Analysis and Representation of Complex Activities in Videos

Joint Viewpoint and Keypoint Estimation with Real and Synthetic Data

Auteurs: Pau Panareda Busto, Juergen Gall
Publié dans: Pattern Recognition - 41st DAGM German Conference, DAGM GCPR 2019, Dortmund, Germany, September 10–13, 2019, Proceedings, Numéro 11824, 2019, Page(s) 107-121, ISBN 978-3-030-33675-2
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-33676-9_8

Adversarial Synthesis of Human Pose from Text

Auteurs: Yifei Zhang, Rania Briq, Julian Tanke, Juergen Gall
Publié dans: Pattern Recognition - 42nd DAGM German Conference, DAGM GCPR 2020, Tübingen, Germany, September 28 – October 1, 2020, Proceedings, Numéro 12544, 2021, Page(s) 145-158, ISBN 978-3-030-71277-8
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-71278-5_11

Recursive Bayesian Filtering for Multiple Human Pose Tracking from Multiple Cameras

Auteurs: Oh-Hun Kwon, Julian Tanke, Juergen Gall
Publié dans: Computer Vision – ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30 – December 4, 2020, Revised Selected Papers, Part II, Numéro 12623, 2021, Page(s) 438-453, ISBN 978-3-030-69531-6
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-69532-3_27

Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views

Auteurs: Julian Tanke, Juergen Gall
Publié dans: Pattern Recognition - 41st DAGM German Conference, DAGM GCPR 2019, Dortmund, Germany, September 10–13, 2019, Proceedings, Numéro 11824, 2019, Page(s) 537-550, ISBN 978-3-030-33675-2
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-33676-9_38

Discovering Multi-label Actor-Action Association in a Weakly Supervised Setting

Auteurs: Sovan Biswas, Juergen Gall
Publié dans: Computer Vision – ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30 – December 4, 2020, Revised Selected Papers, Part V, Numéro 12626, 2021, Page(s) 547-561, ISBN 978-3-030-69540-8
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-69541-5_33

Spatio-temporal Channel Correlation Networks for Action Classification

Auteurs: Ali Diba, Mohsen Fayyaz, Vivek Sharma, M. Mahdi Arzani, Rahman Yousefzadeh, Juergen Gall, Luc Van Gool
Publié dans: Computer Vision – ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part IV, Numéro 11208, 2018, Page(s) 299-315, ISBN 978-3-030-01224-3
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-01225-0_18

Hand Pose Estimation via Latent 2.5D Heatmap Regression

Auteurs: Umar Iqbal, Pavlo Molchanov, Thomas Breuel, Juergen Gall, Jan Kautz
Publié dans: Computer Vision – ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XI, Numéro 11215, 2018, Page(s) 125-143, ISBN 978-3-030-01251-9
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-01252-6_8

Multi-person Pose Estimation with Local Joint-to-Person Associations

Auteurs: Umar Iqbal, Juergen Gall
Publié dans: Computer Vision – ECCV 2016 Workshops, 2016, Page(s) 627-642, ISBN 978-3-319-48881-3
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-48881-3_44

AVID: Adversarial Visual Irregularity Detection

Auteurs: Mohammad Sabokrou, Masoud Pourreza, Mohsen Fayyaz, Rahim Entezari, Mahmood Fathy, Jürgen Gall, Ehsan Adeli
Publié dans: Computer Vision – ACCV 2018 - 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part VI, Numéro 11366, 2019, Page(s) 488-505, ISBN 978-3-030-20875-2
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-20876-9_31

Long-Term Anticipation of Activities with Cycle Consistency

Auteurs: Yazan Abu Farha, Qiuhong Ke, Bernt Schiele, Juergen Gall
Publié dans: Pattern Recognition - 42nd DAGM German Conference, DAGM GCPR 2020, Tübingen, Germany, September 28 – October 1, 2020, Proceedings, Numéro 12544, 2021, Page(s) 159-173, ISBN 978-3-030-71277-8
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-71278-5_12

MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation

Auteurs: Yazan Abu Farha, Jurgen Gall
Publié dans: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, Page(s) 3570-3579, ISBN 978-1-7281-3293-8
Éditeur: IEEE
DOI: 10.1109/cvpr.2019.00369

Level Selector Network for Optimizing Accuracy-Specificity Trade-Offs

Auteurs: Ahsan Iqbal, Juergen Gall
Publié dans: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019, Page(s) 1466-1473, ISBN 978-1-7281-5023-9
Éditeur: IEEE
DOI: 10.1109/iccvw.2019.00184

Temporal Action Segmentation From Timestamp Supervision

Auteurs: Zhe Li, Yazan Abu Farha, Jurgen Gall
Publié dans: IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, Page(s) 8365-8374
Éditeur: IEEE

Uncertainty-Aware Anticipation of Activities

Auteurs: Yazan Abu Farha, Juergen Gall
Publié dans: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019, Page(s) 1197-1204, ISBN 978-1-7281-5023-9
Éditeur: IEEE
DOI: 10.1109/iccvw.2019.00151

Human Motion Prediction via Spatio-Temporal Inpainting

Auteurs: Alejandro Hernandez, Jurgen Gall, Francesc Moreno
Publié dans: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019, Page(s) 7133-7142, ISBN 978-1-7281-4803-8
Éditeur: IEEE
DOI: 10.1109/iccv.2019.00723

Self-supervised Keypoint Correspondences for Multi-person Pose Estimation and Tracking in Videos

Auteurs: Umer Rafi, Andreas Doering, Bastian Leibe, Juergen Gall
Publié dans: Computer Vision – ECCV 2020 - 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Numéro 12365, 2020, Page(s) 36-52, ISBN 978-3-030-58565-5
Éditeur: Springer
DOI: 10.1007/978-3-030-58565-5_3

Recurrent Residual Learning for Action Recognition

Auteurs: Ahsan Iqbal, Alexander Richard, Hilde Kuehne, Juergen Gall
Publié dans: German Conference on Pattern Recognition, 2017, Page(s) 126-137
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-66709-6_11

Weakly Supervised Action Learning with RNN Based Fine-to-Coarse Modeling

Auteurs: Alexander Richard, Hilde Kuehne, Juergen Gall
Publié dans: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Page(s) 1273-1282, ISBN 978-1-5386-0457-1
Éditeur: IEEE
DOI: 10.1109/cvpr.2017.140

PoseTrack: Joint Multi-person Pose Estimation and Tracking

Auteurs: Umar Iqbal, Anton Milan, Juergen Gall
Publié dans: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Page(s) 4654-4663, ISBN 978-1-5386-0457-1
Éditeur: IEEE
DOI: 10.1109/cvpr.2017.495

Pose for Action - Action for Pose

Auteurs: Umar Iqbal, Martin Garbade, Juergen Gall
Publié dans: 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017), 2017, Page(s) 438-445, ISBN 978-1-5090-4023-0
Éditeur: IEEE
DOI: 10.1109/fg.2017.61

Open Set Domain Adaptation

Auteurs: Pau Panareda Busto, Juergen Gall
Publié dans: 2017 IEEE International Conference on Computer Vision (ICCV), 2017, Page(s) 754-763, ISBN 978-1-5386-1032-9
Éditeur: IEEE
DOI: 10.1109/iccv.2017.88

PoseTrack: A Benchmark for Human Pose Estimation and Tracking

Auteurs: Mykhaylo Andriluka, Umar Iqbal, Eldar Insafutdinov, Leonid Pishchulin, Anton Milan, Juergen Gall, Bernt Schiele
Publié dans: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, Page(s) 5167-5176, ISBN 978-1-5386-6420-9
Éditeur: IEEE
DOI: 10.1109/cvpr.2018.00542

Action Sets: Weakly Supervised Action Segmentation Without Ordering Constraints

Auteurs: Alexander Richard, Hilde Kuehne, Juergen Gall
Publié dans: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, Page(s) 5987-5996, ISBN 978-1-5386-6420-9
Éditeur: IEEE
DOI: 10.1109/cvpr.2018.00627

When will you do what? - Anticipating Temporal Occurrences of Activities

Auteurs: Yazan Abu Farha, Alexander Richard, Juergen Gall
Publié dans: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, Page(s) 5343-5352, ISBN 978-1-5386-6420-9
Éditeur: IEEE
DOI: 10.1109/cvpr.2018.00560

NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning

Auteurs: Alexander Richard, Hilde Kuehne, Ahsan Iqbal, Juergen Gall
Publié dans: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, Page(s) 7386-7395, ISBN 978-1-5386-6420-9
Éditeur: IEEE
DOI: 10.1109/cvpr.2018.00771

Direct Shot Correspondence Matching

Auteurs: Umer Rafi, Juergen Gall, Bastian Leibe
Publié dans: British Machine Vision Conference, 2018
Éditeur: BMVA

JointFlow: Temporal Flow Fields for Multi Person Pose Estimation

Auteurs: Andreas Doering, Umar Iqbal, Juergen Gall
Publié dans: British Machine Vision Conference, 2018
Éditeur: BMVA

Convolutional Simplex Projection Network for Weakly Supervised Semantic Segmentation

Auteurs: Rania Briq, Michael Moeller, Juergen Gall
Publié dans: British Machine Vision Conference, 2018
Éditeur: BMVA

Structural Recurrent Neural Network (SRNN) for Group Activity Analysis

Auteurs: Sovan Biswas, Juergen Gall
Publié dans: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018, Page(s) 1625-1632, ISBN 978-1-5386-4886-5
Éditeur: IEEE
DOI: 10.1109/wacv.2018.00180

An Efficient Convolutional Network for Human Pose Estimation

Auteurs: Umer Rafi, Ilya Kostrikov, Juergen Gall, Bastian Leibe
Publié dans: British Machine Vision Conference, 2016
Éditeur: BMVA Press

Handcrafting vs Deep Learning: An Evaluation of NTraj+ Features for Pose Based Action Recognition

Auteurs: Martin Garbade, Juergen Gall
Publié dans: Workshop New Challenges in Neural Computation, 2016
Éditeur: Thomas Villmann, Frank-Michael Schleif

SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation

Auteurs: Mohsen Fayyaz, Jurgen Gall
Publié dans: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, Page(s) 498-507, ISBN 978-1-7281-7168-5
Éditeur: IEEE
DOI: 10.1109/cvpr42600.2020.00058

Hierarchical Graph-Rnns for Action Detection of Multiple Activities

Auteurs: Sovan Biswas, Yaser Souri, Juergen Gall
Publié dans: 2019 IEEE International Conference on Image Processing (ICIP), 2019, Page(s) 1-5, ISBN 978-1-5386-6249-6
Éditeur: IEEE
DOI: 10.1109/icip.2019.8803650

You Only Need Adversarial Supervision for Semantic Image Synthesis

Auteurs: Edgar Schönfeld, Vadim Sushko, Dan Zhang, Juergen Gall, Bernt Schiele, Anna Khoreva
Publié dans: International Conference on Learning Representations, 2021
Éditeur: OpenReview.net

Unsupervised Video Representation Learning by Bidirectional Feature Prediction

Auteurs: Nadine Behrmann, Juergen Gall, Mehdi Noroozi
Publié dans: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), 2021, Page(s) 1669-1678, ISBN 978-1-6654-0477-8
Éditeur: IEEE
DOI: 10.1109/wacv48630.2021.00171

What Object Should I Use? - Task Driven Object Detection

Auteurs: Johann Sawatzky, Yaser Souri, Christian Grund, Jurgen Gall
Publié dans: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, Page(s) 7597-7606, ISBN 978-1-7281-3293-8
Éditeur: IEEE
DOI: 10.1109/cvpr.2019.00779

Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos

Auteurs: Olga Zatsarynna, Yazan Abu Farha, Juergen Gall
Publié dans: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021
Éditeur: IEEE

Enhancing Temporal Action Localization with Transfer Learning from Action Recognition

Auteurs: Ahsan Iqbal, Alexander Richard, Juergen Gall
Publié dans: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019, Page(s) 1533-1540, ISBN 978-1-7281-5023-9
Éditeur: IEEE
DOI: 10.1109/iccvw.2019.00191

Cross-Modal Knowledge Distillation for Action Recognition

Auteurs: Fida Mohammad Thoker, Juergen Gall
Publié dans: 2019 IEEE International Conference on Image Processing (ICIP), 2019, Page(s) 6-10, ISBN 978-1-5386-6249-6
Éditeur: IEEE
DOI: 10.1109/icip.2019.8802909

Unsupervised Learning of Action Classes With Continuous Temporal Embedding

Auteurs: Anna Kukleva, Hilde Kuehne, Fadime Sener, Jurgen Gall
Publié dans: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, Page(s) 12058-12066, ISBN 978-1-7281-3293-8
Éditeur: IEEE
DOI: 10.1109/cvpr.2019.01234

Large Scale Holistic Video Understanding

Auteurs: Ali Diba, Mohsen Fayyaz, Vivek Sharma, Manohar Paluri, Jürgen Gall, Rainer Stiefelhagen, Luc Van Gool
Publié dans: Computer Vision – ECCV 2020 - 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part V, Numéro 12350, 2020, Page(s) 593-610, ISBN 978-3-030-58557-0
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-58558-7_35

3D CNNs With Adaptive Temporal Feature Resolutions

Auteurs: Mohsen Fayyaz, Emad Bahrami, Ali Diba, Mehdi Noroozi, Ehsan Adeli, Luc Van Gool, Jurgen Gall
Publié dans: IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, Page(s) 4731-4740
Éditeur: IEEE

Harvesting Information from Captions for Weakly Supervised Semantic Segmentation

Auteurs: Johann Sawatzky, Debayan Banerjee, Juergen Gall
Publié dans: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019, Page(s) 4481-4490, ISBN 978-1-7281-5023-9
Éditeur: IEEE
DOI: 10.1109/iccvw.2019.00549

MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation

Auteurs: Shi-Jie Li, Yazan AbuFarha, Yun Liu, Ming-Ming Cheng, Juergen Gall
Publié dans: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, Page(s) 1-1, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2020.3021756

Open Set Domain Adaptation for Image and Action Recognition

Auteurs: Pau Panareda Busto, Ahsan Iqbal, Juergen Gall
Publié dans: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numéro 42/2, 2020, Page(s) 413-429, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2018.2880750

A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation

Auteurs: Hilde Kuehne, Alexander Richard, Juergen Gall
Publié dans: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numéro 42/4, 2020, Page(s) 765-779, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2018.2884469

Weakly supervised learning of actions from transcripts

Auteurs: Hilde Kuehne, Alexander Richard, Juergen Gall
Publié dans: Computer Vision and Image Understanding, Numéro 163, 2017, Page(s) 78-89, ISSN 1077-3142
Éditeur: Academic Press
DOI: 10.1016/j.cviu.2017.06.004

A bag-of-words equivalent recurrent neural network for action recognition

Auteurs: Alexander Richard, Juergen Gall
Publié dans: Computer Vision and Image Understanding, Numéro 156, 2017, Page(s) 79-91, ISSN 1077-3142
Éditeur: Academic Press
DOI: 10.1016/j.cviu.2016.10.014

A dual-source approach for 3D human pose estimation from single images

Auteurs: Umar Iqbal, Andreas Doering, Hashim Yasin, Björn Krüger, Andreas Weber, Juergen Gall
Publié dans: Computer Vision and Image Understanding, Numéro 172, 2018, Page(s) 37-49, ISSN 1077-3142
Éditeur: Academic Press
DOI: 10.1016/j.cviu.2018.03.007

Fast Weakly Supervised Action Segmentation Using Mutual Consistency

Auteurs: Yaser Souri, Mohsen Fayyaz, Luca Minciullo, Gianpiero Francesca, Juergen Gall
Publié dans: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, Page(s) 1-1, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2021.3089127

Pose Refinement Graph Convolutional Network for Skeleton-Based Action Recognition

Auteurs: Shijie Li, Jinhui Yi, Yazan Abu Farha, Juergen Gall
Publié dans: IEEE Robotics and Automation Letters, Numéro 6/2, 2021, Page(s) 1028-1035, ISSN 2377-3766
Éditeur: IEEE
DOI: 10.1109/lra.2021.3056361

Publications

Partager cette page

Télécharger