Papers

We will hold both oral and poster sessions. The accepted papers and their corresponding time slots are as follows.

Oral Session 1
14th September

Interactive Learning of Intrinsic and Extrinsic Properties for All-Day Semantic Segmentation

Qi Bi (University of Amsterdam)*; Shaodi You (University of Amsterdam); Theo Gevers (University of Amsterdam)

GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields

Alessandro Ruzzi (ETH Zürich); Xiangwei Shi (Delft University of Technology)*; Xi Wang (ETH Zürich); Gengyan Li (ETH Zürich); Shalini De Mello (NVIDIA); Hyung Jin Chang (University of Birmingham); Xucong Zhang (Delft University of Technology); Otmar Hilliges (ETH Zürich)

Data-efficient Large Scale Place Recognition with Graded Similarity Supervision

María Leyva-Vallina (University of Groningen); Nicola Strisciuglio (University of Twente)*; Nicolai Petkov (University of Groningen)

Noise Reduction in CT Using Learned Wavelet-Frame Shrinkage Networks

Luis Albert Zavala Mondragon (Eindhoven University of Technology)*; Javier Oliván Bescós (Philips); Peter Rongen ((Former) Philips); P. H. N. de With (Eindhoven University of Technology); Fons van der Sommen (Dept. Electrical Engineering, Eindhoven University of Technology, Eindhoven, NL)

3D Human Pose Estimation via Intuitive Physics
Shashank Tripathi (MPI-IS); Lea Müller (MPI-IS); Chun-Hao P. Huang, Omid Taheri (MPI-IS); Michael J. Black (MPI-IS); Dimitrios Tzionas (University of Amsterdam)

High-level context representation for emotion recognition in images

Willams Costa (Voxar Labs); Estefania Tavalera (University of Twente)*; Lucas Figueiredo (Voxar Labs, Centro de Informática, Universidade Federal de Pernambuco); Veronica Teichrieb (Voxar Labs, Informatics Center, UFPE)

Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations

Mohammadreza Salehi (University of Amsterdam)*; Cees Snoek (Univ. of Amsterdam); Stratis Gavves (University of Amsterdam); Yuki M Asano (University of Amsterdam)

What do neural networks learn in image classification? A frequency shortcut perspective

Shunxin Wang (University of Twente)*; Raymond Veldhuis (University of Twente); Christoph Brune (University of Twente); Nicola Strisciuglio (University of Twente)

A step towards understanding why classification helps regression

Silvia L Pintea (Delft University of Technology)*; Yancong Lin ( Delft University of Technology); Jouke Dijkstra (Leiden Uiniversity Medical Center); Jan C van Gemert (Delft University of Technology)

Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition

Erkut Akdag (Eindhoven University of Technology)*; Zeqi Zhu (Eindhoven University of Technology); Egor Bondarev (TU Eindhoven); P. H. N. de With (Eindhoven University of Technology)

Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization

Fida Mohammad Thoker (University of Amsterdam)*; Hazel Doughty (Leiden University); Cees Snoek (University of Amsterdam)

SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation

Zimin Xia (Delft University of Technology)*; Ted Lentsch (Delft University of Technology); Holger Caesar (Delft University of Technology); Julian F P Kooij (Delft University of Technology)

Relational Prior Knowledge Graphs for Detection and Instance Segmentation
Osman Ülger (University of Amsterdam); Yu Wang (TomTom); Ysbrand Galama (TomTom); Sezer Karaoglu (University of Amsterdam); Theo Gevers (University of Amsterdam); Martin R. Oswald (ETH Zurich)

Poster Session 1

14th September

1. Interactive Learning of Intrinsic and Extrinsic Properties for All-Day Semantic Segmentation

Qi Bi (University of Amsterdam); Shaodi You (University of Amsterdam); Theo Gevers (University of Amsterdam)

2. Poincaré ResNet

Max WF van Spengler (University of Amsterdam); Pascal Mettes (University of Amsterdam); Erwin Berkhout (Academic Center for Dentistry Amsterdam (ACTA))

3. A step towards understanding why classification helps regression

Silvia L Pintea (LUMC & Delft University of Technology); Yancong Lin (Delft University of Technology); Jouke Dijkstra (Leiden Uiniversity Medical Center); Jan C van Gemert (Delft University of Technology)

4. Exploring Different Levels of Supervision for Detecting and Localizing Solar Panels on Remote Sensing Imagery

Rob Wijnhoven (Spotr.ai); Maarten Burger (University of Amsterdam); Shaodi You (University of Amsterdam)

5. Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization

Fida Mohammad Thoker (University of Amsterdam); Hazel Doughty (Leiden University); Cees Snoek (University of Amsterdam)

6. Is there progress in activity progress prediction?

Frans de Boer (TU Delft); Jan C van Gemert (Delft University of Technology); Jouke Dijkstra (Leiden Uiniversity Medical Center); Silvia L Pintea (TUDelft)*

7. LAB: Learnable Activation Binarizer for Binary Neural Networks

Sieger Falkena (Shell); Jan C van Gemert (Delft University of Technology); Hadi Jamali-Rad (Shell & TU Delft)

8. Homography Estimation for Camera Calibration in Complex Topological Scenes

Giacomo D'Amicantonio (Eindhoven University of Technology); Egor Bondarev (TU Eindhoven)

9. Data-efficient Large Scale Place Recognition with Graded Similarity Supervision

María Leyva-Vallina (University of Groningen); Nicola Strisciuglio (University of Twente)*; Nicolai Petkov (University of Groningen)

10. Neural Modulation Fields for Conditional Cone Beam Neural Tomography

David M. Knigge (University of Amsterdam); Samuele Papa (University of Amsterdam); Riccardo Valperga (University of Amsterdam); Nikita Moriakov (Netherlands Cancer Institute); Miltiadis Kofinas (University of Amsterdam); Jan-Jakob Sonke (The Netherlands Cancer Institute); Stratis Gavves (University of Amsterdam)

11. The Robustness of Computer Vision Models against Common Corruptions: a Survey — Larger is not Better

Shunxin Wang (University of Twente); Raymond Veldhuis (University of Twente); Christoph Brune (University of Twente); Nicola Strisciuglio (University of Twente)

12. Intrinsic Appearance Decomposition Using Point Cloud Representation
Xiaoyan Xing (University of Amsterdam); Konrad Groh (Bosch); Sezer Karaoglu (University of Amsterdam); Theo Gevers (University of Amsterdam)

13. SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation

Zimin Xia (Delft University of Technology); Ted Lentsch (Delft University of Technology); Holger Caesar (Delft University of Technology); Julian F P Kooij (Delft University of Technology)

14. High-level context representation for emotion recognition in images

Willams Costa (Voxar Labs); Estefania Tavalera (University of Twente); Lucas Figueiredo (Voxar Labs, Centro de Informática, Universidade Federal de Pernambuco); Veronica Teichrieb (Voxar Labs, Informatics Center, UFPE)

15. Noise Reduction in CT Using Learned Wavelet-Frame Shrinkage Networks

Luis Albert Zavala Mondragon (Eindhoven University of Technology); Javier Oliván Bescós (Philips); Peter Rongen ((Former) Philips); P. H. N. de With (Eindhoven University of Technology); Fons van der Sommen (Dept. Electrical Engineering, Eindhoven University of Technology, Eindhoven, NL)

16. Non-Destructive Infield Quality Estimation of Strawberries using Deep Architectures

Cees Jol (Delft University of Technology); Junhan Wen (Delft University of Technology); Jan C van Gemert (Delft University of Technology)

17. Infinite Class Mixup

Thomas Mensink (Google Research); Pascal Mettes (University of Amsterdam)

18. Using and Abusing Equivariance

Tom Edixhoven (Delft University of Technology); Attila Lengyel (Delft University of Technology); Jan C van Gemert (Delft University of Technology)

19. IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting

Tim Schoonbeek (Eindhoven University of Technology); Tim Houben (Eindhoven University of Technology); Hans Onvlee (ASML); P. H. N. de With (Eindhoven University of Technology); Fons van der Sommen (Dept. Electrical Engineering, Eindhoven University of Technology, Eindhoven, NL)

20. GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields

Alessandro Ruzzi (ETH Zürich)*; Xiangwei Shi (Delft University of Technology)*; Xi Wang (TH Zürich); Gengyan Li (TH Zürich); Shalini De Mello (NVIDIA); Hyung Jin Chang (University of Birmingham); Xucong Zhang (Delft University of Technology); Otmar Hilliges (TH Zürich)

21. Clinical features for AI based pancreatic tumor detection

Terese A.E Hellstrom (Eindhoven University of Technology)

22. Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition

Erkut Akdag (Eindhoven University of Technology); Zeqi Zhu (Eindhoven University of Technology); Egor Bondarev (TU Eindhoven); P. H. N. de With (Eindhoven University of Technology)

23. Detecting Objects with Context-Likelihood Graphs and Graph Refinement

Aritra Bhowmik (University of Amsterdam); Yu Wang (TomTom); Nora Baka (Tomtom); Martin R. Oswald (ETH Zurich); Cees Snoek (Univ. of Amsterdam)

24. Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations

Mohammadreza Salehi (University of Amsterdam); Cees Snoek (Univ. of Amsterdam); Stratis Gavves (University of Amsterdam); Yuki M Asano (University of Amsterdam)

25. What do neural networks learn in image classification? A frequency shortcut perspective

Shunxin Wang (University of Twente); Raymond Veldhuis (University of Twente); Christoph Brune (University of Twente); Nicola Strisciuglio (University of Twente)

26. Graph Convolutional Networks for Complex Traffic Scenario Classification
Tobias Hoek (Delft University of Technology); Holger Caesar (Delft University of Technology)

27. 3D Human Pose Estimation via Intuitive Physics
Shashank Tripathi (MPI-IS); Lea Müller (MPI-IS); Chun-Hao P. Huang, Omid Taheri (MPI-IS); Michael J. Black (MPI-IS); Dimitrios Tzionas (University of Amsterdam)

28. Self-Ordering Point Clouds
Pengwan Yang (University of Amsterdam), Cees G. M. Snoek (University of Amsterdam), Yuki M. Asano (University of Amsterdam)

29. Relational Prior Knowledge Graphs for Detection and Instance Segmentation
Osman Ülger (University of Amsterdam); Yu Wang (TomTom); Ysbrand Galama (TomTom); Sezer Karaoglu (University of Amsterdam); Theo Gevers (University of Amsterdam); Martin R. Oswald (ETH Zurich)

30. Hierarchical Explanations for Video Action Recognition
Sadaf Gulshad (University of Amsterdam); Teng Long (University of Amsterdam); Nanne van Noord (University of Amsterdam)

Oral Session 2
15th September

Modelling Long Range Dependencies in ND: From Task-Specific to a General Purpose CNN

David M. Knigge (University of Amsterdam); David W Romero (Vrije Universiteit Amsterdam); Albert Gu (Stanford University); Stratis Gavves (University of Amsterdam); Jakub Tomczak (Vrije Universiteit Amsterdam); Mark Hoogendoorn (Vrije Universiteit Amsterdam); Jan-Jakob Sonke (The Netherlands Cancer Institute)

Transductive Variational Inference for Few-Shot Image Classification

Anuj R Singh (Delft University of Technology); Hadi Jamali-Rad (Shell & TU Delft)

Spatial-Temporal Transformer for Crime Recognition in Surveillance Videos

Kayleigh Boekhoudt (University of Groningen), Estefania Tavalera (University of Twente)

Maximum Class Separation as Inductive Bias in One Matrix

Tejaswi Kasarla (University of Amsterdam); Gertjan Burghouts (TNO); Max WF van Spengler (University of Amsterdam); Elise van der Pol (Microsoft Research AI4Science); Rita Cucchiara (Università di Modena e Reggio Emilia); Pascal Mettes (University of Amsterdam)

Embracing Contact: Detecting Parent-Infant Interactions

Metehan Doyran (Utrecht University); Ronald Poppe (Utrecht University); Albert Ali Salah (Utrecht University)

SSIG: A Visually-Guided Graph Edit Distance for Floor Plan Similarity

Casper van Engelenburg (Delft University of Technology); Seyran Khademi (Delft University of Technology); Jan C van Gemert (Delft University of Technology)

Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories

Thomas Mensink (Google Research), Jasper Uijlings (Google Research), Lluis Castrejon (Google Research), Arushi Goel (University of Edinburgh), Felipe Cadar (Universidade Federal de Minas Gerais), Howard Zhou, Fei Sha (Google Research), André Araujo (Google Research), Vittorio Ferrari (Google Research)

Content-Aware Token Sharing for Efficient Semantic Segmentation With Vision Transformers

Chenyang Lu (Eindhoven University of Technology); Daan de Geus (Eindhoven University of Technology); Gijs Dubbelman (Eindhoven University of Technology)

Objects do not disappear: Video object detection by single-frame object location anticipation

Xin Liu (Delft University of Technology), Fatemeh Karimi Nejadasl (University of Amsterdam)Jan van Gemert (Delft University of Technology)) Olaf Booij (Delft University of Technology), Silvia L. Pintea (Delft University of Technology)

Poster Session 2
15th September

1. Improving multi-object re-identification at night with GAN data augmentation in Dutch cities

Midas Amersfoort (Vrije Universiteit Amsterdam); Michael Dubbeldam (Technolution B.V.); Arnoud Visser (UvA)

2. Maximum Class Separation as Inductive Bias in One Matrix

3. Differentiable Transportation Pruning

Yunqiang Li (TU Delft); Jan C van Gemert (Delft University of Technology); Torsten Hoefler (ETH Zürich); Bert Moons (Qualcomm); Evangelos Eleftheriou (Axelera AI); Bram-Ernst Verhoef (Imec)

4. Understanding weight-magnitude hyperparameters in training binary networks

Joris Quist (TU Delft); Yunqiang Li (TU Delft); Jan C van Gemert (Delft University of Technology)

5. Transductive Variational Inference for Few-Shot Image Classification

Anuj R Singh (Delft University of Technology); Hadi Jamali-Rad (Shell & TU Delft)

6. Geometry-guided Feature Learning and Fusion for Indoor Scene Reconstruction
Ruihong Yin (University of Amsterdam); Sezer Karaoglu (University of Amsterdam); Theo Gevers (University of Amsterdam)

7. Are current long-term video understanding datasets long-term?

Ombretta Strafforello (Delft University of Technology, TNO); Klamer Schutte (TNO); Jan C van Gemert (Delft University of Technology)

8. Benchmarking Data Efficiency and Computational Efficiency of Temporal Action Localization Models

Jan Warchocki (Delft University of Technology); Teodor G Oprescu (Delft University of Technology); Yunhan Wang (Delft University of Technology); Alexandru Damacus (Delft University of Technology); Paul Misterka (TU Delft); Robert-Jan Bruintjes (Delft University of Technology); Attila Lengyel (Delft University of Technology); Ombretta Strafforello (Delft University of Technology, TNO); Jan C van Gemert (Delft University of Technology)

9. Content-Aware Token Sharing for Efficient Semantic Segmentation With Vision Transformers

Chenyang Lu (Eindhoven University of Technology); Daan de Geus (Eindhoven University of Technology)*; Gijs Dubbelman (Eindhoven University of Technology)

10. Spatial-Temporal Transformer for Crime Recognition in Surveillance Videos

Kayleigh Boekhoudt (University of Groningen), Estefania Tavalera (University of Twente)

11. DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency

Azhar Shaikh (Vrije Universiteit); Michael Cochez (Vrije Universiteit Amsterdam); Denis Diachkov (Prime Vision); Michiel de Rijcke (Prime Vision); Sahar Yousefi (Prime Vision)

12. SSIG: A Visually-Guided Graph Edit Distance for Floor Plan Similarity

Casper van Engelenburg (Delft University of Technology)*; Seyran Khademi (Delft University of Technology); Jan C van Gemert (Delft University of Technology)

13. Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN

14. Embracing Contact: Detecting Parent-Infant Interactions

Metehan Doyran (Utrecht University); Ronald Poppe (Utrecht University); Albert Ali Salah (Utrecht University)

15. Offline Tracking with Object Permanence

Xianzhong Liu (Delft University of Technology); Holger Caesar (Delft University of Technology)

16. Cross-modal Scalable Hyperbolic Hierarchical Clustering

Teng Long (University of Amsterdam); Nanne van Noord (University of Amsterdam)

17. Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories

18. APNet: Urban-level Scene Segmentation of Aerial Images and Point Clouds
Weijie Wei (University of Amsterdam); Martin R. Oswald (ETH Zurich); Fatemeh Karimi Nejadasl (TomTom); Theo Gevers (University of Amsterdam)

19. IDTransformer: Transformer for Intrinsic Image Decomposition
Partha Das (University of Amsterdam); Maxime Lucienne Gevers (Concordia University ); Sezer Karaoglu (University of Amsterdam); Theo Gevers (University of Amsterdam)

20. Objects do not disappear: Video object detection by single-frame object location anticipation
Xin Liu (Delft University of Technology), Fatemeh Karimi Nejadasl (University of Amsterdam)

Jan van Gemert (Delft University of Technology)) Olaf Booij (Delft University of Technology), Silvia L. Pintea (Delft University of Technology)