Search Results for author:
Found 28 papers, 11 papers with code
DiffAnt: Diffusion Models for Action Anticipation
However, the majority of existing action anticipation models adhere to a deterministic approach, neglecting to account for future uncertainties.
Security Fence Inspection at Airports Using Object Detection
In this work, we explore object detection methods to address the fence inspection task and localize various types of damages.
A Survey on Deep Learning Techniques for Action Anticipation
The ability to anticipate possible future human actions is essential for a wide range of applications, including autonomous driving and human-robot interaction.
POET: A Self-learning Framework for PROFINET Industrial Operations Behaviour
It successfully detects and reports the anomalies triggered by a network attack in a miniaturized PROFINET-based industrial system, executed through valid network protocol exchanges and resulting in invalid PROFINET operation transition for the device.
Attention-based Part Assembly for 3D Volumetric Shape Modeling
Modeling a 3D volumetric shape as an assembly of decomposed shape parts is much more challenging, but semantically more valuable than direct reconstruction from a full shape representation.
Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions
Deep neural networks for scene perception in automated vehicles achieve excellent results for the domains they were trained on.
Attention-based Point Cloud Edge Sampling
Point cloud sampling is a less explored research topic for this data representation.
Ranked #31 on
3D Point Cloud Classification
on ModelNet40
Effects of Architectures on Continual Semantic Segmentation
Specifically, we compare the well-researched CNNs to recently proposed Transformers and Hybrid architectures, as well as the impact of the choice of novel normalization layers and different decoder heads.
Sim2real Transfer Learning for Point Cloud Segmentation: An Industrial Application Case on Autonomous Disassembly
On robotics computer vision tasks, generating and annotating large amounts of data from real-world for the use of deep learning-based approaches is often difficult or even impossible.
SynMotor: A Benchmark Suite for Object Attribute Regression and Multi-task Learning
Our work is a sub-task in the framework of a remanufacturing project, in which small electric motors are used as fundamental objects.
MotorFactory: A Blender Add-on for Large Dataset Generation of Small Electric Motors
To enable automatic disassembly of different product types with uncertain conditions and degrees of wear in remanufacturing, agile production systems that can adapt dynamically to changing requirements are needed.
Object Detection in 3D Point Clouds via Local Correlation-Aware Point Embedding
We present an improved approach for 3D object detection in point cloud data based on the Frustum PointNet (F-PointNet).
Generative-Contrastive Learning for Self-Supervised Latent Representations of 3D Shapes from Multi-Modal Euclidean Input
We propose a combined generative and contrastive neural architecture for learning latent representations of 3D volumetric shapes.
Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation
Although human action anticipation is a task which is inherently multi-modal, state-of-the-art methods on well known action anticipation datasets leverage this data by applying ensemble methods and averaging scores of unimodal anticipation networks.
Ranked #2 on
Action Anticipation
on EPIC-KITCHENS-100
Improving Replay-Based Continual Semantic Segmentation with Smart Data Selection
Continual learning for Semantic Segmentation (CSS) is a rapidly emerging field, in which the capabilities of the segmentation model are incrementally improved by learning new classes or new domains.
Continual Learning for Class- and Domain-Incremental Semantic Segmentation
Therefore, the goal of our work is to evaluate and adapt established solutions for continual object recognition to the task of semantic segmentation and to provide baseline methods and evaluation protocols for the task of continual semantic segmentation.
Class-Incremental Semantic Segmentation
Continual Semantic Segmentation
+6
Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation
Therefore, in a set of experiments and representational analyses, we demonstrate that the semantic shift of the background class and a bias towards new classes are the major causes of forgetting in CiSS.
Class-Incremental Semantic Segmentation
Incremental Learning
+2
UPAR: Unified Pedestrian Attribute Recognition and Person Retrieval
It is based on four well-known person attribute recognition datasets: PA100K, PETA, RAPv2, and Market1501.
Deep Sensor Fusion with Pyramid Fusion Networks for 3D Semantic Segmentation
A novel Pyramid Fusion Backbone fuses these feature maps at different scales and combines the multimodal features in a feature pyramid to compute valuable multimodal, multi-scale features.
Bézier Curve Gaussian Processes
Probabilistic models for sequential data are the basis for a variety of applications concerned with processing timely ordered information.
Deflectometry for specular surfaces: an overview
Deflectometry as a technical approach to assessing reflective surfaces has now existed for almost 40 years.
ReS2tAC -- UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devices
In this, we propose an optimization of the algorithm for embedded CUDA GPUs, by using massively parallel computing, as well as using the NEON intrinsics to optimize the algorithm for vectorized SIMD processing on embedded ARM CPUs.
Do as we do: Multiple Person Video-To-Video Transfer
Our goal is to transfer the motion of real people from a source video to a target video with realistic results.
Human Pose Estimation for Real-World Crowded Scenarios
In order to overcome the transfer gap of JTA originating from a low pose variety and less dense crowds, an extension dataset is created to ease the use for real-world applications.
Ranked #14 on
Multi-Person Pose Estimation
on CrowdPose
A Systematic Evaluation of Recent Deep Learning Architectures for Fine-Grained Vehicle Classification
Fine-grained vehicle classification is the task of classifying make, model, and year of a vehicle.
Open Set Logo Detection and Retrieval
Given a query sample in shape of a logo image, the task is to find all further occurrences of this logo in a set of images or videos.
Unconstrained Face Detection and Open-Set Face Recognition Challenge
Face detection and recognition benchmarks have shifted toward more difficult environments.
Cavlectometry: Towards Holistic Reconstruction of Large Mirror Objects
We introduce a method based on the deflectometry principle for the reconstruction of specular objects exhibiting significant size and geometric complexity.
