newsfeed experience.
result Optimized newsfeed for content creators without compromising user experience.
Proposes a VAE variant for ordinal content factors.
problem Isolating ordinal-valued content factors in deep latent variable models.
method Introduces a partially ordered set (poset) structure and a conditional Gaussian spacing prior model.
result Significant improvements in content-style separation over previous non-ordinal approaches.
Unified framework interprets SSL models, revealing biases.
problem Interpreting black-box SSL models for transparency.
method KREPES framework using Representer Landmarks and Nyström approximation.
result Direct audit of SSL latent space without supervision.