Novel semi-supervised method for online structure learning in noisy data streams.
problem Discovering complex relations in noisy data streams with limited labelled data.
method Combines graph-cut minimization and first-order logic for online, single-pass label completion.
result Improves accuracy of structure learning system by completing missing labels.
Face recognition systems are vulnerable to composite face reconstruction attacks.
problem Vulnerability of face recognition systems to composite face reconstruction attacks.
method Assumed attacker uses composite face parts to reconstruct faces faster and more efficiently.
result Current face recognition systems are extremely vulnerable to random search attacks.
Smart city surveillance benefits from sound event recognition.
problem Improving monitoring capabilities in smart cities.
method Exploration of several classifiers on the SESA dataset.
result SGD achieved 72.13% accuracy in sound event recognition.
MCLNN improves sound event recognition with fewer parameters.
problem Improving sound event recognition with deep neural networks.
method Developed MCLNN to enforce sparseness and frequency shift invariance.
result MCLNN achieved competitive performance with 12% fewer parameters.
This paper reviews deep learning techniques for face recognition and sketch matching.
problem Matching composite sketches to photo images of faces is challenging due to limited details.
method Uses deep learning for feature extraction and classification in face recognition.
result Deep learning improves face recognition accuracy with large datasets.
A new method estimates rare events using tensor trains.
problem Estimating rare event probabilities in high-dimensional problems.
method Approximating optimal importance distribution via tensor-train decompositions and compositions.
result Better variance reduction and efficient computation of rare event probabilities.
Meta-learning improves few-shot acoustic event detection.
problem Detecting new audio events with limited labeled data.
method Formulated few-shot AED problem; explored supervised and meta-learning approaches.
result Meta-learning achieves superior performance in few-shot AED.
Improved audio event recognition using audiovisual transformers.
problem Weakly labeled audio event classification with limited temporal information.
method Adapted transformer architecture that combines audio and video inputs.
result State-of-the-art performance on audiovisual data set.
Several methods exist to infer causal networks from massive volumes of observational data. However, almost all existing methods require a considerable length of time series data to capture cause and effect relationships. In contrast, memory-less transition networks or Markov Chain data, which refers to one-step transit…
Bayesian tensor network reduces conditional probability calculation to polynomial time.
problem Exponential cost of calculating conditional probabilities for multiple events.
method Bayesian tensor network (BTN) with polynomial complexity.
result Competitive performance in image recognition with simple tree structures.
This paper proposes a new method for an optimized mapping of temporal variables, describing a temporal stream data, into the recently proposed NeuCube spiking neural network architecture. This optimized mapping extends the use of the NeuCube, which was initially designed for spatiotemporal brain data, to work on arbitr…
Unified tensor model disentangles object appearance factors.
problem Representing hierarchical intrinsic and extrinsic causal factors of object appearance.
method Compositional hierarchical tensor factorization.
result Interpretable object representation robust to occlusion and reduced training data requirements.
ACI converts call center conversations into actionable data.
problem Real-time spoken language understanding for call center conversations.
method Combines speech recognition, entity and intent recognition, and a business rules engine.
result ACI converts live audio into structured events for real-time supervision and assistance.
FSD50K provides an open dataset of over 51k audio clips for sound event recognition.
problem Small and domain-specific sound event recognition datasets.
method Creation of an open dataset with over 51k audio clips manually labeled using 200 classes.
result FSD50K is a new open benchmark for sound event recognition research.
Induction of common sense knowledge about prototypical sequences of events has recently received much attention. Instead of inducing this knowledge in the form of graphs, as in much of the previous work, in our method, distributed representations of event realizations are computed based on distributed representations o…
The paper analyzes sports commentary to automatically recognize events and extract insights.
problem Automatically recognizing and categorizing major actions in sports events from commentary.
method Used multiple Natural Language Processing techniques for classification and sentiment analysis.
result Identified insights from analyzing live sport commentaries and classifying major actions.
Paper explores activity recognition and prediction in real homes using sensor data and video.
problem Improving accuracy of activity recognition and prediction in real home environments.
method Binary sensor data, depth video data, field trial, probabilistic methods, LSTM networks, transfer learning, IIR filter.
result Achieved good accuracy in predicting next sensor event and its mean time of occurrence using LSTM model.
Deep learning for particle classification on large event images.
problem Training deep learning models on large, high-fidelity event images from MicroBooNE is challenging and time-consuming.
method Scaling training to multiple GPUs and architectures, using simulated MicroBooNE events.
result Demonstrated successful scaling of particle classification training to multiple GPUs and architectures.
Study uses HMM for real-time activity recognition from sensor data.
problem Real-time activity recognition from streaming sensor data.
method Online hierarchical hidden Markov model.
result Improved activity recognition accuracy compared to existing methods.
Paper explores deep learning features for complex emotion recognition.
problem Improving emotion recognition accuracy in complex emotions.
method Used pretrained networks (AudioSet Net, VoxCeleb Net, Deep Speech Net) and their deep layer features for emotion recognition.
result Achieved highest F1 score of 0.85 on EmoReact dataset.
This paper models how features influence event triggers in high-dimensional networks.
problem Estimating context-dependent networks in high-dimensional marked point processes.
method Leveraging compositional time series and regularization methods, the paper considers autoregressive multinomial and logistic-normal models for network estimation.
result The logistic-normal model leads to a convex negative log-likelihood objective and captures dependence across categories.
New framework infers multiple classes per image for one-shot learning.
problem Inferring multiple classes per image in one-shot learning.
method Compositional embedding framework with joint training of embedding and composition/query functions.
result Compositional embedding models outperform existing methods on various datasets.
Efficient SNN on Loihi achieves high gesture recognition accuracy.
problem Real-time gesture recognition using event-based sensors.
method Design and training of SNN, conversion from DNN, pre-processing of DVS data.
result 89.64% classification accuracy with 37 Loihi cores.
This paper tackles G-ZSL by learning compositional spaces to classify unseen classes.
problem Classifying unseen classes in a test set.
method Space decomposition method to estimate and fine-tune decision boundaries between source and target classes.
result State-of-the-art performance on multiple G-ZSL benchmarks.
AVEC 2019 challenges AI in detecting depression and cross-cultural emotions.
problem Detecting depression and cross-cultural emotions from audiovisual data.
method Comparison of machine learning methods under standardized conditions.
result Baseline system performance on state-of-mind, depression, and cross-cultural tasks.
New method embeds time span into self-attention for better temporal pattern recognition.
problem Capturing temporal patterns in event sequences without recurrent networks.
method Functional time representation learning with Bochner's and Mercer's Theorems.
result Proposed methods outperform baseline models in various continuous-time event sequence prediction tasks.
New method estimates composite outcomes for precision medicine.
problem Balancing multiple outcomes in precision medicine.
method Optimal treatment rule for composite outcomes.
result Estimates composite outcomes and optimal treatment rule.
ActiLabel learns activity patterns across diverse sensor devices.
problem Limited adoption of activity recognition models across different domains due to diverse sensor devices.
method Combination of graph model and optimal tiered mapping for learning activity labels.
result Superior performance compared to state-of-the-art methods on public datasets.
MCLNN improves sound recognition by learning frequency bands.
problem Efficiently recognizing acoustic events from audio signals.
method MCLNN uses a binary mask to force sparseness in network weights, focusing on frequency bands.
result MCLNN achieves competitive performance in sound recognition compared to state-of-the-art methods.
Develops STC for sequential data with missing labels.
problem Learning from partially labeled and unsegmented sequential data.
method Introduces Star Temporal Classification (STC) using a star token and GTN framework.
result Recover most of supervised baseline performance with up to 70% missing labels.
Master thesis applies deep learning to sEMG hand gesture recognition, improving accuracy.
problem Reliability issues in sEMG-based hand gesture recognition due to motion artefacts and variability.
method Used deep learning on Unibo-INAIL dataset, collecting data over 8 sessions of 7 subjects.
result Deep learning architecture yields 81.2% inter-posture test accuracy and 75.9% inter-day test accuracy.
New algorithm detects unique events in time series data.
problem Detecting anomalous events in unknown properties.
method Model-free, unsupervised detection using Temporal Outlier Factor (TOF).
result TOF outperforms traditional outlier detection methods.
This paper develops a method to select a reference contract for multi-contract quoting to minimize execution risk.
problem Minimizing execution risk in multi-contract quoting sequences.
method Develops a diagnostic framework using order-flow Hawkes forecasts and CLF to select a stable reference contract.
result Event-history and LOB-state signals offer complementary views for reference-contract selection.
Enhances survival analysis by separating population behavior from individual dynamics.
problem Improving the training and inference of survival analysis models for sparsely occurring events.
method Decouples survival analysis into an aggregated baseline hazard and independent survival scores.
result Achieves competitive performance and robust results without fine-tuning.
Method captures shared information across many views robustly.
problem Modeling hundreds of views per event and learning robust embeddings without view knowledge.
method View bootstrapping using multi-view correlation and matrix concentration theory.
result View bootstrapping captures shared information across many views robustly.
Study uncovers financial trends from cross-lingual news data.
problem Understanding financial dynamics across diverse global economies.
method Sentiment analysis, NER, and semantic textual similarity for news articles.
result Meaningful correlation between stock price movements and cross-linguistic news sentiments.
Proposes COALA method for learning audio representations aligned with tags.
problem Lack of annotated data for high-performance audio representation learning.
method Aligns latent representations of audio and tags using a contrastive loss.
result Audio embedding model captures both acoustic and semantic characteristics.
EvoNet predicts events in time-series data by evolving state graphs.
problem Predicting events in time-series data with interpretable patterns.
method Evolutionary State Graph (ESG) and EvoNet model.
result EvoNet outperforms baselines and provides insights into event predictions.
AdaPrivate-TS: A differentially private Thompson Sampling algorithm for contextual bandits
problem Private Thompson Sampling for Contextual Bandits
method Combining Thompson Sampling with batched zCDP composition
result Achieves 93-99% of non-private performance at ε ∈ [0.5, 5] with logarithmic privacy cost
PHASE dataset simulates complex social interactions in physical environments.
problem Lack of datasets for evaluating physically grounded perception of complex social interactions.
method Created PHASE dataset of 2D animations with procedural generation and physics engine.
result SIMPLE model outperforms neural networks in recognizing complex social interactions.
Generalized Earley parser predicts future events from sequence data.
problem Predicting future events from unsegmented, unlabeled sequence data.
method Integrates grammar parsing and classification for optimal segmentation and labels.
result Significantly outperforms other approaches in future human activity prediction.
We present a systematic algorithm testing for the existence of collective self-organization in the behavior of agents in social systems, with a concrete empirical implementation on the Dow Jones Industrial Average index (DJIA) over the 20th century and on Hong Kong Hang Seng composite index (HSI) since 1969. The algori…
We show that the problem of recognizing that a knot diagram represents a specific torus knot, or any torus knot at all, is in the complexity class NP∩co-NP, assuming the generalized Riemann hypothesis. We also show that satellite knot detection is in NP under the same assumption, and t…
New CRF model segments music into chords with rich features.
problem Harmonic analysis of music segments.
method Semi-Markov Conditional Random Field (semi-CRF) with segment-level features.
result Semi-CRF model performs better than previous approaches.
Paper improves predictive distributions for rare events using a simple framework.
problem Local miscalibration of predictive distributions for rare events.
method Semiparametric diagnostic transport maps to correct tail probabilities.
result Semiparametric maps improve predictions for severe weather hazards.
Study develops efficient algorithm for probabilistic penetration response of composite plates.
problem Probabilistic modeling of discrete structural response, focusing on binary events like buckling.
method Adaptive domain-based decomposition, sparse grid sampling, assumption of monotonic behavior.
result Efficient computational framework for probabilistic penetration response of composite plates.
Machine learning detects and diagnoses coughs for respiratory infections.
problem Detecting and diagnosing coughs for respiratory infections.
method Convolutional Neural Networks (CNNs) to detect cough events and diagnose three illnesses.
result Accuracy over 89% for detection and diagnosis.
End-to-end sound event detection uses learned time-frequency representations.
problem Sound event detection using standard features like mel spectrogram.
method End-to-end approach with a feedforward layer block and convolutional recurrent network.
result The learned time-frequency representations improve performance over fixed features.