Learning to Train with Synthetic Humans

David T. Hoffmann, Dimitrios Tzionas, Micheal J. Black +1

The paper investigates using synthetic human images to train multi‑person 2D pose estimation models, compares purely synthetic versus real data augmented with synthetic humans, and…

Local Temporal Bilinear Pooling for Fine-grained Action Parsing

Yan Zhang, Siyu Tang, Krikamol Muandet +2

Temporal Human Action Segmentation via Dynamic Clustering

Yan Zhang, He Sun, Siyu Tang +1

End-to-end Learning for Graph Decomposition

Jie Song, Bjoern Andres, Michael Black +2

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

Leonid Pishchulin, Eldar Insafutdinov, Siyu Tang +4

ArtTrack: Articulated Multi-person Tracking in the Wild

Eldar Insafutdinov, Mykhaylo Andriluka, Leonid Pishchulin +4

Generating Descriptions with Grounded and Co-Referenced People

Anna Rohrbach, Marcus Rohrbach, Siyu Tang +2

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

Margret Keuper, Siyu Tang, Yu Zhongjie +3

Part-Aligned Bilinear Representations for Person Re-identification

Yumin Suh, Jingdong Wang, Siyu Tang +2

Gossip-based Search in Multipeer Communication Networks

Eva Jaho, Ioannis Koukoutsidis, Siyu Tang +2

Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications

Evgeny Levinkov, Jonas Uhrig, Siyu Tang +7

Are Friends Overrated? A Study for the Social News Aggregator Digg.com

Christian Doerr, Norbert Blenn, Siyu Tang +1

Multi-Person Tracking by Multicut and Deep Matching

Siyu Tang, Bjoern Andres, Mykhaylo Andriluka +1