Search Results for author: Simone Frintrop

Found 21 papers, 8 papers with code

S$^3$AD: Semi-supervised Small Apple Detection in Orchard Environments

no code implementations8 Nov 2023 Robert Johanson, Christian Wilms, Ole Johannsen, Simone Frintrop

However, crop detection, e. g., apple detection in orchard environments remains challenging due to a lack of large-scale datasets and the small relative size of the crops in the image.

object-detection Small Object Detection

High-Level Features Parallelization for Inference Cost Reduction Through Selective Attention

no code implementations9 Aug 2023 André Peter Kelm, Lucas Schmidt, Tim Rolff, Christian Wilms, Ehsan Yaghoubi, Simone Frintrop

In this work, we parallelize high-level features in deep networks to selectively skip or select class-specific features to reduce inference costs.

Audio-Visual Speech Enhancement with Score-Based Generative Models

no code implementations2 Jun 2023 Julius Richter, Simone Frintrop, Timo Gerkmann

This paper introduces an audio-visual speech enhancement system that leverages score-based generative models, also known as diffusion models, conditioned on visual information.

Automatic Speech Recognition Lipreading +3

Teacher Network Calibration Improves Cross-Quality Knowledge Distillation

1 code implementation15 Apr 2023 Pia Čuk, Robin Senge, Mikko Lauri, Simone Frintrop

We investigate cross-quality knowledge distillation (CQKD), a knowledge distillation method where knowledge from a teacher network trained with full-resolution images is transferred to a student network that takes as input low-resolution images.

Image Classification Knowledge Distillation

Immersive Neural Graphics Primitives

1 code implementation24 Nov 2022 Ke Li, Tim Rolff, Susanne Schmidt, Reinhard Bacher, Simone Frintrop, Wim Leemans, Frank Steinicke

In this paper, we present and evaluate a NeRF-based framework that is capable of rendering scenes in immersive VR allowing users to freely move their heads to explore complex real-world scenes.

Benchmarking Super-Resolution

Segmenting Medical Instruments in Minimally Invasive Surgeries using AttentionMask

no code implementations21 Mar 2022 Christian Wilms, Alexander Michael Gerlach, Rüdiger Schmitz, Simone Frintrop

Our evaluation in an object proposal generation framework shows that our adapted AttentionMask system is robust to image degradations, generalizes well to unseen types of surgeries, and copes well with small instruments.

Object Object Proposal Generation +1

Localizing Small Apples in Complex Apple Orchard Environments

no code implementations23 Feb 2022 Christian Wilms, Robert Johanson, Simone Frintrop

Since the apples are very small objects in such scenarios, we tackle this problem by adapting the object proposal generation system AttentionMask that focuses on small objects.

Object Object Proposal Generation

DeepFH Segmentations for Superpixel-based Object Proposal Refinement

no code implementations7 Aug 2021 Christian Wilms, Simone Frintrop

Class-agnostic object proposal generation is an important first step in many object detection pipelines.

Object object-detection +3

The MSR-Video to Text Dataset with Clean Annotations

1 code implementation12 Feb 2021 Haoran Chen, Jianmin Li, Simone Frintrop, Xiaolin Hu

We cleaned the MSR-VTT annotations by removing these problems, then tested several typical video captioning models on the cleaned dataset.

Sentence Video Captioning

Superpixel-based Refinement for Object Proposal Generation

1 code implementation12 Jan 2021 Christian Wilms, Simone Frintrop

Precise segmentation of objects is an important problem in tasks like class-agnostic object proposal generation or instance segmentation.

Instance Segmentation Object +3

Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization

no code implementations4 Jul 2020 Mikko Lauri, Joni Pajarinen, Jan Peters, Simone Frintrop

We consider the problem of creating a 3D model using depth images captured by a team of multiple robots.

6D Object Pose Regression via Supervised Learning on Point Clouds

1 code implementation24 Jan 2020 Ge Gao, Mikko Lauri, Yulong Wang, Xiaolin Hu, Jianwei Zhang, Simone Frintrop

We use depth information represented by point clouds as the input to both deep networks and geometry-based pose refinement and use separate networks for rotation and translation regression.

Object regression +1

AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects

1 code implementation21 Nov 2018 Christian Wilms, Simone Frintrop

We propose a novel approach for class-agnostic object proposal generation, which is efficient and especially well-suited to detect small objects.

Object Proposal Generation

Multi-label Object Attribute Classification using a Convolutional Neural Network

no code implementations10 Nov 2018 Soubarna Banik, Mikko Lauri, Simone Frintrop

With this inspiration, a deep convolutional neural network for low-level object attribute classification, called the Deep Attribute Network (DAN), is proposed.

Attribute General Classification +2

Occlusion Resistant Object Rotation Regression from Point Cloud Segments

no code implementations16 Aug 2018 Ge Gao, Mikko Lauri, Jianwei Zhang, Simone Frintrop

Rotation estimation of known rigid objects is important for robotic applications such as dexterous manipulation.

Object regression

Saliency-guided Adaptive Seeding for Supervoxel Segmentation

no code implementations13 Apr 2017 Ge Gao, Mikko Lauri, Jianwei Zhang, Simone Frintrop

We propose a new saliency-guided method for generating supervoxels in 3D space.

Segmentation

Object proposal generation applying the distance dependent Chinese restaurant process

1 code implementation12 Apr 2017 Mikko Lauri, Simone Frintrop

In application domains such as robotics, it is useful to represent the uncertainty related to the robot's belief about the state of its environment.

Bayesian Inference Object +2

Multi-Robot Active Information Gathering with Periodic Communication

no code implementations7 Mar 2017 Mikko Lauri, Eero Heinänen, Simone Frintrop

We address the problem of coordinating the actions of a team of robots with periodic communication capability executing an information gathering task.

Decision Making

Traditional Saliency Reloaded: A Good Old Model in New Shape

no code implementations CVPR 2015 Simone Frintrop, Thomas Werner, German Martin Garcia

In this paper, we show that the seminal, biologically-inspired saliency model by Itti et al. is still competitive with current state-of-the-art methods for salient object segmentation if some important adaptions are made.

Object Object Proposal Generation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.