Siyu Tang

Research Group Leader

Perceiving Systems

Office: N3.009
Max-Planck-Ring 4
72076 Tübingen
Germany

I am leading the Holistic Vision Group (HVG) in the Department of Perceiving Systems at the Max Planck Institute for Intelligent Systems, my group is funded by the DFG through the CRC 1233 on Robust Vision.

I am interested in the intersection between computer vision and machine learning with a focus on holistic visual scene understanding. In particular, I am interested in analyzing and modeling people in our complex visual scenes.

Offers: I am looking for highly motivated PhD student and PhD interns. I also have projects for bachelor and master thesis. If you are interested, please contact me direclty or send your application to ps-apply@tuebingen.mpg.de

I was a postdoctoral researcher at the Max Planck Institute for Intelligent Systems, advised by Michael Black. I finished my PhD summa cum laude at the Max Planck Institute for Informatics, under the supervision of Prof. Bernt Schiele. Before that, I received Master degree in Computer Science at RWTH Aachen University, advised by Prof. Bastian Leibe and Bachelor degree in Computer Science and Technology Department at Zhejiang University, China. I was a research intern at National Institute of Informatics, under the supervision of Prof. Helmut Prendinger.

News:

New! We have one paper accepted to ECCV 2018, details coming soon.
New! We have one paper accepted to BMVC 2018, details coming soon.
Our work on part-aligned bilinear representations for person re-identification is online.
Our work on human action segmentation in real time is online, and the code is available.
I will be an area chair for ACCV 2018.
I received an Early career research grant to start my own research group at the Max Planck Instiute for Intelligent Systems and the University of Tübingen, details coming soon. I am looking for highly motivated PhD student and PhD interns!
I have successfully defended my PhD thesis "People Detection and Tracking in Crowded Scenes" on the 29th September 2017 at the Max Planck Institute for Informatics. Thesis Committee: Prof. Bernt Schiele, Prof. Michael Black, Prof. Luc Van Gool.
Winner of the CVPR 2017 Multi-Object Tracking Challenge (MOT17).
Four papers accepted at CVPR 2017!

Awards:

Winner of the Multi-Object Tracking Challenge at CVPR 2017
Winner of the Multi-Object Tracking Challenge at ECCV 2016
BMVC Best Paper Award, 2012
Scholarship for excellence in academic performance RWTH Aachen 2009, 2010

Teaching:

SS 2016: High-Level Computer Vision, Saarland University, teaching assistant
SS 2015: High-Level Computer Vision, Saarland University, teaching assistant
SS 2013: High-Level Computer Vision, Saarland University, teaching assistant

Reviewing:

IJCV, TPAMI

CVPR 2016, ECCV 2016,

CVPR 2017, ICCV 2017, NIPS 2017, ICML 2017.

Current Master Student

David Hoffmann

April 2018 - present

Past Visitor

Jie Song

June 2017 - December 2017

16 results (View BibTeX file of all listed publications)

2018

Part-Aligned Bilinear Representations for Person Re-identification

Suh, Y., Wang, J., Tang, S., Mei, T., Lee, K. M.

European Conference on Computer Vision (ECCV), September 2018 (conference)

Abstract

Comparing the appearance of corresponding body parts is essential for person re-identification. However, body parts are frequently misaligned be- tween detected boxes, due to the detection errors and the pose/viewpoint changes. In this paper, we propose a network that learns a part-aligned representation for person re-identification. Our model consists of a two-stream network, which gen- erates appearance and body part feature maps respectively, and a bilinear-pooling layer that fuses two feature maps to an image descriptor. We show that it results in a compact descriptor, where the inner product between two image descriptors is equivalent to an aggregation of the local appearance similarities of the cor- responding body parts, and thereby significantly reduces the part misalignment problem. Our approach is advantageous over other pose-guided representations by learning part descriptors optimal for person re-identification. Training the net- work does not require any part annotation on the person re-identification dataset. Instead, we simply initialize the part sub-stream using a pre-trained sub-network of an existing pose estimation network and train the whole network to minimize the re-identification loss. We validate the effectiveness of our approach by demon- strating its superiority over the state-of-the-art methods on the standard bench- mark datasets including Market-1501, CUHK03, CUHK01 and DukeMTMC, and standard video dataset MARS.

pdf supplementary [BibTex]

2018

Suh, Y., Wang, J., Tang, S., Mei, T., Lee, K. M. Part-Aligned Bilinear Representations for Person Re-identification European Conference on Computer Vision (ECCV), September 2018 (conference)

pdf supplementary [BibTex]

Human Motion Parsing by Hierarchical Dynamic Clustering

Zhang, Y., Tang, S., Sun, H., Neumann, H.

British Machine Vision Conference, September 2018 (conference)

Abstract

Parsing continuous human motion into meaningful segments plays an essential role in various applications. In this work, we propose a hierarchical dynamic clustering framework to derive action clusters from a sequence of local features in an unsuper- vised bottom-up manner. We systematically investigate the modules in this framework and particularly propose diverse temporal pooling schemes, in order to realize accurate temporal action localization. We demonstrate our method on two motion parsing tasks: temporal action segmentation and abnormal behavior detection. The experimental results indicate that the proposed framework is significantly more effective than the other related state-of-the-art methods on several datasets.

pdf [BibTex]

Zhang, Y., Tang, S., Sun, H., Neumann, H. Human Motion Parsing by Hierarchical Dynamic Clustering British Machine Vision Conference, September 2018 (conference)

pdf [BibTex]

Temporal Human Action Segmentation via Dynamic Clustering

Zhang, Y., Sun, H., Tang, S., Neumann, H.

arXiv preprint arXiv:1803.05790, 2018 (article)

Abstract

We present an effective dynamic clustering algorithm for the task of temporal human action segmentation, which has comprehensive applications such as robotics, motion analysis, and patient monitoring. Our proposed algorithm is unsupervised, fast, generic to process various types of features, and applica- ble in both the online and offline settings. We perform extensive experiments of processing data streams, and show that our algorithm achieves the state-of- the-art results for both online and offline settings.

link (url) [BibTex]

Zhang, Y., Sun, H., Tang, S., Neumann, H. Temporal Human Action Segmentation via Dynamic Clustering arXiv preprint arXiv:1803.05790, 2018 (article)

link (url) [BibTex]

2017

Joint Graph Decomposition and Node Labeling by Local Search

Levinkov, E., Uhrig, J., Tang, S., Omran, M., Insafutdinov, E., Kirillov, A., Rother, C., Brox, T., Schiele, B., Andres, B.

Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (conference)

PDF Supplementary [BibTex]

2017

Levinkov, E., Uhrig, J., Tang, S., Omran, M., Insafutdinov, E., Kirillov, A., Rother, C., Brox, T., Schiele, B., Andres, B. Joint Graph Decomposition and Node Labeling by Local Search Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (conference)

PDF Supplementary [BibTex]

Articulated Multi-person Tracking in the Wild

Insafutdinov, E., Andriluka, M., Pishchulin, L., Tang, S., Levinkov, E., Andres, B., Schiele, B.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017, Oral (inproceedings)

[BibTex]

Insafutdinov, E., Andriluka, M., Pishchulin, L., Tang, S., Levinkov, E., Andres, B., Schiele, B. Articulated Multi-person Tracking in the Wild In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017, Oral (inproceedings)

[BibTex]

Multi People Tracking with Lifted Multicut and Person Re-identification

Tang, S., Andriluka, M., Andres, B., Schiele, B.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

[BibTex]

Tang, S., Andriluka, M., Andres, B., Schiele, B. Multi People Tracking with Lifted Multicut and Person Re-identification In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

[BibTex]

Generating Descriptions with Grounded and Co-Referenced People

Rohrbach, A., Rohrbach, M., Tang, S., Oh, S. J., Schiele, B.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

PDF [BibTex]

Rohrbach, A., Rohrbach, M., Tang, S., Oh, S. J., Schiele, B. Generating Descriptions with Grounded and Co-Referenced People In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

PDF [BibTex]

2016

DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation

Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P., Schiele, B.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2016 (inproceedings)

Abstract

This paper considers the task of articulated human pose estimation of multiple people in real-world images. We propose an approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene, identifies occluded body parts, and disambiguates body parts between people in close proximity of each other. This joint formulation is in contrast to previous strategies, that address the problem by first detecting people and subsequently estimating their body pose. We propose a partitioning and labeling formulation of a set of body-part hypotheses generated with CNN-based part detectors. Our formulation, an instance of an integer linear program, implicitly performs non-maximum suppression on the set of part candidates and groups them to form configurations of body parts respecting geometric and appearance constraints. Experiments on four different datasets demonstrate state-of-the-art results for both single person and multi person pose estimation.

code pdf supplementary [BibTex]

2016

Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P., Schiele, B. DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2016 (inproceedings)

code pdf supplementary [BibTex]

Multi-Person Tracking by Multicuts and Deep Matching

(Winner of the Multi-Object Tracking Challenge ECCV 2016)

Tang, S., Andres, B., Andriluka, M., Schiele, B.

ECCV Workshop on Benchmarking Mutliple Object Tracking, 2016 (conference)

PDF [BibTex]

Tang, S., Andres, B., Andriluka, M., Schiele, B. Multi-Person Tracking by Multicuts and Deep Matching ECCV Workshop on Benchmarking Mutliple Object Tracking, 2016 (conference)

PDF [BibTex]

A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects

Keuper, M., Tang, S., Yu, Z., Andres, B., Brox, T., Schiele, B.

In arXiv:1607.06317, 2016 (inproceedings)

PDF [BibTex]

Keuper, M., Tang, S., Yu, Z., Andres, B., Brox, T., Schiele, B. A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects In arXiv:1607.06317, 2016 (inproceedings)

PDF [BibTex]

2015

Subgraph decomposition for multi-target tracking

Tang, S., Andres, B., Andriluka, M., Schiele, B.

In CVPR, 2015 (inproceedings)

PDF Proof-of-Lemma-1 [BibTex]

2015

Tang, S., Andres, B., Andriluka, M., Schiele, B. Subgraph decomposition for multi-target tracking In CVPR, 2015 (inproceedings)

PDF Proof-of-Lemma-1 [BibTex]

2014

Learning People Detectors for Tracking in Crowded Scenes.

Tang, S., Andriluka, M., Milan, A., Schindler, K., Roth, S., Schiele, B.

2014, Scene Understanding Workshop (SUNw, CVPR workshop) (unpublished)

[BibTex]

2014

Tang, S., Andriluka, M., Milan, A., Schindler, K., Roth, S., Schiele, B. Learning People Detectors for Tracking in Crowded Scenes. 2014, Scene Understanding Workshop (SUNw, CVPR workshop) (unpublished)

[BibTex]

Detection and Tracking of Occluded People

Tang, S., Andriluka, M., Schiele, B.

IJCV, 2014 (article)

PDF [BibTex]

Tang, S., Andriluka, M., Schiele, B. Detection and Tracking of Occluded People IJCV, 2014 (article)

PDF [BibTex]

2013

Learning People Detectors for Tracking in Crowded Scenes

Tang, S., Andriluka, M., Milan, A., Schindler, K., Roth, S., Schiele, B.

In ICCV, 2013 (inproceedings)

PDF [BibTex]

2013

Tang, S., Andriluka, M., Milan, A., Schindler, K., Roth, S., Schiele, B. Learning People Detectors for Tracking in Crowded Scenes In ICCV, 2013 (inproceedings)

PDF [BibTex]

2012

Detection and Tracking of Occluded People

(Best Paper Award)

Tang, S., Andriluka, M., Schiele, B.

In British Machine Vision Conference (BMVC), 2012, BMVC Best Paper Award (inproceedings)

PDF [BibTex]

2012

Tang, S., Andriluka, M., Schiele, B. Detection and Tracking of Occluded People In British Machine Vision Conference (BMVC), 2012, BMVC Best Paper Award (inproceedings)

PDF [BibTex]

2011

OpenBioSafetyLab: A virtual world based biosafety training application for medical students

Nakasone, A., Tang, S., Shigematsu, M., Heinecke, B., Fujimoto, S., Prendinger, H.

In International Conference on Information Technology: New Generations (ITNG), IEEE CPS, 2011 (inproceedings)

PDF [BibTex]

2011

Nakasone, A., Tang, S., Shigematsu, M., Heinecke, B., Fujimoto, S., Prendinger, H. OpenBioSafetyLab: A virtual world based biosafety training application for medical students In International Conference on Information Technology: New Generations (ITNG), IEEE CPS, 2011 (inproceedings)

PDF [BibTex]

Siyu Tang

News:

Awards:

Teaching:

Reviewing:

Current Master Student

Past Visitor

2018

2018

2017

2017

2016

2016

2015

2015

2014

2014

2013

2013

2012

2012

2011

2011

Latest News

Links

Contact Us