Abstract is missing.
- Utilizing Transformers on OCT Imagery and Metadata for Treatment Response Prediction in Macular Edema PatientsSahar Vahdati, Deepankan Bharathi Nagaraj, Maximilian Bryan, Sobhan Moazemi, Sabine Gründer-Fahrer, Michael Martin 0001. 3-15 [doi]
- Prototype Softmax Cross Entropy: A New Perspective on Softmax Cross EntropyQendrim Bytyqi, Nicola Wolpert, Elmar Schömer, Ulrich Schwanecke. 16-31 [doi]
- Evidential Deep Learning for Class-Incremental Semantic SegmentationKarl Holmquist, Lena Klasén, Michael Felsberg. 32-48 [doi]
- Synthesizing Hard Training Data from Latent Hierarchical RepresentationsBenjamin J. Høj, Andreas Møgelmose. 49-58 [doi]
- Rigidity Preserving Image Transformations and Equivariance in PerspectiveLucas Brynte, Georg Bökman, Axel Flinth, Fredrik Kahl. 59-76 [doi]
- Tangent Phylogenetic PCAMorten Akhøj, Xavier Pennec, Stefan Sommer. 77-90 [doi]
- Deep Simplex Classifier for Maximizing the Margin in Both Euclidean and Angular SpacesHakan Cevikalp, Hasan Saribas. 91-107 [doi]
- Impact of Image Blur on Classification and Augmentation of Deep Convolutional NetworksMatej Lébl, Filip Sroubek, Jan Flusser. 108-117 [doi]
- Gradient Adjusting Networks for Domain InversionErez Sheffi, Michael Rotman, Lior Wolf. 118-137 [doi]
- From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation LearningZhuo Su 0002, Matti Pietikäinen, Li Liu 0002. 138-155 [doi]
- ConvMix: Combining Intermediate Latent Features in Deep Convolutional Neural NetworksMofassir ul Islam Arif, Johannes Burchert, Lars Schmidt-Thieme. 156-174 [doi]
- Fully Variational Noise-Contrastive EstimationChristopher Zach. 175-190 [doi]
- An Analysis of Spatial-Spectral Dependence in Hyperspectral AutoencodersWilliam Michael Laprade, Jesper Cairo Westergaard, Jon Nielsen, Mads Nielsen, Anders Bjorholm Dahl. 191-202 [doi]
- ConvSegFormer - A Convolution Aided SegFormer Architecture for Detection of Discontinuities in Wrapped Interferometric Phase Imagery of Sea IceRohit Venkata Sai Dulam, Emily R. Fedders, Andrew R. Mahoney, Chandra Kambhamettu. 203-213 [doi]
- Introducing Spatial Context in Patch-Based Deep Learning for Semantic Segmentation in Whole Body MRIEva Breznik, Joel Kullberg, Håkan Ahlström, Robin Strand. 214-228 [doi]
- Learning to Pay Attention by Paying Attention - Attention U-Net with Extra Supervision for MRI-based Pseudo-CT SynthesisGurbandurdy Dovletov, Utku Karadeniz, Stefan Lörcks, Josef Pauli, Marcel Gratz, Harald H. Quick. 229-242 [doi]
- Correl-Net: Defect Segmentation in Old Films Using Correlation NetworksArthur Renaudeau, Travis Seng, Axel Carlier, Jean-Denis Durou. 245-259 [doi]
- Non-negative Spherical Relaxations for Universe-Free Multi-matching and ClusteringJohan Thunberg, Florian Bernard. 260-277 [doi]
- A Function Space Perspective on Stochastic Shape EvolutionElizabeth Baker, Thomas Besnier, Stefan Sommer. 278-292 [doi]
- Systematic Augmentation in HSV Space for Semantic Segmentation of Prostate BiopsiesFilip Winzell, Ida Arvidsson, Niels Christian Overgaard, Kalle Åström, Felicia-Elena Marginean, Anders Bjartell, Agnieszka Krzyzanowska, Athanasios Simoulis, Anders Heyden. 293-308 [doi]
- Out-of-Distribution Detection for Adaptive Computer VisionSimon Kristoffersson Lind, Rudolph Triebel, Luigi Nardi, Volker Krüger. 311-325 [doi]
- TAU-Indoors Dataset for Visual and LiDAR Place RecognitionAtakan Dag, Farid Alijani, Jukka Peltomäki, Lauri Suomela, Esa Rahtu, Harry Edelman, Joni-Kristian Kämäräinen. 326-339 [doi]
- Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-MotionZeeshan Khan Suri. 340-353 [doi]
- Varied Realistic Autonomous Vehicle Collision Scenario GenerationMaria Priisalu, Ciprian Paduraru, Cristian Sminchisescu. 354-372 [doi]
- Vessel Bearing Estimation Using Visible and Thermal ImagingAjinkya Gorad, Sakira Hassan, Simo Särkkä. 373-381 [doi]
- Learnable Eulerian Dynamics for Micro-Expression Action Unit DetectionTuomas Varanka, Wei Peng, Guoying Zhao 0001. 385-400 [doi]
- Single-Stage 3D Pose Estimation of Vulnerable Road Users Using Pseudo-LabelsFabian Windbacher, Michael Hödlmoser, Margrit Gelautz. 401-417 [doi]
- TAPE: Temporal Attention-Based Probabilistic Human Pose and Shape EstimationNikolaos Vasilikopoulos, Nikos Kolotouros, Aggeliki Tsoli, Antonis A. Argyros. 418-431 [doi]
- ID2image: Leakage of Non-ID Information into Face Descriptors and Inversion from Descriptors to ImagesMingrui Li, William A. P. Smith, Patrik Huber 0001. 432-448 [doi]
- Robust and Accurate Cylinder TriangulationAnna Gummeson, Magnus Oskarsson. 451-466 [doi]
- MSDA: Monocular Self-supervised Domain Adaptation for 6D Object Pose EstimationDingding Cai, Janne Heikkilä, Esa Rahtu. 467-481 [doi]
- The Multi-view Geometry of Parallel CylindersErik Tegler, Johanna Engman, David Gillsjö, Gabrielle Flood, Viktor Larsson, Magnus Oskarsson, Kalle Åström. 482-499 [doi]
- Exploiting Redundancy for Large Scale Bundle Adjustment: In Partial Defense of Minimization by AlternationChristopher Zach, Huu Le. 500-516 [doi]
- Learning to Estimate Two Dense Depths from LiDAR and Event DataVincent Brebion, Julien Moreau, Franck Davoine. 517-533 [doi]
- Polarimetric Underwater StereoRyo Kawahara, Meng-Yu Jennifer Kuo, Takahiro Okabe. 534-550 [doi]
- BS3D: Building-Scale 3D Reconstruction from RGB-D ImagesJanne Mustaniemi, Juho Kannala, Esa Rahtu, Li Liu 0002, Janne Heikkilä. 551-565 [doi]
- Detection and Pose Estimation of Flat, Texture-Less Industry Objects on HoloLens Using Synthetic TrainingThomas Pöllabauer, Fabian Rücker, Andreas Franek, Felix Gorschlüter. 569-585 [doi]
- Assessing the Feasibility of Remote Photoplethysmography Through Videocalls: A Study of Network and Computing ConstraintsConstantino Álvarez Casado, Le Ngu Nguyen, Olli Silvén, Miguel Bordallo López. 586-598 [doi]
- Anchor-ReID: A Test Time Adaptation for Person Re-identificationMohammed Almansoori, Mustansar Fiaz, Hisham Cholakkal. 599-612 [doi]