One of the greatest challenges in the design of a real-time perception system for autonomous driving vehicles and drones is the conflicting requirement of safety (high prediction accuracy) and efficiency. Traditional approaches use a single frame rate for the entire system. Motivated by the observation that the lack of…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “high frame rate”
Automatic video modification to hide faces while maintaining pose, illumination, and expression.
problem Face de-identification in video to protect identities.
method A novel feed-forward encoder-decoder network architecture conditioned on facial image high-level representation.
result Fully automatic video modification at high frame rates with minimal distortion.
Objective: Ultrasound elastography is gaining traction as an accessible and useful diagnostic tool for such things as cancer detection and differentiation and thyroid disease diagnostics. Unfortunately, state of the art shear wave imaging techniques, essential to promote this goal, are limited to high-end ultrasound ha…
Paper proposes a CNN-based method for estimating intra frame bits and quality.
problem Efficient video delivery and bit allocation in video coding.
method Deep learning approach using CNNs trained on original frames and encoded distortions.
result Accurate estimation of intra frame bits and quality for better bit allocation.
Sparse-RS framework efficiently attacks models with sparse perturbations.
problem Efficiently attacking models with sparse perturbations in the black-box setting.
method Random search-based Sparse-RS framework for score-based attacks.
result Sparse-RS achieves state-of-the-art success rate and query efficiency.
Recent advances in video super-resolution have shown that convolutional neural networks combined with motion compensation are able to merge information from multiple low-resolution (LR) frames to generate high-quality images. Current state-of-the-art methods process a batch of LR frames to generate a single high-resolu…
CNN improves frame selection for ultrasound elastography.
problem Choosing suitable frames for accurate strain estimation in ultrasound elastography.
method Convolutional Neural Network (CNN) for frame selection.
result CNN selects frames in 5.4 ms for high-quality strain images.
New wavelet frames constructed from reproducing kernels for continuous and discrete domains.
problem Generating wavelet frames on non-Euclidean structures.
method Spectral filtering of integral operators associated with reproducing kernels.
result Discrete frames as Monte Carlo estimates of continuous frames, with finite-sample rates derived.
New method for tensor classification with missing data.
problem Handling incomplete tensor data in high-dimensional classification.
method High-dimensional tensor linear discriminant analysis with TGMM and Tensor LDA-MD.
result Established convergence rates and minimax optimal bounds for misclassification rate.
Paper proposes SMFN for high-res spherical video super-resolution.
problem Super-resolution of 360-degree panoramic videos is expensive and challenging.
method Deformable convolutions, mixed attention mechanism, dual learning strategy, weighted mean square error loss function.
result The proposed SMFN method improves super-resolution of equatorial regions in 360-degree videos.
LVTINO improves high-definition video restoration with consistent temporal details.
problem Restoring high-definition video with fine spatial detail and temporal consistency.
method LVTINO uses Video Consistency Models to bypass frame-by-frame image-based LDMs, achieving perceptual quality and computational efficiency.
result Significant perceptual improvements over current methods, achieving state-of-the-art quality with minimal evaluations.
The paper shows that random frames have full spark with high probability.
problem The probability of a random frame having full spark.
method Relating frame spaces to toric symplectic manifolds to analyze geometric and spectral properties.
result The probability of a random frame having full spark is one.
Our goal is to predict future video frames given a sequence of input frames. Despite large amounts of video data, this remains a challenging task because of the high-dimensionality of video frames. We address this challenge by proposing the Decompositional Disentangled Predictive Auto-Encoder (DDPAE), a framework that …
Deep learning predicts frame errors in CIRN using SC2 dataset.
problem Predicting frame errors in Collaborative Intelligent Radio Networks (CIRN).
method Deep learning model trained on SC2 dataset with randomized or fixed bandwidth and channel allocation strategies.
result Deep learning model predicts frame error rates and instances with interesting characteristics over different SNR ranges.
In deep reinforcement learning (RL) tasks, an efficient exploration mechanism should be able to encourage an agent to take actions that lead to less frequent states which may yield higher accumulative future return. However, both knowing about the future and evaluating the frequentness of states are non-trivial tasks, …
The paper uses Frenet frame to unify electrical and geometric quantities.
problem Defining time derivatives of electrical quantities in various conditions.
method Utilizes Frenet frame from differential geometry to define time derivatives in both stationary and transient conditions.
result Unifies and generalizes time- and phasor-domain frameworks.
This paper presents GRASTA (Grassmannian Robust Adaptive Subspace Tracking Algorithm), an efficient and robust online algorithm for tracking subspaces from highly incomplete information. The algorithm uses a robust -norm cost function in order to estimate and track non-stationary subspaces when the streaming data …
High-speed model accurately simulates neuromorphic devices.
problem Accurately modeling stochastic synapses in large-scale neuromorphic systems.
method Generative vector autoregressive model based on resistive memory cell data.
result Fast, high-throughput model reproduces synaptic parameters and correlations.
VISION-XL improves HD video quality using latent image diffusion models.
problem Improving high-definition video quality and resolution.
method Latent image diffusion models and pseudo-batch consistent sampling.
result State-of-the-art video reconstruction across various inverse problems.
Video classification is a challenging task in computer vision. Although Deep Neural Networks (DNNs) have achieved excellent performance in video classification, recent research shows adding imperceptible perturbations to clean videos can make the well-trained models output wrong labels with high confidence. In this pap…
This paper examines fairness and arbitrariness in bias mitigation methods.
problem Understanding how different bias mitigation strategies affect individual predictions and whether they introduce arbitrariness.
method FRAME framework to evaluate bias mitigation through five dimensions: Impact Size, Change Direction, Decision Rates, Affected Subpopulations, and Neglected Subpopulations.
result Significant differences in the behaviors of debiasing methods were exhibited, highlighting the limitations of current fairness criteria and the inherent arbitrariness in the debiasing process.
The Kuperberg invariant is shown to be gauge invariant for certain framed 3-manifolds.
problem Exploring gauge invariance of the Kuperberg invariant for specific 3-manifolds.
method Using hyperbolic 3-manifolds and finite-dimensional Hopf algebras.
result First examples of gauge invariants of general finite-dimensional Hopf algebras via topological methods.
Deep learning has revolutionised many fields, but it is still challenging to transfer its success to small mobile robots with minimal hardware. Specifically, some work has been done to this effect in the RoboCup humanoid football domain, but results that are performant and efficient and still generally applicable outsi…
The paper addresses classification imbalance by framing it as a transfer learning problem.
problem Classification imbalance where one class is much rarer than the other.
method The paper studies oversampling procedures to balance classes, focusing on SMOTE and bootstrapping.
result The excess risk decomposes into balanced training rate and transfer cost, with SMOTE having a higher transfer cost.
Crowdsourcing provides a popular paradigm for data collection at scale. We study the problem of selecting subsets of workers from a given worker pool to maximize the accuracy under a budget constraint. One natural question is whether we should hire as many workers as the budget allows, or restrict on a small number of …
LLoCa makes any network Lorentz-equivariant, achieving high accuracy and efficiency.
problem Limitations of specialized layers in Lorentz-equivariant neural networks.
method LLoCa framework using local reference frames and geometric message passing.
result Models achieve competitive and state-of-the-art accuracy on particle physics tasks.
Detecting the intention of drivers is an essential task in self-driving, necessary to anticipate sudden events like lane changes and stops. Turn signals and emergency flashers communicate such intentions, providing seconds of potentially critical reaction time. In this paper, we propose to detect these signals in video…
Proposes SE(3) equivariant graph neural networks with local frames for efficient geometric approximation.
problem Equivariance in deep learning for arbitrary transformations, especially in physics.
method Introduces SE(3) equivariant graph neural networks with complete local frames to efficiently approximate geometric quantities.
result Achieves best or competitive performance in Newton mechanics modeling and equilibrium molecule conformation generation.
Improved speech separation and enhancement using neural beamforming.
problem Challenging speech separation and enhancement in reverberant environments.
method Sequential neural beamforming combining spectral and spatial separation methods.
result Average improvement of 2.75 dB in scale-invariant signal-to-noise ratio and 14.2% absolute reduction in speech recognition metric.
X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using la…
TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applicationscs.LG
Ball trajectory data are one of the most fundamental and useful information in the evaluation of players' performance and analysis of game strategies. Although vision-based object tracking techniques have been developed to analyze sport competition videos, it is still challenging to recognize and position a high-speed …
Confirming a conjecture, we show fundamental groups of certain abelian differentials are framed mapping class groups.
problem Confirming a 1997 conjecture about fundamental groups of abelian differentials.
method Algebraic-geometric approach using Shimada's techniques for computing fundamental groups via morphisms of varieties.
result Orbifold fundamental groups of these strata are described as framed mapping class groups.
Sparse coding in learned dictionaries has been established as a successful approach for signal denoising, source separation and solving inverse problems in general. A dictionary learning method adapts an initial dictionary to a particular signal class by iteratively computing an approximate factorization of a training …
Automatic music transcription is considered to be one of the hardest problems in music information retrieval, yet recent deep learning approaches have achieved substantial improvements on transcription performance. These approaches commonly employ supervised learning models that predict various time-frequency represent…
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance of sequence trained context dependent (CD) hidden Markov model (HMM) acoustic m…
Learned Video Compressioneess.IV
We present a new algorithm for video coding, learned end-to-end for the low-latency mode. In this setting, our approach outperforms all existing video codecs across nearly the entire bitrate range. To our knowledge, this is the first ML-based method to do so. We evaluate our approach on standard video compression test …
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but requ…
MCSAE improves speaker embedding by focusing on both high- and low-level features.
problem Reduced effect of low-level features in speaker embedding encoding.
method Masked cross self-attentive encoding using ResNet with multi-layer aggregation and random masking regularization.
result Improved speaker embedding with equal error rate of 2.63% and minimum detection cost function of 0.1453.
Improved action recognition in live videos with hybrid FR-DL method.
problem High computational costs and lack of temporal information in conventional action recognition.
method Automated selection of representative frames, feature extraction, background subtraction, HOG, deep neural network, LSTM, Softmax-KNN classifier.
result Significant improvement in accuracy and speed compared to state-of-the-art methods.
Bertrand framed surfaces defined in Euclidean 3-space with applications.
problem Defining and characterizing Bertrand framed surfaces.
method Using moving frames to define Bertrand framed surfaces and analyzing their caustics and involutes.
result Conditions for caustics and involutes to be inverse operations of framed surfaces.
Quaternionic frames' admissibility and homotopy proven.
problem Existence and interpolation of quaternionic frames.
method Interpreting frames as adjoint orbits.
result Spaces of quaternionic frames are path-connected.
We propose a limit order book (LOB) model with dynamics that account for both the impact of the most recent order and the shape of the LOB. We present an empirical analysis showing that the type of the last order significantly alters the submission rate of immediate future orders, even after accounting for the state of…
Introduces hyperbolic generalized framed surfaces and their properties.
problem None explicitly stated; focuses on introducing new geometric objects.
method Generalization of hyperbolic framed surfaces and curves.
result Established conditions for a surface to be a hyperbolic generalized framed base surface and explored their singularities.
Paper presents a new video generation model using diffusion probabilistic methods.
problem Generating high-quality video sequences.
method Denoising diffusion probabilistic models, autoregressive, end-to-end optimization.
result Significant improvements in perceptual quality and probabilistic frame forecasting.
Study of generalized Bishop frames on curves in 4D space.
problem Understanding frames on curves in 4D space.
method Introducing and studying four types of generalized Bishop frames on curves in .
result Every regular curve in admits all four types of generalized Bishop frames.
Noether's Theorem yields conservation laws for a Lagrangian with a variational symmetry group. The explicit formulae for the laws are well known and the symmetry group is known to act on the linear space generated by the conservation laws. The aim of this paper is to explain the mathematical structure of both the Euler…
We simplify Bayesian filtering by framing it as optimization, making it practical for high-dimensional systems.
problem Bayesian filtering struggles in high-dimensional state spaces like neural networks.
method We frame Bayesian filtering as optimization, using gradient descent for nonlinear cases.
result Our method results in effective, robust, and scalable filters for high-dimensional systems.
The main drawback of the Frenet frame is that it is undefined at those points where the curvature is zero. Further- more, in the case of planar curves, the Frenet frame does not agree with the standard framing of curves in the plane. The main drawback of the Bishop frame is that the principle normal vector N is not in …