Sphere recognition is known to be undecidable in dimensions five and beyond, and no polynomial time method is known in dimensions three and four. Here we report on positive and negative computational results with the goal to explore the limits of sphere recognition from a practical point of view. An important ingredien…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “goal recognition”
Detect knots from photos using machine learning and traditional algorithms.
problem Automatically recognize knots from images.
method Combining CNN and transformer architectures for image recognition with traditional knot invariants.
result Lightweight machine learning models can recover meaningful structural information from images.
A framework uses deep learning for activity recognition in IoT devices.
problem Activity recognition in IoT devices without physical contact.
method Background subtraction followed by 3D-Convolutional Neural Networks.
result Enhanced activity recognition using small IoT devices.
An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is encoded by a reproducing kernel. Unlike traditional approaches where neural networks …
An important goal of computer vision is to build systems that learn visual representations over time that can be applied to many tasks. In this paper, we investigate a vision-language embedding as a core representation and show that it leads to better cross-task transfer than standard multi-task learning. In particular…
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.
ClovaCall introduces a new Korean call speech corpus for contact centers.
problem Lack of large-scale call-based speech corpora for Korean dialog scenarios.
method Development of a new large-scale Korean call-based speech corpus (ClovaCall) in a restaurant reservation domain.
result Validation of the dataset with ASR models shows its effectiveness.
Emotion Recognition in Low-Resource Settings: An Evaluation of Automatic Feature Selection Methodscs.LG
Study evaluates feature selection methods for emotion recognition in resource-constrained settings.
problem Reducing memory and computational requirements for emotion recognition in low-resource settings.
method Evaluation of three feature selection methods: ILFS, ReliefF, Fisher, and AFS.
result Smaller feature sets can achieve similar or better accuracy, reducing resource usage.
Quantum analysis tags news for sentiment and entities.
problem Identifying bias in news reporting.
method Continuous data collection, NER and sentiment analysis.
result A corpus of tagged news articles for public use.
While several approaches to face emotion recognition task are proposed in literature, none of them reports on power consumption nor inference time required to run the system in an embedded environment. Without adequate knowledge about these factors it is not clear whether we are actually able to provide accurate face e…
The study compares adversarial and multi-task learning for speech recognition, finding invariant representations are key.
problem Improving speech recognition performance with speaker information.
method Investigated multi-task learning and adversarial learning for speech recognition, comparing their effects on error rates.
result Deep models already develop speaker-invariant representations, and adversarial learning has a minor impact.
Paper proposes a method to encrypt faces while maintaining visual similarity.
problem Protecting personal data from unauthorized face recognition.
method Targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks.
result TIP-IM provides 95%+ protection success rate against face recognition models.
As we enter into the big data age and an avalanche of images have become readily available, recognition systems face the need to move from close, lab settings where the number of classes and training data are fixed, to dynamic scenarios where the number of categories to be recognized grows continuously over time, as we…
SpeechYOLO detects and locates speech objects in audio signals.
problem Detecting and localizing speech in audio signals.
method Inspired by YOLO, SpeechYOLO uses a convolutional neural network with a least-mean-squares loss function.
result SpeechYOLO performs well on keyword spotting tasks, including read and spontaneous speech.
We propose a general framework for sequential and dynamic acquisition of useful information in order to solve a particular task. While our goal could in principle be tackled by general reinforcement learning, our particular setting is constrained enough to allow more efficient algorithms. In this paper, we work under t…
This paper presents a locally decoupled network parameter learning with local propagation. Three elements are taken into account: (i) sets of nonlinear transforms that describe the representations at all nodes, (ii) a local objective at each node related to the corresponding local representation goal, and (iii) a local…
Inspired by the importance of diversity in biological system, we built an heterogeneous system that could achieve this goal. Our architecture could be summarized in two basic steps. First, we generate a diverse set of classification hypothesis using both Convolutional Neural Networks, currently the state-of-the-art tec…
Improved far-field speaker verification for short utterances in noisy conditions.
problem Challenges in speaker verification on short utterances in uncontrolled noisy environments.
method Used deep neural network architectures (TDNN and ResNet) and experimented with various embedding extractors and training procedures.
result ResNet architectures outperform x-vector approach in speaker verification quality for both long and short utterances.
Few-shot goal learning for robot tasks from a few examples.
problem Learning objectives for robot tasks from limited examples.
method Meta-learning a classifier to recognize new goals from a few examples.
result Meta-learning approach can be applied to both reinforcement learning and visual planning.
This study analyzes how one-layer transformers learn regular language recognition tasks.
problem Understanding how one-layer transformers solve regular language recognition tasks like even pairs and parity check.
method Theoretical analysis of training dynamics and gradient descent for a one-layer transformer.
result A one-layer transformer can solve even pairs directly but needs CoT for parity check. Training phases show rapid growth in attention layer followed by logarithmic growth in linear layer.
This research generates synthetic data streams for handling concept drifts and novel classes.
problem Handling concept drifts and novel classes in dynamic data streams.
method Synthetic data stream generation for both concept drifts and novel classes.
result Demonstrates the effectiveness of unsupervised drift detectors in open set recognition.
This research explores a modified VAE model to learn disentangled representations for object recognition.
problem Learning invariant representations for object recognition from diverse appearances.
method Develops a modified Variational Autoencoder (-VAE) to enforce disentangled representations using variational inference.
result Demonstrates that the incompatibility between -VAE's conditional independence and latent variable independence leads to non-monotonic inference performance.
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.
Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans …
Our team won the second prize of the Safe Aging with SPHERE Challenge organized by SPHERE, in conjunction with ECML-PKDD and Driven Data. The goal of the competition was to recognize activities performed by humans, using sensor data. This paper presents our solution. It is based on a rich pre-processing and state of th…
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…
Method approximates high-dimensional feature vectors for supervised learning.
problem Reducing storage and computational complexity in high-dimensional data.
method Approximates feature vectors using a kernel-based approach to reduce data size.
result Significant improvements in classification and regression tasks.
Improved speech recognition using EEG and video.
problem Enhancing continuous speech recognition systems.
method Implemented a CTC-based ASR model using EEG features.
result EEG features improve continuous visual speech recognition.
Active learning selects most informative unlabeled samples for labeling.
problem Efficiently label unlabeled data in applications with scarce labeled data.
method Formulated as open-set recognition, uses VNNs to identify uncertain samples.
result Achieved state-of-the-art results on MNIST, CIFAR-10, and CIFAR-100.
New approach learns neural network parameters by balancing local objectives and data propagation constraints.
problem Learning neural network parameters with trade-offs between local objectives and data propagation.
method Introduces nonlinear transforms and local propagation constraints to balance learning objectives.
result Validated approach on image recognition tasks with improved learning time and network size.
Solves recognition problem of frontal singularities.
problem Recognition of frontal singularities.
method Specified geometric frontal singularities, provided explicit normal forms, combined results from K. Saji and applied to tangent surfaces of null curves.
result Classification of singularities in tangent surfaces of null curves.
CSI-Net learns WiFi signals for body characterization and pose recognition.
problem Unified learning of body characteristics and pose recognition.
method Unified Deep Neural Network (DNN) for WiFi signal representation and multi-task learning.
result CSI-Net solves biometrics estimation and person recognition.
This paper evaluates ASR models on various co-processors, showing hardware acceleration benefits.
problem Lack of detailed training efficiency analysis for modern ASR systems.
method Developed a deep neural network ASR model and evaluated it on three co-processor platforms.
result Hardware acceleration yields good results even with less expensive equipment.
Study shows emotion affects speaker recognition and vice versa.
problem Dependencies between emotion and speaker recognition.
method Transfer learning and fine-tuning for emotion classification.
result Fine-tuning improves emotion recognition performance by 30.40% on IEMOCAP, 7.99% on MSP-Podcast, and 8.61% on Crema-D.
With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to scale the recognition to a large number of classes with few or now training samp…
End-to-end speech recognition using EEG without speech input.
problem Speech recognition without direct speech input.
method Implemented attention model and CTC-based ASR systems for EEG signals; fused EEG with noisy speech features.
result Demonstrated end-to-end speech recognition using EEG signals.
Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyondcs.CV
Automatic understanding of human affect using visual signals is of great importance in everyday human-machine interactions. Appraising human emotional states, behaviors and reactions displayed in real-world settings, can be accomplished using latent continuous dimensions (e.g., the circumplex model of affect). Valence …
Develops a multi-class classifier using quantum detection theory.
problem Improving multi-class classification models in machine learning.
method Inspired by quantum detection theory, develops a multi-class classifier.
result Demonstrates improved effectiveness of multi-class classification models.
The goal of temporal alignment is to establish time correspondence between two sequences, which has many applications in a variety of areas such as speech processing, bioinformatics, computer vision, and computer graphics. In this paper, we propose a novel temporal alignment method called least-squares dynamic time war…
Patterns and Tracksmath.GT
New proof for sphere recognition algorithm.
problem Sphere recognition algorithm proof.
method New proof of a lemma in Abigail Thompson's algorithm.
result New proof of a lemma in Abigail Thompson's proof of the Recognition Algorithm for 3-spheres.
Continuous speech recognition from brain activity without vocalization.
problem Recognizing silent speech from EEG signals.
method Implemented a CTC ASR model using EEG signals.
result Demonstrated feasibility of EEG for continuous silent speech recognition.
VoxCeleb 2019 challenge assesses speaker recognition in uncontrolled settings.
problem Evaluate speaker recognition technology in unconstrained data.
method Public dataset, challenge, and workshop at Interspeech 2019.
result Baseline results and discussions provided.
Roweisposes, Including Eigenposes, Supervised Eigenposes, and Fisherposes, for 3D Action Recognitioncs.CV
Paper proposes Roweisposes for 3D action recognition using generalized eigenvalue problem.
problem Need for basic methods in 3D action recognition.
method Roweisposes uses Roweis discriminant analysis for generalized subspace learning.
result Roweisposes is effective for 3D action recognition.
Develops a new learning framework for dynamic data.
problem Poor performance of existing strategies in dynamic data and goals.
method Prospective Learning framework and Prospective ERM algorithm.
result Prospective ERM converges to Bayes risk under certain assumptions.
Paper closes neural-symbolic learning loop with grammar model and back-search algorithm.
problem Slow convergence in neural-symbolic learning due to error propagation issues.
method Introduces grammar model as symbolic prior and back-search algorithm for efficient error propagation.
result Significantly outperforms RL methods in performance, converging speed, and data efficiency.
Paper tackles zero-shot activity recognition using video features and text embeddings.
problem Zero-shot activity recognition with videos.
method Auto-encoder model for multimodal joint embedding, 3D convolutional action recognition for visual features, GloVe word embeddings for textual features.
result Improved zero-shot recognition results with top-n accuracy and mean Nearest Neighbor Overlap.
Survey of open set recognition techniques and their limitations.
problem Recognition tasks with unknown classes during testing.
method Comprehensive review of techniques, datasets, and evaluation criteria.
result Highlighting the limitations and future directions in open set recognition.
A new deep neural network improves short-speech recognition.
problem Improving speaker recognition for short-duration speech segments.
method Proposes UtterIdNet, a novel deep neural network architecture.
result Consistent and stable performance for short segments, especially sub-second durations.