Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
teaching:se-iu-ss16 [2016/04/18 07:21] – jworchteaching:se-iu-ss16 [2016/04/18 08:03] (current) – [Features] raider
Line 16: Line 16:
 The seminar will deal with the challenges of semantic perception in the context of robotics, presenting various aspects of it. Students will be presented with an overview of the field followed by individual presentations and reports of pre-defined topics. The seminar will deal with the challenges of semantic perception in the context of robotics, presenting various aspects of it. Students will be presented with an overview of the field followed by individual presentations and reports of pre-defined topics.
  
 +===== Literature =====
 +
 +==== Segmentation ====
 +
 +Weakly supervised graph based semantic segmentation by learning 
 +communities of image-parts
 +http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Pourian_Weakly_Supervised_Graph_ICCV_2015_paper.pdf
 +
 +Decision Making under Uncertain Segmentations
 +http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7139359
 +
 +==== Features ====
 +
 +KAZE Features **+** Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces
 +http://www.robesafe.com/personal/pablo.alcantarilla/papers/Alcantarilla12eccv.pdf
 +http://www.robesafe.com/personal/pablo.alcantarilla/papers/Alcantarilla13bmvc.pdf
 +
 +B-SHOT: A Binary Feature Descriptor for Fast and Efficient Keypoint 
 +Matching on 3D Point Clouds
 +http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7353630
 +
 +Rotation and Translation Invariant 3D Descriptor for Surfaces
 +http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7353450
 +
 +==== Object Detection, Recognition and Tracking ====
 +
 +Real-time Pose Detection and Tracking of Hundreds of Objects **+** SimTrack: A Simulation-based Framework for Scalable Real-time Object 
 +Pose Detection and Tracking
 +http://www.karlpauwels.com/downloads/tcsvt_2015/Pauwels_IEEE_TCSVT_2015.pdf
 +http://www.karlpauwels.com/downloads/iros_2015/Pauwels_IROS_2015.pdf
 +
 +Surface Oriented Traverse for Robust Instance Detection in RGB-D
 +http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7353983
 +
 +RGB-D Object Modelling for Object Recognition and Tracking
 +http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7353360
 +
 +Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
 +http://arxiv.org/abs/1506.01497
 +
 +Rich feature hierarchies for accurate object detection and semantic segmentation
 +http://arxiv.org/abs/1311.2524
 +
 +Efficient RGB-D Object Categorization Using cascaded Ensembles of 
 +Randomized Decision Trees
 +http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7139358
 +
 +Robust 3D tracking of Unknown Objects
 +http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=7139520
 +
 +Depth-Based Tracking with Physical Constraints for Robot Manipulation
 +http://homes.cs.washington.edu/~tws10/DepthBasedTracking.pdf
 +
 +==== Affordances ====
 +
 +AfNet: The Affordance Network
 +http://link.springer.com/chapter/10.1007%2F978-3-642-37331-2_39
 +
 +Affordance detection of Tool parts from Geometric Features
 +http://www.visionmeetscognition.org/fpic2014/Camera_Ready/Paper%2035.pdf
 +
 +Long-term human affordance maps
 +http://dx.doi.org/10.1109/IROS.2015.7354193
 +
 +==== Deep Learning ====
 +
 +Visualizing and Understanding Convolutional Networks
 +https://www.cs.nyu.edu/~fergus/papers/zeilerECCV2014.pdf
 +
 +DeepFace: Closing the Gap to Human-Level Performance in Face Verification
 +https://www.cs.toronto.edu/~ranzato/publications/taigman_cvpr14.pdf
 +
 +MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation
 +http://cs.nyu.edu/~ajain/accv2014/paper.pdf
 +
 +Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
 +https://www.robots.ox.ac.uk/~vgg/rg/papers/tompson2014.pdf
 +
 +Flowing ConvNets for Human Pose Estimation in Videos
 +https://www.robots.ox.ac.uk/~vgg/publications/2015/Pfister15a/pfister15a.pdf
 +
 +Multimodal deep learning for robust RGB-D object recognition
 +http://arxiv.org/pdf/1507.06821v2.pdf
 +
 +RGB-D Object Recognition and Pose Estimation Based on Pre-Trained 
 +Convolutional Neural Network Features
 +https://www.ais.uni-bonn.de/papers/ICRA_2015_Schwarz_RGB-D-Objects_Transfer-Learning.pdf
 +
 +==== Unsupervised Deep Learning ====
 +
 +Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition
 +http://yann.lecun.com/exdb/publis/pdf/ranzato-cvpr-07.pdf
 +
 +Convolution Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations
 +http://web.eecs.umich.edu/~honglak/icml09-ConvolutionalDeepBeliefNetworks.pdf
 +
 +Sparse Feature Learning for Deep Belief Networks
 +https://papers.nips.cc/paper/3363-sparse-feature-learning-for-deep-belief-networks.pdf
 +
 +Efficient sparse coding algorithms
 +https://papers.nips.cc/paper/2979-efficient-sparse-coding-algorithms.pdf
 +
 +==== Human Detection and Tracking ==== 
 +
 +Automatic initialization for skeleton tracking in optical motion capture
 +http://dx.doi.org/10.1109/ICRA.2015.7139260
 +
 +Unsupervised robot learning to predict person motion
 +http://dx.doi.org/10.1109/ICRA.2015.7139254
 +
 +Pose estimation for a partially observable human body from RGB-D cameras
 +http://dx.doi.org/10.1109/IROS.2015.7354068
 +
 +Real-time full-body human attribute classification in RGB-D using a 
 +tessellation boosting approach
 +http://dx.doi.org/10.1109/IROS.2015.7353541
 +
 +==== Action Recognition ====
 +
 +Learning symbolic representations of actions from human demonstrations
 +http://dx.doi.org/10.1109/ICRA.2015.7139728
 +
 +Fast Target Prediction of Human Reaching Motion for Cooperative 
 +Human-Robot Manipulation Tasks Using Time Series Classification
 +http://dx.doi.org/10.1109/ICRA.2015.7140066
 +
 +Effective 3D action recognition using EigenJoints
 +http://dx.doi.org/10.1016/j.jvcir.2013.03.001
 +
 +Sequence of the most informative joints (SMIJ): A new representation for 
 +human skeletal action recognition
 +http://dx.doi.org/10.1016/j.jvcir.2013.04.007
 +
 +Unsupervised Temporal Segmentation of Repetitive Human Actions Based on 
 +Kinematic Modeling and Frequency Analysis
 +http://arxiv.org/abs/1512.04115
 +
 +sEMG-based decoding of detailed human intentions from finger-level hand 
 +motions
 +http://dx.doi.org/10.1109/IROS.2015.7353982
 +
 +Human motion classification and recognition using wholebody contact force
 +http://dx.doi.org/10.1109/IROS.2015.7353979
 +
 +Context-based intent understanding using an Activation Spreading 
 +architecture
 +http://dx.doi.org/10.1109/IROS.2015.7353791
 +
 +A framework for unsupervised online human reaching motion recognition 
 +and early prediction
 +http://dx.doi.org/10.1109/IROS.2015.7353706
 +
 +Human intention inference and motion modeling using approximate E-M with 
 +online learning
 +http://dx.doi.org/10.1109/IROS.2015.7353614
 +
 +==== RoboSherlock ====
 +
 +**These four papers count as one block, i.e. they have to be presented together.**
 +
 +RoboSherlock: Unstructured Information Processing for Robot Perception
 +http://ai.uni-bremen.de/_media/paper/beetz15robosherlock.pdf
 +
 +RoboSherlock: Unstructured Information Processing Framework for Robotic Perception
 +http://dx.doi.org/10.1007/978-3-319-26327-4_8
 +
 +Pervasive 'Calm' Perception for Autonomous Robotic Agents
 +http://ai.uni-bremen.de/_media/paper/Wiedemeyer15pervasive.pdf
 +
 +Perception for Everyday Human Robot Interaction
 +http://dx.doi.org/10.1007/s13218-015-0400-1
- Impressum - Datenschutz



Prof. Dr. hc. Michael Beetz PhD
Head of Institute

Contact via
Andrea Cowley
assistant to Prof. Beetz
ai-office@cs.uni-bremen.de

Discover our VRB for innovative and interactive research


Memberships and associations:


Social Media: