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.
Proposes a bilinear form to efficiently represent high-order temporal action information.
DACNN improves skeleton-based action recognition and segmentation.
We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions. Unlike dynamics models that operate over individual discrete timesteps, we learn the distribution over future state trajectories conditioned on past state, past acti…
Method learns reusable actions from human demonstrations.
Many real-world vision problems suffer from inherent ambiguities. In clinical applications for example, it might not be clear from a CT scan alone which particular region is cancer tissue. Therefore a group of graders typically produces a set of diverse but plausible segmentations. We consider the task of learning a di…
New method improves weakly-supervised action localization.
Study of polygon degeneration to segments in complex space.
This survey analyzes deep learning methods for real-time semantic image segmentation.
Extending the earlier results for analytic curve segments, in this article we describe the asymptotic behaviour of evolution of a finite segment of a C^n-smooth curve under the geodesic flow on the unit tangent bundle of a finite volume hyperbolic n-manifold. In particular, we show that if the curve satisfies certain n…
In a previous article, analytic 1-submanifolds had been classified w.r.t. their symmetry under a given regular and separately analytic Lie group action on an analytic manifold. It was shown that such an analytic 1-submanifold is either free or (via the exponential map) analytically diffeomorphic to the unit circle or a…
Paper proposes a new model for fine-grained review classification using weak supervision.
Deep reinforcement learning (DRL) has shown incredible performance in learning various tasks to the human level. However, unlike human perception, current DRL models connect the entire low-level sensory input to the state-action values rather than exploiting the relationship between and among entities that constitute t…
The aim of this paper is to develop a new axiomatization of planar geometry by reinterpreting the original axioms of Euclid. The basic concept is still that of a line segment but its equivalent notion of betweenness is viewed as a topological, not a metric concept. That leads quickly to the notion of connectedness with…
New method for IRL with missing data.
DeepMRSeg uses deep learning for brain tissue segmentation.
We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence segmentation module to learn latent encodings of sequential d…
Segmental structure is a common pattern in many types of sequences such as phrases in human languages. In this paper, we present a probabilistic model for sequences via their segmentations. The probability of a segmented sequence is calculated as the product of the probabilities of all its segments, where each segment …
Bayesian nonparametric method segments multi-sequence time series data.
Due to burdensome data requirements, learning from demonstration often falls short of its promise to allow users to quickly and naturally program robots. Demonstrations are inherently ambiguous and incomplete, making correct generalization to unseen situations difficult without a large number of demonstrations in varyi…
BiPE blends intra-segment and inter-segment encodings for better length extrapolation.
CNNs can be trained with clinically available segmentations for OARs in radiotherapy.
Novel framework provides statistical significance for image segmentation results.
Learning-based methods for visual segmentation have made progress on particular types of segmentation tasks, but are limited by the necessary supervision, the narrow definitions of fixed tasks, and the lack of control during inference for correcting errors. To remedy the rigidity and annotation burden of standard appro…
Develops deep learning for logical code segmentation.
A framework uses complex networks for image segmentation.
Hybrid CNN improves segmentation and registration of white matter tracts.
DNA rearrangement processes recombine gene segments that are organized on the chromosome in a variety of ways. The segments can overlap, interleave or one may be a subsegment of another. We use directed graphs to represent segment organizations on a given locus where contigs containing rearranged segments represent ver…
Preformer improves Transformer for long-term time series forecasting.
The Hausdorff Distance (HD) is widely used in evaluating medical image segmentation methods. However, existing segmentation methods do not attempt to reduce HD directly. In this paper, we present novel loss functions for training convolutional neural network (CNN)-based segmentation methods with the goal of reducing HD…
The symmetries of paths in a manifold are classified with respect to a given pointwise proper action of a Lie group on . Here, paths are embeddings of a compact interval into . There are at least two types of symmetries: Firstly, paths that are parts of an integral curve of a fundamental vector field on $…
We introduce a novel Deep Learning framework, which quantitatively estimates image segmentation quality without the need for human inspection or labeling. We refer to this method as a Quality Assurance Network -- QANet. Specifically, given an image and a `proposed' corresponding segmentation, obtained by any method inc…
Study uses LLM to extract and compare segment disclosures from financial filings.
A new method models uncertainty in medical image segmentation.
Spatially-aware metrics improve uncertainty evaluation in segmentation.
LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify the speaker, which results in a critical mismatch between testing and training. T…
Deep learning improves automatic image segmentation.
Proposes a new method for medical image segmentation.
Wavelet features improve image clustering and segmentation accuracy.
This paper reviews deep learning for multi-modality medical image segmentation.
A novel 3D U-Net approach improves kidney tumor segmentation in medical imaging.
A new deep neural network improves short-speech recognition.
We derive a convex optimization problem for the task of segmenting sequential data, which explicitly treats presence of outliers. We describe two algorithms for solving this problem, one exact and one a top-down novel approach, and we derive a consistency results for the case of two segments and no outliers. Robustness…
We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main contribution is the characterization of the nature of its shape: a general polytope (Aigner et al., 2010). To demonstrate this result, we exhibit several properties of the structu…
A new heuristic LM algorithm improves -segmentation accuracy with less computation.
Proposes adversarial normalization for multi-domain image segmentation.
This paper improves level generation using VAEs for coherent, logically following segments.
OTSS learns personalized decision weights from logged decisions and outputs.
Music generation research has grown in popularity over the past decade, thanks to the deep learning revolution that has redefined the landscape of artificial intelligence. In this paper, we propose a novel approach to music generation inspired by musical segment concatenation methods and hash learning algorithms. Given…