Search Results for author:
Found 46 papers, 24 papers with code
CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models
In this work, we provide a benchmark, named by CARL-GT, which evaluates CAusal Reasoning capabilities of large Language models using Graphs and Tabular data.
Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images
In recent years, 3D parametric animal models have been developed to aid in estimating 3D shape and pose from images and video.
CLHOP: Combined Audio-Video Learning for Horse 3D Pose and Shape Estimation
In the monocular setting, predicting 3D pose and shape of animals typically relies solely on visual information, which is highly under-constrained.
Causality for Tabular Data Synthesis: A High-Order Structure Causal Benchmark Framework
In this paper, we introduce high-order structural causal information as natural prior knowledge and provide a benchmark framework for the evaluation of tabular synthesis models.
VAREN: Very Accurate and Realistic Equine Network
We introduce VAREN a novel 3D articulated parametric shape model learned from 3D scans of many real horses.
To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation
The goal of Online Domain Adaptation for semantic segmentation is to handle unforeseeable domain changes that occur during deployment, like sudden weather events.
Predictive Modeling of Equine Activity Budgets Using a 3D Skeleton Reconstructed from Surveillance Recordings
In this work, we present a pipeline to reconstruct the 3D pose of a horse from 4 simultaneous surveillance camera recordings.
Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models
Data-driven and controllable human motion synthesis and prediction are active research areas with various applications in interactive media and social robotics.
Learn the Time to Learn: Replay Scheduling in Continual Learning
In such settings, we propose that continual learning systems should learn the time to learn and schedule which tasks to replay at different time steps.
Going Deeper than Tracking: a Survey of Computer-Vision Based Recognition of Animal Pain and Affective States
Advances in animal motion tracking and pose recognition have been a game changer in the study of animal behavior.
Optimal transport for causal discovery
With this criterion, we propose a novel optimal transport-based algorithm for ANMs which is robust to the choice of models and extend it to post-nonlinear models.
Recur, Attend or Convolve? On Whether Temporal Modeling Matters for Cross-Domain Robustness in Action Recognition
Most action recognition models today are highly parameterized, and evaluated on datasets with appearance-wise distinct classes.
Aligned Multi-Task Gaussian Process
Building on the previous work by Kazlauskaiteet al. [2019], we include a separate monotonic warp of the input data to model temporal misalignment.
Equine Pain Behavior Classification via Self-Supervised Disentangled Pose Representation
Consequently, a pragmatic equine pain classification system would use video of the unobserved horse and weak labels.
Multimodal analysis of the predictability of hand-gesture properties
Embodied conversational agents benefit from being able to accompany their speech with gestures.
Speech2Properties2Gestures: Gesture-Property Prediction as a Tool for Generating Representational Gestures from Speech
We propose a new framework for gesture generation, aiming to allow data-driven approaches to produce more semantically rich gestures.
hSMAL: Detailed Horse Shape and Pose Reconstruction for Motion Pattern Recognition
In this paper we present our preliminary work on model-based behavioral analysis of horse motion.
Sharing Pain: Using Pain Domain Transfer for Video Recognition of Low Grade Orthopedic Pain in Horses
Moreover, we present a human expert baseline for the problem, as well as an extensive empirical study of various domain transfer methods and of what is detected by the pain recognition method trained on clean experimental pain in the orthopedic dataset.
A Framework for Integrating Gesture Generation Models into Interactive Conversational Agents
To date, recent end-to-end gesture generation methods have not been evaluated in a real-time interaction with users.
Automated Detection of Equine Facial Action Units
To automate parts of this process, we propose a Deep Learning-based method to detect EquiFACS units automatically from images.
Asymptotically Exact and Fast Gaussian Copula Models for Imputation of Mixed Data Types
Missing values with mixed data types is a common problem in a large number of machine learning applications such as processing of surveys and in different medical applications.
A Subjective Model of Human Decision Making Based on Quantum Decision Theory
Computer modeling of human decision making is of large importance for, e. g., sustainable transport, urban development, and online recommendation systems.
Full-Glow: Fully conditional Glow for more realistic image generation
Autonomous agents, such as driverless cars, require large amounts of labeled visual data for their training.
How Do Fair Decisions Fare in Long-term Qualification?
Our results show that static fairness constraints can either promote equality or exacerbate disparity depending on the driving factor of qualification transitions and the effect of sensitive attributes on feature distributions.
Moving fast and slow: Analysis of representations and post-processing in speech-driven automatic gesture generation
We provide an analysis of different representations for the input (speech) and the output (motion) of the network by both objective and subjective evaluations.
Action Graphs: Weakly-supervised Action Localization with Graph Convolution Networks
We present a method for weakly-supervised action localization based on graph convolutions.
Interpreting video features: a comparison of 3D convolutional networks and convolutional LSTM networks
A number of techniques for interpretability have been presented for deep learning in computer vision, typically with the goal of understanding what the networks have based their classification on.
Bayesian nonparametric shared multi-sequence time series segmentation
In this paper, we introduce a method for segmenting time series data using tools from Bayesian nonparametrics.
Gesticulator: A framework for semantically-aware speech-driven gesture generation
During speech, people spontaneously gesticulate, which plays a key role in conveying information.
Real-Time Semantic Stereo Matching
Scene understanding is paramount in robotics, self-navigation, augmented reality, and many other fields.
Non-Parametric Calibration for Classification
Many applications of classification methods not only require high accuracy but also reliable estimation of predictive uncertainty.
Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation
We show that the data generated from our simulator have similar statistics as real-world data.
Analyzing Input and Output Representations for Speech-Driven Gesture Generation
We evaluate different representation sizes in order to find the most effective dimensionality for the representation.
Gesture Generation
Human-Computer Interaction
I.2.6; I.5.1; J.4
Dynamics are Important for the Recognition of Equine Pain in Video
Sequential models are experimentally compared to single-frame models, showing the importance of the temporal dimension of the data, and are benchmarked against a veterinary expert classification of the data.
A Hierarchical Grocery Store Image Dataset with Visual and Semantic Labels
In this paper, we provide a new benchmark dataset for a challenging task in this application - classification of fruits, vegetables, and refrigerated products, e. g. milk packages and juice cartons, in grocery stores.
Mixed Likelihood Gaussian Process Latent Variable Model
We present the Mixed Likelihood Gaussian process latent variable model (GP-LVM), capable of modeling data with attributes of different types.
A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling
Therefore, video-based human activity modeling is concerned with a number of tasks such as inferring current and future semantic labels, predicting future continuous observations as well as imagining possible future label and feature sequences.
Simultaneous Measurement Imputation and Outcome Prediction for Achilles Tendon Rupture Rehabilitation
However, it is challenging to train an automatic method for predicting the ATR rehabilitation outcome from treatment data, due to a massive amount of missing entries in the data recorded from ATR patients, as well as complex nonlinear relations between measurements and outcomes.
Causal Discovery in the Presence of Missing Data
When these data entries are not missing completely at random, the (conditional) independence relations in the observed data may be different from those in the complete data generated by the underlying causal process.
A Neural Network Approach to Missing Marker Reconstruction in Human Motion Capture
Optical motion capture systems have become a widely used technology in various fields, such as augmented reality, robotics, movie production, etc.
Causality Refined Diagnostic Prediction
In this work, we explore the possibility of utilizing causal relationships to refine diagnostic prediction.
Anticipating many futures: Online human motion prediction and synthesis for human-robot collaboration
Fluent and safe interactions of humans and robots require both partners to anticipate the others' actions.
Deep representation learning for human motion prediction and classification
To quantify the learned features, we use the output of different layers for action classification and visualize the receptive fields of the network units.
Bridging Medical Data Inference to Achilles Tendon Rupture Rehabilitation
Imputing incomplete medical tests and predicting patient outcomes are crucial for guiding the decision making for therapy, such as after an Achilles Tendon Rupture (ATR).
Generative One-Class Models for Text-based Person Retrieval in Forensic Applications
The proposed generative method is compared to a corresponding discriminative approach.
Persistent Homology for Learning Densities with Bounded Support
We present a novel method for learning densities with bounded support which enables us to incorporate `hard' topological constraints.
