Our paper "CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relations" won the Best Paper Award at the 3rd Workshop on Scene Graphs and Graph Representation Learning (SG2RL).

This workshop took place as part of this year's ICCV 2025 in Honolulu, Hawaii.

The paper "Towards Practical Multi-label Causal Discovery in High-Dimensional Event Sequences via One-Shot Graph Aggregation" by Hugo Math and Rainer Lienhart has been accepted at the "SPIGM: Structural Probabilistic Inference and Generative Modeling" workshop. The workshop will take place in December 2025 as part of NeuRIPS 2025 in San Diego.

The paper "One-Shot Multi-Label Causal Discovery in High-Dimensional Event Sequences" by Hugo Math, Robin Schön, and Rainer Lienhart has been accepted at the "Workshop on CauScien: Discovering Causality in Science." The workshop will take place in December 2025 as part of NeuRIPS 2025 in San Diego.

A paper titled "MMMS: Multi-Modal Multi-Surface Interactive Segmentation" by Robin Schön, Julian Lorenz, Katja Ludwig, Daniel Kienzle, and Rainer Lienhart has been accepted at the "2025 IEEE International Conference on Content-Based Multimedia Indexing (IEEE CBMI)." The conference will take place in October 2025 in Dublin, Ireland. 

We are pleased to announce that our research has been highlighted in Episode 5 of the SportsAI Podcast. In this episode, the hosts discuss their favorite papers from the recent CVPR conference, and we are happy for this recognition of our work.

Our paper "On the Importance of Conditioning for Privacy-Preserving Data Augmentation" by Julian Lorenz, Katja Ludwig, Valentin Haug, and Rainer Lienhart has been accepted to the Workshop on Safe and Trustworthy Multimodal AI Systems (SafeMM-AI) at the International Conference on Computer Vision 2025 and our paper has been selected for an oral presentation at the conference by the reviewers.

 

Our paper "CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relations" by Julian Lorenz, Mrunmai Phatak, Robin Schön, Katja Ludwig, Nico Hörmann, Annemarie Friedrich, and Rainer Lienhart has been accepted to the 3rd Workshop on Scene Graphs and Graph Representation Learning (SG2RL) at the International Conference on Computer Vision 2025.

The Paper "HOIverse: A Synthetic Scene Graph Dataset With Human Object Interactions" by Mrunmai Vivek Phatak, Julian Lorenz, Nico Hörmann, Jörg Hähner and Rainer Lienhart has been accepted on IEEE 8^th International Conference on Multimedia Information Processing and Retrieval (IEEE MIPR 2025).

 

Our paper "Towards Ball Spin and Trajectory Analysis in Table Tennis Broadcast Videos via Physically Grounded Synthetic-to-Real Transfer" won the Best Paper Award at the 11th International Workshop on Computer Vision in Sports (CVsports)  This workshop took place as part of this year's CVPR 2025 in Nashville, Tennessee.

Congratulations to Katja Ludwig on the successful defense of her dissertation: Human Pose Estimation in Images and Videos for Sports Analytics: 2D Keypoint and 3D Mesh Estimation for Challenging Scenarios and Extreme Poses.

Two papers are accepted at CVsports@CVPR 2025: "Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes" by Katja Ludwig, Julian Lorenz, Daniel Kienzle, Tuan Bui & Rainer Lienhart as well as "
Efficient 2D to Full 3D Human Pose Uplifting including Joint Rotations" by Katja Ludwig, Yuliia Oksymets, et al.

The paper "Towards Ball Spin and Trajectory Analysis in Table Tennis Broadcast Videos via Physically Grounded Synthetic-to-Real Transfer" by Daniel Kienzle, Robin Schön, Rainer Lienhart, and Shin’Ichi Satoh has been accepted to the CVSports Workshop, held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).