JULAIN-Journal-Club.md

@@ -44,13 +44,36 @@ tbd
 
 ## Next Meeting
 
+
+
+### 17 October 2022  
+
+* on-site: INM Seminar room building 15.9, room 4001b
+* remote: https://zoom.us/j/92267844792?pwd=Um5wdmk1dlhiNVYweDNNNVc4MmwvQT09
+
+Meeting ID: 922 6784 4792
+Passcode: 265985
+
+### Relationformer: A Unified Framework for Image-to-Graph Generation 
+
+Suprosanna Shit, Image-Based Biomedical Modeling Group (IBBM), TU Munich
+
+**Abstract**<br>
+Segmenting tubular structure is a recurring problem in medicine, biology, and remote sensing. Image segmentation serves as an intermediate representation of the task at hand, which broadly deals with the underlying network structure or structural graph. For example, vessel networks for medicine, and neuronal networks in biology, heavily rely on segmentation, and correct network topology is often of paramount interest. However, the traditional loss function gives equal weightage to false positives and false negatives pixels, irrespective of its importance in preserving the topological structure during segmentation. Finding an efficient loss to enforce topological correctness is the central theme of this talk. In an alternative direction, one can ask the following research question: Can we directly infer the underlying graph representation without an explicit segmentation stage? If so, how far can we go? Notably, graph extraction from an image is a relatively new field of research and mainly involves semantic knowledge graphs, i.e., scene-graph extraction from natural images. Can we merge these two parallel endeavors under a single framework? Moreover, can we benefit from translating image-to-graph models from the scene-graph community to structural graph extraction? This question will lead to the second part of the talk.
+
+#### Papers
+* **Relationformer: A Unified Framework for Image-to-Graph Generation** <br>
+Suprosanna Shit, Rajat Koner, Bastian Wittmann, Johannes Paetzold, Ivan Ezhov, Hongwei Li, Jiazhen Pan, Sahand Sharifzadeh, Georgios Kaissis, Volker Tresp, Bjoern Menze
+* [[paper](https://arxiv.org/abs/2203.10202)]
+* [[clDice-a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://scholar.google.co.in/citations?view_op=view_citation&hl=en&user=WhAMNrcAAAAJ&citation_for_view=WhAMNrcAAAAJ:4OULZ7Gr8RgC)]
+
+**Invitation and moderation**: Hanno Scharr
+
+## Past Meetings
+
 ### 19 September 2022  
 
 **Hybrid format**
-* on-site: INM Seminar room building 15.9, room 4001b
-* remote: https://zoom.us/j/99172632590?pwd=SndGMlYrTlB6SHNWV3BZME1FbmljUT09<br>
-Meeting ID: 991 7263 2590<br>
-Passcode: 399760
 
 #### Domain Adaptation and Generalisation of Image Segmentation with Semantic Equivariance
 
@@ -67,20 +90,6 @@ arXiv preprint
 
 **Invitation and moderation**: Hanno Scharr
 
-### 17 October 2022  
-
-Virtual Meeting using [BigBlueButton](https://webconf.fz-juelich.de/b/wen-mym-pj7)
-
-* **Relationformer: A Unified Framework for Image-to-Graph Generation** <br>
-Suprosanna Shit, Rajat Koner, Bastian Wittmann, Johannes Paetzold, Ivan Ezhov, Hongwei Li, Jiazhen Pan, Sahand Sharifzadeh, Georgios Kaissis, Volker Tresp, Bjoern Menze
-* [[paper](https://arxiv.org/abs/2203.10202)]
-* [[clDice-a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://scholar.google.co.in/citations?view_op=view_citation&hl=en&user=WhAMNrcAAAAJ&citation_for_view=WhAMNrcAAAAJ:4OULZ7Gr8RgC)]
-* Speaker: Suprosanna Shit
-* Invitation: Hanno Scharr
-* Moderation: tbd
-
-## Past Meetings
-
 ### 20 June 2022  
 
 * **Hopfield Networks is All You Need** <br>
@@ -457,4 +466,4 @@ A training schedule using filter pruning and orthogonal reinitialization
 
 
 ---
-last change: 7.9.2022 sw
\ No newline at end of file
+last change: 13.10.2022 sw
\ No newline at end of file