MT-VAE learns motion transitions for generating diverse future motions.
problem Learning long-term human motion sequences with transitions.
method Jointly learns motion mode embeddings and transitions using Variational Auto-Encoders.
result Generates multiple plausible future motion sequences from input.
Programmatic Motion Concepts learn human actions from paired videos.
problem Learning motion concepts from paired video and action sequences.
method Semi-supervised learning architecture for hierarchical motion representation.
result Outperforms established baselines, especially in small data settings.
Framework transfers inertial motion across domains without labeled data.
problem Inertial measurements are sensitive to sensor placement and motion dynamics.
method Extracts domain-invariant features and transfers them to new domains.
result Framework converts raw IMU sequences into accurate inertial trajectories.
Deep network predicts action sequences for complex tasks from a scene image.
problem Scalable task and motion planning from initial scene images.
method Deep convolutional recurrent neural network that predicts action sequences.
result Predicts promising action sequences, reducing motion planning problems.
New framework predicts diverse, contextually plausible 3D human motions.
problem Predicting multiple plausible future 3D poses given observed poses.
method Developed a new variational framework that conditions latent variable on past observation to encourage relevant information.
result Our approach generates motions of higher quality and preserves contextual information.
Paper introduces a new method for generating diverse human motion predictions.
problem Stochastic human motion prediction with limited flexibility.
method Stochastically combines root variations with previous pose information in a recurrent network.
result Model generates more diverse motion sequences than existing techniques.
We consider the task of learning to extract motion from videos. To this end, we show that the detection of spatial transformations can be viewed as the detection of synchrony between the image sequence and a sequence of features undergoing the motion we wish to detect. We show that learning about synchrony is possible …
In this paper we compute a presentation for the group of ring motions of the split union of a Hopf link with Euclidean components and a Euclidean circle. A key part of this work is the study of a short exact sequence of groups of ring motions of general ring links in R3. This sequence allowed us to build th…
Deep learning animates objects from input images and videos.
problem Animating arbitrary objects from input images and videos.
method A deep learning framework with three modules: Keypoint Detector, Dense Motion prediction network, and Motion Transfer Network.
result Our method outperforms state-of-the-art image animation and video generation methods.
This work compresses sequences by treating them as continuous-time processes, enabling efficient discretization.
problem Efficient compression of sequences, especially with deep learning models that scale with sequence length.
method Treat sequences as continuous-time processes, learn efficient discretization, and decode at different time intervals.
result Automatic bit rate reductions in video and motion capture sequences using learned discretization.
Synthesizing human's movements such as dancing is a flourishing research field which has several applications in computer graphics. Recent studies have demonstrated the advantages of deep neural networks (DNNs) for achieving remarkable performance in motion and music tasks with little effort for feature pre-processing.…
Linking human whole-body motion and natural language is of great interest for the generation of semantic representations of observed human behaviors as well as for the generation of robot behaviors based on natural language input. While there has been a large body of research in this area, most approaches that exist to…
Deep learning predicts human survival from cardiac MRI motion data.
problem Predicting human survival from cardiac MRI motion data.
method Fully convolutional network for dense motion modeling, autoencoder for latent code learning, Cox partial likelihood loss for right-censored data.
result Predictive accuracy (C-index) significantly higher (p < .0001) for deep learning model (C=0.73) than human benchmark (C=0.59).
Model predicts multi-modal sequences using N-curves.
problem Capturing multi-modal data in sequential data.
method Neural network model based on Mixture Density Networks with Bézier curves.
result Smooth multi-mode predictions without Monte Carlo simulation.
New algorithm disentangles latent space in GANs using video sequences.
problem Learning disentangled latent spaces in GANs without supervision.
method Adversarial training with video sequences, modifying standard GAN algorithm.
result Disentangled latent space into content and motion attributes.
Paper introduces new motion synthesis model using normalizing flows.
problem Data-driven motion synthesis with probabilistic and controllable models.
method Probabilistic, generative, autoregressive model using normalizing flows and LSTMs.
result Randomly sampled motion from the model outperforms task-agnostic baselines.
We characterise completely when limit sets, as parametrised by Cannon-Thurston maps, move discontinuously for a sequence of algebraically convergent quasi-Fuchsian groups.
High dimensional time series are endemic in applications of machine learning such as robotics (sensor data), computational biology (gene expression data), vision (video sequences) and graphics (motion capture data). Practical nonlinear probabilistic approaches to this data are required. In this paper we introduce the v…
Generative adversarial networks model and generate physical therapy exercises.
problem Mathematical modeling of human movements in physical therapy.
method Generative adversarial network structure with discriminative and generative models trained concurrently.
result Ability to classify and generate motion examples that resemble recorded sequences.
Improved speech recognition with audio-visual fusion.
problem Enhance speech recognition accuracy in noisy conditions.
method Proposes an attention-based audio-visual fusion strategy to align and learn from acoustic and lip motion data.
result Significant improvements in recognition accuracy (7-30%) on TCD-TIMIT dataset.
A measure called relative cluster entropy distinguishes between correlated and uncorrelated sequences.
problem Distinguishing between sequences with different correlation degrees.
method Minimum relative entropy principle applied to cluster partitions of power-law correlated sequences.
result Optimal Hurst exponents are selected for market price series, indicating non-markovianity.
DMGNN predicts 3D human motions using adaptive multiscale graphs.
problem Predicting 3D skeleton-based human motions accurately.
method Dynamic multiscale graph neural networks (DMGNN) with adaptive multiscale graphs and MGCU.
result DMGNN outperforms state-of-the-art methods in short and long-term predictions.
The cohomology of the pure string motion group PSigma_n admits a natural action by the hyperoctahedral group W_n. Church and Farb conjectured that for each k > 0, the sequence of degree k rational cohomology groups of PSigma_n is uniformly representation stable with respect to the induced action by W_n, that is, the de…
Paper describes a video surveillance system for highway traffic events.
problem Detecting specific sequences of situations in highway traffic videos.
method Compares RNN and CNN architectures for analyzing video frames and sequences.
result Best architecture performs well in real conditions.
Classifies 3-braids from choreographic motions on Lissajous curves, linking them to mapping classes and geodesics.
problem Classifying 3-braids from choreographic motions on Lissajous curves.
method Parametrization in terms of levels and slopes, using dilatation and geodesic cutting sequences.
result Dilatation of pseudo-Anosov mapping classes increases with level or slope.
Improved multi-step prediction of drivable space for autonomous vehicles.
problem Accurate prediction of drivable space for safer, more comfortable navigation.
method Recurrent Neural Network (RNN) architectures trained on KITTI dataset, incorporating motion features.
result Significant improvement in prediction accuracy over state-of-the-art methods.
This thesis investigates unsupervised time series representation learning for sequence prediction problems, i.e. generating nice-looking input samples given a previous history, for high dimensional input sequences by decoupling the static input representation from the recurrent sequence representation. We introduce thr…
Semi-supervised learning classifies cardiac pathology using motion features from cine MRI.
problem Classifying cardiac pathology based on motion features from cine MRI.
method Semi-supervised learning of apparent flow to generate motion features from non-segmented images.
result The model achieves 95% classification accuracy on ACDC test set.
Cardiac motion modeling using LDDMM and shape splines.
problem Difficulties in probing cardiac function due to shape and deformation interactions.
method LDDMM framework, parallel transport, normalization, shape splines.
result Significant differences in model parameters between pathologies, revealing insights into disease dynamics.
Traditional pairwise sequence alignment is based on matching individual samples from two sequences, under time monotonicity constraints. However, in many application settings matching subsequences (segments) instead of individual samples may bring in additional robustness to noise or local non-causal perturbations. Thi…
We study Brownian motion and stochastic parallel transport on Perelman's almost Ricci flat manifold M=M×SN×I, whose dimension depends on a parameter N unbounded from above. We construct sequences of projected Brownian motions and stochastic parallel transports which for N→∞ …
Study characterizes bladder motion using dynamic MRI and statistical analysis.
problem Limited volume coverage in dynamic MRI sequences hinders 3D shape reconstruction.
method 3D dense velocity measurements, LDDMM framework, statistical characterization, mean curvature changes, surface deformation analysis.
result Stable shape descriptor for characterizing bladder surface dynamics.
Using the lamination theory developed by Colding and Minicozzi for sequences of embedded, finite genus minimal surfaces with boundaries going to infinity \cite{CM5}, we show that the space of genus-one helicoids is compact (modulo rigid motions and homotheties). This generalizes a result of Hoffman and White \cite{HW}.
NAOMI improves imputation accuracy for long-range sequences.
problem Missing value imputation in spatiotemporal data.
method Non-autoregressive deep generative model exploiting multiresolution structure.
result Significant improvement in imputation accuracy (60% reduction in average prediction error).
RTN generates realistic character transitions from context.
problem Manual transition animation creation is tedious and time-consuming.
method Recurrent Neural Network (RNN) with LSTM architecture trained on past context.
result RTN produces realistic transitions that rival motion capture.
Motion Code models time series dynamics with sparse approximations.
problem Challenges in time series classification and forecasting on noisy data.
method Motion Code views time series as stochastic processes, assigning unique signatures to distinct dynamics.
result Motion Code outperforms benchmarks in noisy datasets, including real-world Parkinson's disease tracking.
RNN operators solve Newton's equations with large timesteps for molecular dynamics.
problem Solving Newton's equations of motion with large timesteps for molecular dynamics simulations.
method Recurrent Neural Networks (RNN) operators to solve Newton's equations using past trajectory data.
result Significant speedup in molecular dynamics simulations with timesteps up to 4000 times larger.
Making predictions of future frames is a critical challenge in autonomous driving research. Most of the existing methods for video prediction attempt to generate future frames in simple and fixed scenes. In this paper, we propose a novel and effective optical flow conditioned method for the task of video prediction wit…
GANVO uses GANs to estimate camera motion and depth from unlabelled images.
problem Lack of labelled data for deep VO and depth estimation.
method Generative adversarial networks for unsupervised learning of 6-DoF pose and depth.
result Outperforms existing methods in pose estimation and depth recovery.
Deep dynamic generative models are developed to learn sequential dependencies in time-series data. The multi-layered model is designed by constructing a hierarchy of temporal sigmoid belief networks (TSBNs), defined as a sequential stack of sigmoid belief networks (SBNs). Each SBN has a contextual hidden state, inherit…
Study geometric mKdV flows for Legendrian curves in a 3-sphere.
problem Investigate geometric evolution equations for Legendrian curves.
method Define a symplectic structure and show mKdV and associated flows.
result Show mKdV equation as curvature evolution induced by Hamiltonian flows.
A comparison of SLDS and LSTM for pedestrian behavior prediction shows SLDS works better with shorter sequences.
problem Time-critical pedestrian behavior prediction in autonomous vehicles.
method Comparison of a switching linear dynamical system (SLDS) and a three-layered bi-directional LSTM neural network.
result SLDS achieves higher accuracy with shorter sequences (10 samples) compared to LSTM's 80% accuracy with 100 samples.
MultiPath predicts multi-modal future trajectories for better motion planning.
problem Predicting human behavior in uncertain real-world domains like autonomous driving.
method Leverages fixed future state-sequence anchors and regresses offsets with uncertainties.
result Achieves more accurate predictions with an order of magnitude fewer trajectories.
We propose a Bayesian nonparametric approach to the problem of jointly modeling multiple related time series. Our model discovers a latent set of dynamical behaviors shared among the sequences, and segments each time series into regions defined by a subset of these behaviors. Using a beta process prior, the size of the…
New friction model for geometric locomotion systems.
problem Modeling asymmetric friction in locomotion systems.
method Introducing asymmetric friction into geometric locomotion models using Finsler metrics.
result Generalized motility map for systems with asymmetric friction.
We construct Zero-Coupon Bond markets driven by a cylindrical Brownian motion in which the notion of generalized portfolio has important flaws: There exist bounded smooth random variables with generalized hedging portfolios for which the price of their risky part is +∞ at each time. For these generalized portfol…
This paper considers a sequence of discrete-time random walk markets with a safe and a single risky investment opportunity, and gives conditions for the existence of arbitrages or free lunches with vanishing risk, of the form of waiting to buy and selling the next period, with no shorting, and furthermore for weak conv…
RCNs match and exceed MLPs and SCNs in reinforcement learning tasks.
problem Efficiently learning rhythmic motion in reinforcement learning.
method Combining RNNs and SCN structures to create RCNs.
result RCNs outperform MLPs and SCNs across all environment tasks.