Search Results for author:
Found 87 papers, 40 papers with code
SplatPose & Detect: Pose-Agnostic 3D Anomaly Detection
Detecting anomalies in images has become a well-explored problem in both academia and industry.
Ranked #1 on
Anomaly Detection
on PAD Dataset
Cell Tracking according to Biological Needs -- Strong Mitosis-aware Random-finite Sets Tracker with Aleatoric Uncertainty
Cell tracking and segmentation assist biologists in extracting insights from large-scale microscopy time-lapse data.
Personalized 3D Human Pose and Shape Refinement
To address this issue, we propose to construct dense correspondences between initial human model estimates and the corresponding images that can be used to refine the initial predictions.
Segment Any Object Model (SAOM): Real-to-Simulation Fine-Tuning Strategy for Multi-Class Multi-Instance Segmentation
The foundational Segment Anything Model (SAM) is designed for promptable multi-class multi-instance segmentation but tends to output part or sub-part masks in the "everything" mode for various real-world applications.
Robust Shape Fitting for 3D Scene Abstraction
A RANSAC estimator guided by a neural network fits these primitives to a depth map.
Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games
The combination of self-play and planning has achieved great successes in sequential games, for instance in Chess and Go.
Quantum Normalizing Flows for Anomaly Detection
A Normalizing Flow computes a bijective mapping from an arbitrary distribution to a predefined (e. g. normal) distribution.
PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus
We present a real-time method for robust estimation of multiple instances of geometric models from noisy data.
Q-SENN: Quantized Self-Explaining Neural Networks
Explanations in Computer Vision are often desired, but most Deep Neural Networks can only provide saliency maps with questionable faithfulness.
Ranked #1 on
Interpretable Machine Learning
on CUB-200-2011
The voraus-AD Dataset for Anomaly Detection in Robot Applications
During the operation of industrial robots, unusual events may endanger the safety of humans and the quality of production.
Ranked #1 on
Anomaly Detection
on voraus-AD
FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing
In this paper, for the first time, we introduce optical flow into the attention module in the diffusion model's U-Net to address the inconsistency issue for text-to-video editing.
HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization
Sparse neural networks are a key factor in developing resource-efficient machine learning applications.
Markerless human pose estimation for biomedical applications: a survey
Markerless Human Pose Estimation (HPE) proved its potential to support decision making and assessment in many fields of application.
Color-aware Deep Temporal Backdrop Duplex Matting System
In addition, the proposed studio set is actor friendly, and produces high-quality, temporal consistent alpha and color estimations that include a superior color spill compensation.
Human Spine Motion Capture using Perforated Kinesiology Tape
A maximal focus is on the accurate detection of markers and fast usage of the system.
Compensation Learning in Semantic Segmentation
In this paper, we propose Compensation Learning in Semantic Segmentation, a framework to identify and compensate ambiguities as well as label noise.
Learning Similarity between Scene Graphs and Images with Transformers
Scene graph generation is conventionally evaluated by (mean) Recall@K, which measures the ratio of correctly predicted triplets that appear in the ground truth.
Take 5: Interpretable Image Classification with a Handful of Features
We argue that a human can only understand the decision of a machine learning model, if the features are interpretable and only very few of them are used for a single decision.
Ranked #2 on
Interpretable Machine Learning
on CUB-200-2011
Fine-Grained Image Classification
Interpretable Machine Learning
Blind Knowledge Distillation for Robust Image Classification
We introduce Blind Knowledge Distillation - a novel teacher-student approach for learning with noisy labels by masking the ground truth related teacher output to filter out potentially corrupted knowledge and to estimate the tipping point from generalizing to overfitting.
Semantic Segmentation for Fully Automated Macrofouling Analysis on Coatings after Field Exposure
Biofouling is a major challenge for sustainable shipping, filter membranes, heat exchangers, and medical devices.
SSGVS: Semantic Scene Graph-to-Video Synthesis
A semantic scene graph-to-video synthesis framework (SSGVS), based on the pre-trained VSG encoder, VQ-VAE, and auto-regressive Transformer, is proposed to synthesize a video given an initial scene image and a non-fixed number of semantic scene graphs.
Asymmetric Student-Teacher Networks for Industrial Anomaly Detection
We train a normalizing flow for density estimation as a teacher and a conventional feed-forward network as a student to trigger large distances for anomalies: The bijectivity of the normalizing flow enforces a divergence of teacher outputs for anomalies compared to normal data.
Ranked #1 on
Anomaly Detection
on MVTEC 3D-AD
(Detection AUROC metric, using extra
training data)
AdaCC: Cumulative Cost-Sensitive Boosting for Imbalanced Classification
Class imbalance poses a major challenge for machine learning as most supervised learning models might exhibit bias towards the majority class and under-perform in the minority class.
POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning
The goal of Unsupervised Reinforcement Learning (URL) is to find a reward-agnostic prior policy on a task domain, such that the sample-efficiency on supervised downstream tasks is improved.
ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing
In this work, we address the problem of learning deep neural networks on small datasets.
Contextualize Me -- The Case for Context in Reinforcement Learning
While Reinforcement Learning ( RL) has made great strides towards solving increasingly complicated problems, many algorithms are still brittle to even slight environmental changes.
RelTR: Relation Transformer for Scene Graph Generation
Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy.
LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking
Multi-Camera Multi-Object Tracking is currently drawing attention in the computer vision field due to its superior performance in real-world applications such as video surveillance in crowded scenes or in wide spaces.
Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection
In industrial manufacturing processes, errors frequently occur at unpredictable times and in unknown manifestations.
Ranked #1 on
Anomaly Detection
on Surface Defect Saliency of Magnetic Tile
(using extra training data)
CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning
While Reinforcement Learning has made great strides towards solving ever more complicated tasks, many algorithms are still brittle to even slight changes in their environment.
Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths
We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT).
Disentangled Lifespan Face Synthesis
The generated face image given a target age code is expected to be age-sensitive reflected by bio-plausible transformations of shape and texture, while being identity preserving.
Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows
3D human pose estimation from monocular images is a highly ill-posed problem due to depth ambiguities and occlusions.
Ranked #46 on
3D Human Pose Estimation
on MPI-INF-3DHP
(PCK metric)
Monocular 3D Human Pose Estimation
Multi-Hypotheses 3D Human Pose Estimation
Spatial-Temporal Transformer for Dynamic Scene Graph Generation
Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects and the temporal dependencies between frames allowing for a richer semantic interpretation.
World-GAN: a Generative Model for Minecraft Worlds
This work introduces World-GAN, the first method to perform data-driven Procedural Content Generation via Machine Learning in Minecraft from a single example.
Automatic Risk Adaptation in Distributional Reinforcement Learning
The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes, depending on the familiarity of the agent with its environment.
Distributional Reinforcement Learning
reinforcement-learning
+1
Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images
A RANSAC estimator guided by a neural network fits these primitives to 3D features, such as a depth map.
Text to Image Generation with Semantic-Spatial Aware GAN
Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions.
Context-Aware Layout to Image Generation with Enhanced Object Appearance
We argue that these are caused by the lack of context-aware object and stuff feature encoding in their generators, and location-sensitive appearance representation in their discriminators.
Ranked #1 on
Layout-to-Image Generation
on COCO-Stuff 128x128
Localization of Cochlear Implant Electrodes from Cone Beam Computed Tomography using Particle Belief Propagation
Currently the methods used in clinics to characterize the geometry of the cochlea as well as to estimate the electrode positions are manual, error-prone and time consuming.
CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild
Human pose estimation from single images is a challenging problem in computer vision that requires large amounts of labeled training data to be solved accurately.
Ranked #3 on
3D Human Pose Estimation
on SkiPose
Monocular 3D Human Pose Estimation
Weakly-supervised 3D Human Pose Estimation
Exploring Dynamic Context for Multi-path Trajectory Prediction
In our framework, first, the spatial context between agents is explored by using self-attention architectures.
Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows
To achieve a high robustness and performance we exploit multiple transformations in training and evaluation.
Ranked #2 on
Anomaly Detection
on InsPLAD
TOAD-GAN: Coherent Style Level Generation from a Single Example
In this work, we present TOAD-GAN (Token-based One-shot Arbitrary Dimension Generative Adversarial Network), a novel Procedural Content Generation (PCG) algorithm that generates token-based video game levels.
Weakly-supervised Learning of Human Dynamics
This paper proposes a weakly-supervised learning framework for dynamics estimation from human motion.
Lifted Disjoint Paths with Application in Multiple Object Tracking
We present an extension to the disjoint paths problem in which additional \emph{lifted} edges are introduced to provide path connectivity priors.
Ranked #2 on
Multi-Object Tracking
on 2D MOT 2015
AMENet: Attentive Maps Encoder Network for Trajectory Prediction
Trajectory prediction is critical for applications of planning safe future movements and remains challenging even for the next few seconds in urban mixed traffic.
LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery
This strengthens the local feature invariance for the resampled features and enables detecting vehicles in an arbitrary orientation.
Image Captioning through Image Transformer
Inspired by the successes in text analysis and translation, previous work have proposed the \textit{transformer} architecture for image captioning.
FairNN- Conjoint Learning of Fair Representations for Fair Decisions
In this paper, we propose FairNN a neural network that performs joint feature representation and classification for fairness-aware learning.
MCENET: Multi-Context Encoder Network for Homogeneous Agent Trajectory Prediction in Mixed Traffic
In inference time, we combine the past context and motion information of the target agent with samplings of the latent variables to predict multiple realistic trajectories in the future.
NODIS: Neural Ordinary Differential Scene Understanding
Detected objects, their labels and the discovered relations can be used to construct a scene graph which provides an abstract semantic interpretation of an image.
Ranked #8 on
Scene Graph Generation
on Visual Genome
CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus
We present a robust estimator for fitting multiple parametric models of the same form to noisy measurements.
Neural Random Forest Imitation
We present Neural Random Forest Imitation - a novel approach for transforming random forests into neural networks.
Learning Disentangled Representations via Independent Subspaces
We use face images as our example of choice.
Temporally Consistent Horizon Lines
The horizon line is an important geometric feature for many image processing and scene understanding tasks in computer vision.
Ranked #1 on
Horizon Line Estimation
on KITTI Horizon
Multiple People Tracking using Body and Joint Detections
We evaluate our framework on the MOT16/17 benchmark.
Ranked #32 on
Multi-Object Tracking
on MOT17
(MOTA metric)
Target-Tailored Source-Transformation for Scene Graph Generation
We further explore more powerful representations by integrating language prior with the visual context in the transformation for the scene graph generation.
RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation
This efficiently avoids a simple memorization of the training data and allows for a weakly supervised training.
Ranked #24 on
Weakly-supervised 3D Human Pose Estimation
on Human3.6M
Security Event Recognition for Visual Surveillance
The experimental results show that the proposed approach outperforms the state-of-the-art methods and effective in recognizing complex security events.
Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera
In this work, we propose a method that combines a single hand-held camera and a set of Inertial Measurement Units (IMUs) attached at the body limbs to estimate accurate 3D poses in the wild.
Markov Chain Neural Networks
In this work we present a modified neural network model which is capable to simulate Markov Chains.
Triplet-based Deep Similarity Learning for Person Re-Identification
Moreover, we trained the model jointly on six different datasets, which differs from common practice - one model is just trained on one dataset and tested also on the same one.
Video Event Recognition and Anomaly Detection by Combining Gaussian Process and Hierarchical Dirichlet Process Models
In our framework, three levels of video events are connected by Hierarchical Dirichlet Process (HDP) model: low-level visual features, simple atomic activities, and multi-agent interactions.
Slice Sampling Particle Belief Propagation
We propose to avoid dependence on a proposal distribution by introducing a slice sampling based PBP algorithm.
Temporally Object-based Video Co-Segmentation
Therefore, we formulate a graphical model to select a proposal stream for each object in which the pairwise potentials consist of the appearance dissimilarity between different streams in the same video and also the similarity between the streams in different videos.
Vehicle Detection in Aerial Images
Also, the focal loss function is used to substitute for conventional cross entropy loss function in both of the region proposed network and the final classifier.
Natural Language Guided Visual Relationship Detection
Most of the existing works treat this task as a pure visual classification task: each type of relationship or phrase is classified as a relation category based on the extracted visual features.
Object Recognition from very few Training Examples for Enhancing Bicycle Maps
These algorithms are usually trained on large datasets consisting of thousands or millions of labeled training examples.
Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection
We present a novel approach for vanishing point detection from uncalibrated monocular images.
Ranked #3 on
Horizon Line Estimation
on York Urban Dataset
Automatic tracking of vessel-like structures from a single starting point
Further visual results also show the potential of our approach for identifying vascular networks topologies.
Fusion of Head and Full-Body Detectors for Multi-Object Tracking
In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be a very effective approach.
Ranked #21 on
Multi-Object Tracking
on MOT16
Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs
We address the problem of making human motion capture in the wild more practical by using a small set of inertial sensors attached to the body.
A Kinematic Chain Space for Monocular Motion Capture
This paper deals with motion capture of kinematic chains (e. g. human skeletons) from monocular image sequences taken by uncalibrated cameras.
Motion Segmentation via Global and Local Sparse Subspace Optimization
In this paper, we propose a new framework for segmenting feature-based moving objects under affine subspace model.
On Support Relations and Semantic Scene Graphs
In contrast to previous methods for extracting support relations, the proposed approach generates more accurate results, and does not require a pixel-wise semantic labeling of the scene.
Unbiased Sparse Subspace Clustering By Selective Pursuit
If these unknown subspaces are well-separated this algorithm is guaranteed to succeed.
Tracking with multi-level features
We present a novel formulation of the multiple object tracking problem which integrates low and mid-level features.
PSyCo: Manifold Span Reduction for Super Resolution
The main challenge in Super Resolution (SR) is to discover the mapping between the low- and high-resolution manifolds of image patches, a complex ill-posed problem which has recently been addressed through piecewise linear regression with promising results.
Multicamera Calibration From Visible and Mirrored Epipoles
Multicamera rigs are used in a large number of 3D Vision applications, such as 3D modeling, motion capture or telepresence and a robust calibration is of utmost importance in order to achieve a high accuracy results.
Automatic 3D Liver Segmentation Using Sparse Representation of Global and Local Image Information via Level Set Formulation
A sparse representation of both global (region-based) and local (voxel-wise) image information is embedded in a level set formulation to innovate a new cost function.
Expanding Object Detector's Horizon: Incremental Learning Framework for Object Detection in Videos
By incrementally detecting object instances in video and adding confident detections into the model, we are able to dynamically adjust the complexity of the detector over time by instantiating new prototypes to span all domains the model has seen.
Learning an Image-based Motion Context for Multiple People Tracking
We present a novel method for multiple people tracking that leverages a generalized model for capturing interactions among individuals.
Posebits for Monocular Human Pose Estimation
We advocate the inference of qualitative information about 3D human pose, called posebits, from images.
Class Generative Models Based on Feature Regression for Pose Estimation of Object Categories
In this paper, we propose a method for learning a class representation that can return a continuous value for the pose of an unknown class instance using only 2D data and weak 3D labelling information.
