Paper presents a robust time-series retrieval method using segmental alignment.
problem Noise and local non-causal perturbations in time-series data.
method Joint segmentation and alignment of sequences using a modified pair-HMM with a new distance metric.
result Improved classification performance and robustness to noise.
CARDS improves decoding efficiency and alignment quality for LLMs.
problem Efficiency bottlenecks in decoding-time alignment for LLMs.
method Cascade Reward Sampling (CARDS) with segment-level rejection sampling and uncertainty-based segmentation.
result Significant improvement in decoding efficiency and alignment quality.
Spatially-aware metrics improve uncertainty evaluation in segmentation.
problem Uncertainty evaluation metrics treat voxels independently, ignoring spatial context.
method Proposed three spatially aware metrics incorporating structural and boundary information.
result Improved alignment with clinically important factors and better discrimination between uncertainty patterns.
We consider the maximum likelihood (Viterbi) alignment of a hidden Markov model (HMM). In an HMM, the underlying Markov chain is usually hidden and the Viterbi alignment is often used as the estimate of it. This approach will be referred to as the Viterbi segmentation. The goodness of the Viterbi segmentation can be me…
End-to-end training improves segmental models for speech recognition.
problem Training segmental models is challenging and lacks understanding under different settings and losses.
method Investigated a model class based on recent successful approaches, trained end-to-end with various losses.
result Marginal log loss provides the most consistent strong performance without requiring ground-truth alignments.
DACNN improves skeleton-based action recognition and segmentation.
problem Lack of spatial relationships and non-uniform temporal scalings in skeleton-based data.
method Introduces deep-aligned convolutional neural network (DACNN) with new filters trained on local subsequences.
result DACNN achieves competitive performance compared to state-of-the-art models.
Bayesian HMM for protein alignment state estimation.
problem Estimating the MAP state sequence for a Bayesian HMM.
method Training data with Dirichlet priors, iterative algorithms for MAP path estimation.
result Bayesian setup outperforms frequentist estimation in protein alignment.
End-to-end TTS framework uses hard alignment to improve accuracy.
problem End-to-end TTS systems struggle with accurate alignment between input text and output acoustic features.
method Proposes a constrained alignment scheme with hard monotonic alignments, marginalized during training.
result Improves alignment learning and prediction in end-to-end TTS systems.
Mix and match networks enable image translation without paired data.
problem Image translation between domains or modalities with no direct paired data.
method Multiple encoders and decoders aligned for test-time composition.
result Model outperforms baselines in cross-modal image translation.
Study uses LLM to extract and compare segment disclosures from financial filings.
problem Challenges in completeness and comparability of segment disclosures in financial reports.
method Developed a large language model framework to extract and preserve segment information from Form 10-K filings.
result The LLM accurately extracts segment-level information and addresses cross-period knowledge questions.
Improved speech segment clustering using FTDTW.
problem Clustering speech segments of varying lengths and features.
method Feature Trajectory Dynamic Time Warping (FTDTW) for pairwise alignment of feature trajectories.
result Consistent and statistically significant improvements in cluster quality (F-measure and NMI).
ZegOT uses optimal transport to zero-shot segment images with text prompts.
problem Zero-shot semantic segmentation with limited image-text alignment knowledge.
method ZegOT uses optimal transport to match multiple text prompts with frozen image embeddings.
result ZegOT achieves state-of-the-art performance in zero-shot semantic segmentation.
GIBLy adds geometric priors to 3D segmentation models, improving performance with minimal overhead.
problem Lack of explicit geometric information in 3D semantic segmentation models.
method Introduces GIBLy, a lightweight geometric inductive bias layer that integrates learnable geometric priors into existing 3D segmentation pipelines.
result Consistent performance gains across multiple benchmarks, including up to +11.5% mIoU on TS40K with PTV3.
New approach speeds up DNA sequence alignment.
problem Efficiently estimating alignment scores for large sets of reads.
method Rank-one crowdsourcing models and multi-armed bandit algorithm.
result Adaptive algorithm identifies pairs with large alignment scores.
OTSeg uses multi-prompt Sinkhorn attention to improve zero-shot semantic segmentation.
problem Leveraging pre-trained CLIP knowledge to align text embeddings with pixel embeddings.
method OTSeg employs Multi-Prompts Sinkhorn (MPS) and Multi-Prompts Sinkhorn Attention (MPSA) to enhance semantic feature matching.
result OTSeg achieves state-of-the-art performance in zero-shot semantic segmentation tasks.
Algorithm adapts pretrained semantic segmentation models to new domains.
problem Adapting pretrained models to new, unlabeled domains without source data.
method Learn prototypical distribution in embedding space, align target domain with source domain.
result Method achieves competitive performance on benchmark tasks.
SWD improves unsupervised domain adaptation by measuring classifier outputs.
problem Improving unsupervised domain adaptation between domains.
method Proposes sliced Wasserstein discrepancy (SWD) for feature distribution alignment.
result SWD effectively aligns source and target distributions for various tasks.
New method uses contours of segmented images for X-ray classification.
problem Classifying X-ray images of segmented radiography.
method Develops a new approach for image analysis of multivariate planar curves, addressing alignment issues.
result Demonstrates the robustness and appeal of the proposed method through detection of cardiomegaly and numerical experiments.
LEAK learns from mistakes to improve point cloud segmentation.
problem Improving point cloud semantic segmentation performance.
method Coarse-to-fine clustering, class-conditional prototypical feature alignment, fairness weighting.
result State-of-the-art performances on different architectures, datasets, and tasks.
PiNets provide faithful explanations for neural networks.
problem Lack of true explanations for neural network predictions.
method Pointwise-interpretable Networks (PiNets) that form linear models instance-wise.
result PiNets offer explanations that are meaningful, aligned, robust, and sufficient.
Adapts segmentation networks across synthetic and real domains using GANs.
problem Difficulty in learning informative representations across domain shift for semantic segmentation.
method Generative Adversarial Networks (GANs) to align embeddings in feature space.
result Achieves state-of-the-art results on synthetic to real domain adaptation scenarios.
The paper uses attention networks for character-based handwritten text transcription.
problem Handwritten text recognition with improved character-level alignment.
method Attentional encoder-decoder networks trained on character sequences, comparing different activation functions.
result Softmax attention provides more precise character alignment than sigmoid attention.
The paper proposes a new method for product recommendation that considers revenue contributions and user similarity.
problem High dimensionality and sparsity in user-item data, especially in terms of revenue contributions.
method The approach encodes revenue contributions in the user-item matrix and computes customer similarity using suitable distance measures.
result The method segments users based on revenue-based similarity and supports recommendations aligned with profitability objectives.
LangDA improves domain adaptation for semantic segmentation by learning context-aware scene descriptions.
problem Improving domain adaptation for semantic segmentation with dense prediction tasks.
method LangDA learns contextual relationships between objects via VLM-generated scene descriptions and aligns image features with text representation.
result LangDA sets new state-of-the-art across three DASS benchmarks, outperforming existing methods.
The paper concerns a simple model of bicycle kinematics: a bicycle is represented by an oriented segment of constant length in n-dimensional space that can move in such a way that the velocity of its rear end is aligned with the segment (the rear wheel is fixed on the bicycle frame). Starting with a closed trajectory o…
Graph neural network improves SOH estimation of lithium-ion batteries.
problem Accurate SOH estimation requires alignment of statistical distributions between training and testing datasets.
method Graph convolutional networks (GCNs) with anomaly detection for selecting discharge voltage segments.
result Achieves precise SOH estimation with a root mean squared error of less than 1%.
ReDO extracts object masks from images without annotations.
problem Solving object segmentation with supervised learning requires large datasets and pixel-level annotations.
method ReDO uses an adversarial architecture where a generator redraws objects in images without annotations.
result ReDO successfully extracts high-quality object masks from various datasets.
Paper tackles domain adaptation without labeled target data.
problem Performing well on an unlabeled target domain using only labeled source data.
method Learning self-supervised tasks on both source and target domains simultaneously.
result Successfully generalizes to the unlabeled target domain.
TACO learns task decomposition from demonstrations without domain knowledge.
problem Learning complex tasks from demonstrations without domain-specific knowledge.
method Weakly supervised approach based on task sketches and temporal alignment.
result Improves generalization and requires less annotation effort compared to fully supervised methods.
Paper uses CNN to create realistic LiDAR data.
problem Creating high-resolution LiDAR data with missing points.
method Modified per-point loss and perceptual loss applied to generate realistic LiDAR data.
result Significant improvement in geometric and semantic accuracy over traditional methods.
This study analyzes the alignment between charter value and supervision in banks.
problem The alignment between charter value and supervision in banks is complex and varies by risk type.
method Classification and regression tree analysis using the CAMELS rating system.
result Supervision and charter value are aligned for some types of risk.
A new method uncovers intrinsic data structures for unsupervised domain adaptation.
problem Learning domain-aligned features can damage intrinsic target discrimination.
method Structurally Regularized Deep Clustering (H-SRDC) integrating structural source regularization.
result H-SRDC outperforms existing methods in image classification and semantic segmentation.
Adapts models incrementally for continual changes in environments.
problem Continual appearance shifts impact machine learning model performance.
method Adversarial approach for lifelong, incremental domain adaptation.
result Improves handling of large appearance changes compared to direct methods.
Improves TTS accuracy by correcting context-dependent units.
problem Improves text-to-speech accuracy through speaker adaptation.
method Statistical model predicting context-dependent phonetic unit classes and their mean error values.
result Corrected boundaries of units improve TTS accuracy compared to HMM segmentation.
CROCS clusters consumer behaviour from smart meters, capturing variability and robustness.
problem Insufficient consumer segmentation in existing clustering methods.
method Two-stage clustering framework: first stage clusters daily load profiles, second stage uses WSMD for set-to-set comparison.
result CROCS captures intra-consumer variability and robustness to anomalies and missing data.
End-to-end transformer model improves lexical stress detection accuracy.
problem Inaccurate phoneme boundaries and limited features for stress classification.
method End-to-end sequence to sequence model using transformer trained on feature sequences and phoneme sequences with stress marks.
result End-to-end model achieves better performance and lower phoneme error rate (6.36%) compared to syllable segmentation methods.
INVERT connects neural representations to human-understandable concepts.
problem Lack of understanding and statistical significance in existing explainability methods.
method Inverse Recognition (INVERT) approach that connects learned representations to human-understandable concepts.
result INVERT provides interpretable metrics and statistical significance for representation alignment.
Develops efficient method to detect multiple collective anomalies in multivariate data streams.
problem Detecting anomalies in multivariate data streams, especially collective anomalies.
method MVCAPA: A method that efficiently detects multiple collective anomalies without approximations.
result MVCAPA consistently estimates the number and location of collective anomalies.
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural ma…
Adversarial learning improves image registration networks without smoothness penalties.
problem Training image registration networks with weak labels and without smoothness constraints.
method Adversarial learning to regularize network predictions, using biomechanical simulations.
result End-to-end trained network predicts plausible deformations with minimal smoothness penalties.
Bayesian nonparametric method partitions shapes using curves.
problem Capturing complex shapes in multi-dimensional data.
method Proposes a novel spline partitioning approach using curves.
result Demonstrates improved shape modeling compared to existing methods.
Study evaluates different saliency maps for CT image classification.
problem Understanding how deep learning models make decisions in medical imaging.
method Compared several saliency maps using three evaluation metrics.
result Two versions of SmoothGrad performed best across all metrics.
Model sequences through their segmentations using dynamic programming.
problem Modeling sequences with unknown segmentations.
method Probabilistic model based on segmentations, using existing tools for segments, summing over all valid segmentations, dynamic programming for efficient computation.
result Demonstrated on text and speech recognition, discovering meaningful segments.
DeepMRSeg uses deep learning for brain tissue segmentation.
problem Automated segmentation of brain tissues and abnormalities.
method Modified UNet architecture with multi-scale feature extraction.
result DeepMRSeg achieves high accuracy on various brain segmentation tasks.
Bayesian nonparametric method segments multi-sequence time series data.
problem Temporal segmentation of multi-sequence time series data into stationary segments.
method Gaussian process priors and nonparametric distribution for segment partitioning.
result Model effectively segments synthetic and real-time series data.
Proposes guided networks for fast, accurate few-shot segmentation.
problem Few supervision limits learning-based segmentation methods.
method Extracts latent task representation from supervision, optimizes end-to-end.
result First results for segmentation from one pixel per concept, real-time interactive video segmentation.
BiPE blends intra-segment and inter-segment encodings for better length extrapolation.
problem Improving length extrapolation in language models.
method Bilevel Positional Encoding (BiPE) that separates intra-segment and inter-segment encodings.
result BiPE enhances length extrapolation across various text modalities.
CNNs can be trained with clinically available segmentations for OARs in radiotherapy.
problem Lack of dedicated training volumes for CNNs in radiotherapy.
method Used clinically available segmentations from PACS, applied multi-label segmentation, empirically assessed training set size.
result Clinically available segmentations can be used to train an accurate OAR segmentation model.