Anton Milan
YOU?
Author Swipe
View article: Kaputt: A Large-Scale Dataset for Visual Defect Detection
Kaputt: A Large-Scale Dataset for Visual Defect Detection Open
We present a novel large-scale dataset for defect detection in a logistics setting. Recent work on industrial anomaly detection has primarily focused on manufacturing scenarios with highly controlled poses and a limited number of object ca…
View article: Learn to Predict Sets Using Feed-Forward Neural Networks
Learn to Predict Sets Using Feed-Forward Neural Networks Open
This paper addresses the task of set prediction using deep feed-forward neural networks. A set is a collection of elements which is invariant under permutation and the size of a set is not fixed in advance. Many real-world problems, such a…
View article: MOT20: A benchmark for multi object tracking in crowded scenes
MOT20: A benchmark for multi object tracking in crowded scenes Open
Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore…
View article: CVPR19 Tracking and Detection Challenge: How crowded can it get?
CVPR19 Tracking and Detection Challenge: How crowded can it get? Open
Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore…
View article: PoseTrack: A Benchmark for Human Pose Estimation and Tracking
PoseTrack: A Benchmark for Human Pose Estimation and Tracking Open
Human poses and motions are important cues for analysis of videos with people and there is strong evidence that representations based on body pose are highly effective for a variety of tasks such as activity recognition, content retrieval …
View article: Joint Learning of Set Cardinality and State Distribution
Joint Learning of Set Cardinality and State Distribution Open
We present a novel approach for learning to predict sets using deep learning. In recent years, deep neural networks have shown remarkable results in computer vision, natural language processing and other related problems. Despite their suc…
View article: Design of a Multi-Modal End-Effector and Grasping System: How Integrated Design helped win the Amazon Robotics Challenge
Design of a Multi-Modal End-Effector and Grasping System: How Integrated Design helped win the Amazon Robotics Challenge Open
We present the grasping system and design approach behind Cartman, the winning entrant in the 2017 Amazon Robotics Challenge. We investigate the design processes leading up to the final iteration of the system and describe the emergent sol…
View article: Mechanical Design of a Cartesian Manipulator for Warehouse Pick and Place
Mechanical Design of a Cartesian Manipulator for Warehouse Pick and Place Open
Robotic manipulation and grasping in cluttered and unstructured environments is a current challenge for robotics. Enabling robots to operate in these challenging environments have direct applications from automating warehouses to harvestin…
View article: DeepSetNet: Predicting Sets with Deep Neural Networks
DeepSetNet: Predicting Sets with Deep Neural Networks Open
This paper addresses the task of set prediction using deep learning. This is important because the output of many computer vision tasks, including image tagging and object detection, are naturally expressed as sets of entities rather than …
View article: Semantic Segmentation from Limited Training Data
Semantic Segmentation from Limited Training Data Open
We present our approach for robotic perception in cluttered scenes that led to winning the recent Amazon Robotics Challenge (ARC) 2017. Next to small objects with shiny and transparent surfaces, the biggest challenge of the 2017 competitio…
View article: Cartman: The low-cost Cartesian Manipulator that won the Amazon Robotics Challenge
Cartman: The low-cost Cartesian Manipulator that won the Amazon Robotics Challenge Open
The Amazon Robotics Challenge enlisted sixteen teams to each design a pick-and-place robot for autonomous warehousing, addressing development in robotic vision and manipulation. This paper presents the design of our custom-built, cost-effe…
View article: Joint Learning of Set Cardinality and State Distribution
Joint Learning of Set Cardinality and State Distribution Open
We present a novel approach for learning to predict sets using deep learning. In recent years, deep neural networks have shown remarkable results in computer vision, natural language processing and other related problems. Despite their suc…
View article: RGB-D object detection and semantic segmentation for autonomous manipulation in clutter
RGB-D object detection and semantic segmentation for autonomous manipulation in clutter Open
Autonomous robotic manipulation in clutter is challenging. A large variety of objects must be perceived in complex scenes, where they are partially occluded and embedded among many distractors, often in restricted spaces. To tackle these c…
View article: Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking
Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking Open
Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore…
View article: Online Multi-Target Tracking Using Recurrent Neural Networks
Online Multi-Target Tracking Using Recurrent Neural Networks Open
We present a novel approach to online multi-target tracking based on recurrent neural networks (RNNs). Tracking multiple objects in real-world scenes involves many challenges, including a) an a-priori unknown and time-varying number of tar…
View article: Data-Driven Approximations to NP-Hard Problems
Data-Driven Approximations to NP-Hard Problems Open
There exist a number of problem classes for which obtaining the exact solution becomes exponentially expensive with increasing problem size. The quadratic assignment problem (QAP) or the travelling salesman problem (TSP) are just two examp…
View article: PoseTrack: Joint Multi-Person Pose Estimation and Tracking
PoseTrack: Joint Multi-Person Pose Estimation and Tracking Open
In this work, we introduce the challenging problem of joint multi-person pose estimation and tracking of an unknown number of persons in unconstrained videos. Existing methods for multi-person pose estimation in images cannot be applied di…
View article: RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation Open
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated subsam…
View article: MOT16: A Benchmark for Multi-Object Tracking
MOT16: A Benchmark for Multi-Object Tracking Open
Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore…
View article: MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking Open
In the recent past, the computer vision community has developed centralized benchmarks for the performance evaluation of a variety of tasks, including generic object and pedestrian detection, 3D reconstruction, optical flow, single-object …