2020
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration
B. L. Bhatnagar, C. Sminchisescu, C. Theobalt and G. Pons-Moll
Advances in Neural Information Processing Systems 33 (NIPS 2020), 2020
Neural Unsigned Distance Fields for Implicit Function Learning
J. Chibane, A. Mir and G. Pons-Moll
Advances in Neural Information Processing Systems 33 (NIPS 2020), 2020
Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction
B. L. Bhatnagar, C. Sminchisescu, C. Theobalt and G. Pons-Moll
Computer Vision -- ECCV 2020, 2020
Kinematic 3D Object Detection in Monocular Video
G. Brazil, G. Pons-Moll, X. Liu and B. Schiele
Computer Vision -- ECCV 2020, 2020
NASA: Neural Articulated Shape Approximation
B. Deng, J. P. Lewis, T. Jeruzalski, G. Pons-Moll, G. Hinton, M. Norouzi and A. Tagliasacchi
Computer Vision -- ECCV 2020, 2020
An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
Y. Liu, B. Schiele and Q. Sun
Computer Vision -- ECCV 2020, 2020
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
M. Rolínek, P. Swoboda, D. Zietlow, A. Paulus, V. Musil and G. Martius
Computer Vision -- ECCV 2020, 2020
Towards Automated Testing and Robustification by Semantic Adversarial Data Generation
R. Shetty, M. Fritz and B. Schiele
Computer Vision -- ECCV 2020, 2020
SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing
G. Tiwari, B. L. Bhatnagar, T. Tung and G. Pons-Moll
Computer Vision -- ECCV 2020, 2020
(Accepted/in press)
Unsupervised Shape and Pose Disentanglement for 3D Meshes
K. Zhou, B. L. Bhatnagar and G. Pons-Moll
Computer Vision -- ECCV 2020, 2020
Sparse Recovery with Integrality Constraints
J.-H. Lange, M. E. Pfetsch, B. M.Seib and A. M.Tillmann
Discrete Applied Mathematics, Volume 283, 2020
Norm-Aware Embedding for Efficient Person Search
D. Chen, S. Zhang, J. Yang and B. Schiele
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), 2020
Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
J. Chibane, T. Alldieck and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), 2020
DeepCap: Monocular Human Performance Capture Using Weak Supervision
M. Habermann, W. Xu, M. Zollhöfer, G. Pons-Moll and C. Theobalt
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), 2020
Mnemonics Training: Multi-Class Incremental Learning Without Forgetting
Y. Liu, Y. Su, A.-A. Liu, B. Schiele and Q. Sun
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), 2020
Learning to Transfer Texture from Clothing Images to 3D Humans
A. Mir, T. Alldieck and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), 2020
TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style
C. Patel, Z. Liao and G. Pons-Moll
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), 2020
Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering
M. Keuper, S. Tang, B. Andres, T. Brox and B. Schiele
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 42, Number 1, 2020
Meta-Transfer Learning through Hard Tasks
Q. Sun, Y. Liu, Z. Chen, T.-S. Chua and B. Schiele
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
(Accepted/in press)
SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera
D. Tome, T. Alldieck, P. Peluse, G. Pons-Moll, L. Agapito, H. Badino and F. de la Torre
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor
T. Yu, Z. Zheng, K. Guo, J. Zhao, Q. Dai, H. Li, G. Pons-Moll and Y. Liu
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks
T. Orekondy, B. Schiele and M. Fritz
International Conference on Learning Representations (ICLR 2020), 2020
Deep Gaze Pooling: Inferring and Visually Decoding Search Intents from Human Gaze Fixations
H. Sattar, M. Fritz and A. Bulling
Neurocomputing, Volume 387, 2020
On the Lifted Multicut Polytope for Trees
J.-H. Lange and B. Andres
Pattern Recognition (GCPR 2020), 2020
(Accepted/in press)
Anticipating Averted Gaze in Dyadic Interactions
P. Müller, E. Sood and A. Bulling
Proceedings ETRA 2020 Full Papers, 2020
Lifted Disjoint Paths with Application in Multiple Object Tracking
A. Horňáková, R. Henschel, B. Rosenhahn and P. Swoboda
Proceedings of the 37th International Conference on Machine Learning (ICML 2020), 2020
A Primal-Dual Solver for Large-Scale Tracking-by-Assignment
S. Haller, M. Prakash, L. Hutschenreiter, T. Pietzsch, C. Rother, F. Jug, P. Swoboda and B. Savchynskyy
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (AISTATS 2020), 2020
Hierarchical Online Instance Matching for Person Search
D. Chen, S. Zhang, W. Ouyang, J. Yang and B. Schiele
Thirty-Fourth AAAI Conference on Artificial Intelligence Technical Tracks 7, 2020
Improved Methods and Analysis for Semantic Image Segmentation
Y. He
PhD Thesis, Universität des Saarlandes, 2020
Abstract
Modern deep learning has enabled amazing developments of computer vision in recent years (Hinton and Salakhutdinov, 2006; Krizhevsky et al., 2012). As a fundamental task, semantic segmentation aims to predict class labels for each pixel of images, which empowers machines perception of the visual world. In spite of recent successes of fully convolutional networks (Long etal., 2015), several challenges remain to be addressed. In this thesis, we focus on this topic, under different kinds of input formats and various types of scenes. Specifically, our study contains two aspects: (1) Data-driven neural modules for improved performance. (2) Leverage of datasets w.r.t.training systems with higher performances and better data privacy guarantees. In the first part of this thesis, we improve semantic segmentation by designing new modules which are compatible with existing architectures. First, we develop a spatio-temporal data-driven pooling, which brings additional information of data (i.e. superpixels) into neural networks, benefiting the training of neural networks as well as the inference on novel data. We investigate our approach in RGB-D videos for segmenting indoor scenes, where depth provides complementary cues to colors and our model performs particularly well. Second, we design learnable dilated convolutions, which are the extension of standard dilated convolutions, whose dilation factors (Yu and Koltun, 2016) need to be carefully determined by hand to obtain decent performance. We present a method to learn dilation factors together with filter weights of convolutions to avoid a complicated search of dilation factors. We explore extensive studies on challenging street scenes, across various baselines with different complexity as well as several datasets at varying image resolutions. In the second part, we investigate how to utilize expensive training data. First, we start from the generative modelling and study the network architectures and the learning pipeline for generating multiple examples. We aim to improve the diversity of generated examples but also to preserve the comparable quality of the examples. Second, we develop a generative model for synthesizing features of a network. With a mixture of real images and synthetic features, we are able to train a segmentation model with better generalization capability. Our approach is evaluated on different scene parsing tasks to demonstrate the effectiveness of the proposed method. Finally, we study membership inference on the semantic segmentation task. We propose the first membership inference attack system against black-box semantic segmentation models, that tries to infer if a data pair is used as training data or not. From our observations, information on training data is indeed leaking. To mitigate the leakage, we leverage our synthetic features to perform prediction obfuscations, reducing the posterior distribution gaps between a training and a testing set. Consequently, our study provides not only an approach for detecting illegal use of data, but also the foundations for a safer use of semantic segmentation models.
Multicut Optimization Guarantees & Geometry of Lifted Multicuts
J.-H. Lange
PhD Thesis, Universität des Saarlandes, 2020
Learning from Limited Labeled Data - Zero-Shot and Few-Shot Learning
Y. Xian
PhD Thesis, Universität des Saarlandes, 2020
2019
SimulCap : Single-View Human Performance Capture with Cloth Simulation
T. Yu, Z. Zheng, Y. Zhong, J. Zhao, D. Quionhai, G. Pons-Moll and Y. Liu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019