Table of Contents

• Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial DetectionPeter Lorenz, Margret Keuper, Janis Keuper. 27-38 [doi]
• DaDe: Delay-Adaptive Detector for Streaming PerceptionWonwoo Jo, Kyungshin Lee, Jaewon Baik, Sang Sun Lee, Dongho Choi, Hyunkyoo Park. 39-46 [doi]
• A Patch-Based Architecture for Multi-Label Classification from Single Positive AnnotationsWarren Jouanneau, Aurélie Bugeau, Marc Palyart, Nicolas Papadakis, Laurent Vézard. 47-58 [doi]
• Human Object Interaction Detection Primed with ContextMaya Antoun, Daniel C. Asmar. 59-68 [doi]
• Absolute-ROMP: Absolute Multi-Person 3D Mesh Prediction from a Single ImageBilal Abdulrahman, Zhigang Zhu. 69-79 [doi]
• Semi-Supervised Domain Adaptation with CycleGAN Guided by Downstream Task AwarenessAnnika Mütze, Matthias Rottmann, Hanno Gottschalk. 80-90 [doi]
• A General Context Learning and Reasoning Framework for Object Detection in Urban ScenesXuan Wang, Hao Tang, Zhigang Zhu. 91-102 [doi]
• Rethinking the Backbone Architecture for Tiny Object DetectionJinlai Ning, Haoyan Guan, Michael W. Spratling. 103-114 [doi]
• Rotation Equivariance for Diamond IdentificationFloris De Feyter, Bram Claes, Toon Goedemé. 115-123 [doi]
• Toward Few Pixel Annotations for 3D Segmentation of Material from Electron TomographyCyril Li, Christophe Ducottet, Sylvain Desroziers, Maxime Moreaud. 124-131 [doi]
• Leveraging Unsupervised and Self-Supervised Learning for Video Anomaly DetectionDevashish Lohani, Carlos Fernando Crispim Junior, Quentin Barthélemy, Sarah Bertrand, Lionel Robinault, Laure Tougne Rodet. 132-143 [doi]
• Visual Anomaly Detection and Localization with a Patch-Wise Transformer and Convolutional ModelAfshin Dini, Esa Rahtu. 144-152 [doi]
• YOLO: You Only Look 10647 TimesChristian Limberg, Andrew Melnik, Helge J. Ritter, Helmut Prendinger. 153-160 [doi]
• On Attribute Aware Open-Set Face VerificationArun Kumar Subramanian, Anoop M. Namboodiri. 161-172 [doi]
• A Lightweight Gaussian-Based Model for Fast Detection and Classification of Moving ObjectsJoaquin Palma-Ugarte, Laura Jovani Estacio Cerquin, Victor Flores-Benites, Rensso Mora Colque. 173-184 [doi]
• Image Generation from a Hyper Scene Graph with Trinomial HyperedgesRyosuke Miyake, Tetsu Matsukawa, Einoshin Suzuki. 185-195 [doi]
• Automatic Defect Detection in LeatherJoão Soares, Luís Magalhães, Rafaela Pinho, Mehrab K. Allahdad, Manuel Ferreira. 196-204 [doi]
• IFMix: Utilizing Intermediate Filtered Images for Domain Adaptation in ClassificationSaeed Bakhshi Germi, Esa Rahtu. 205-211 [doi]
• DeepCaps+: A Light Variant of DeepCapsPouya Shiri, Amirali Baniasadi. 212-220 [doi]
• Body Part Information Additional in Multi-decoder Transformer-Based Network for Human Object Interaction DetectionZihao Guo, Fei Li 0005, Rujie Liu, Ryo Ishida, Genta Suzuki. 221-229 [doi]
• Multi-View Video Synthesis Through Progressive Synthesis and RefinementMohamed Ilyes Lakhal, Oswald Lanz, Andrea Cavallaro. 230-238 [doi]
• BGD: Generalization Using Large Step Sizes to Attract Flat MinimaMuhammad Ali, Omar Alsuwaidi, Salman Khan 0001. 239-249 [doi]
• Tackling Data Bias in Painting Classification with Style TransferMridula Vijendran, Frederick W. B. Li, Hubert P. H. Shum. 250-261 [doi]
• Dynamically Modular and Sparse General Continual LearningArnav Varma, Elahe Arani, Bahram Zonooz. 262-273 [doi]
• Emotion Transformer: Attention Model for Pose-Based Emotion RecognitionPedro V. V. Paiva, Josué J. G. Ramos, Marina L. Gavrilova, Marco A. G. Carvalho. 274-281 [doi]
• Evaluation of Computer Vision-Based Person Detection on Low-Cost Embedded SystemsFrancesco Pasti, Nicola Bellotto. 282-293 [doi]
• Triple-stream Deep Metric Learning of Great Ape Behavioural ActionsOtto Brookes, Majid Mirmehdi, Hjalmar S. Kühl, Tilo Burghardt. 294-302 [doi]
• Efficient Deep Learning Ensemble for Skin Lesion ClassificationDavid Dueñas Gaviria, Md Mostafa Kamal Saker, Petia Radeva. 303-314 [doi]
• Linking Data Separation, Visual Separation, and Classifier Performance Using Pseudo-labeling by Contrastive LearningBarbara Caroline Benato, Alexandre Xavier Falcão, Alexandru Cristian Telea. 315-324 [doi]
• HaloAE: A Local Transformer Auto-Encoder for Anomaly Detection and Localization Based on HaloNetEmilie Mathian, Huidong Liu, Lynnette Fernandez-Cuesta, Dimitris Samaras, Matthieu Foll, Liming Chen 0002. 325-337 [doi]
• FInC Flow: Fast and Invertible k × k Convolutions for Normalizing FlowsAditya Kallappa, Sandeep Nagar, Girish Varma. 338-348 [doi]
• Learning Less Generalizable Patterns for Better Test-Time AdaptationThomas Duboudin, Emmanuel Dellandréa, Corentin Abgrall, Gilles Hénaff, Liming Chen 0002. 349-358 [doi]
• A Multi-Class Probabilistic Optimum-Path ForestSilas Evandro Nachif Fernandes, Leandro A. Passos, Danilo S. Jodas, Marco Akio, André N. de Souza, João Paulo Papa. 361-368 [doi]
• Quantitative Analysis to Find the Optimum Scale Range for Object Representations in Remote Sensing ImagesRasna A. Amit, C. Krishna Mohan. 369-379 [doi]
• Mixing Augmentation and Knowledge-Based Techniques in Unsupervised Domain Adaptation for Segmentation of Edible Insect StatesPawel Majewski, Piotr Lampa, Robert Burduk, Jacek Reiner. 380-387 [doi]
• Combining Metric Learning and Attention Heads for Accurate and Efficient Multilabel Image ClassificationKirill Prokofiev, Vladislav Sovrasov. 388-396 [doi]
• False Negative Reduction in Semantic Segmentation Under Domain Shift Using Depth EstimationKira Maag, Matthias Rottmann. 397-408 [doi]
• Exploring Deep Learning Capabilities for Coastal Image Segmentation on Edge DevicesJonay Suárez-Ramírez, Alejandro Betancor-Del-Rosario, Daniel Santana-Cedrés, Nelson Monzón. 409-418 [doi]
• Fast Eye Detector Using Siamese Network for NIR Partial Face ImagesYuka Ogino, Yuho Shoji, Takahiro Toizumi, Ryoma Oami, Masato Tsukada. 419-428 [doi]
• Understanding of Feature Representation in Convolutional Neural Networks and Vision TransformerHiroaki Minoura, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi. 429-436 [doi]
• Combining Two Adversarial Attacks Against Person Re-Identification SystemsEduardo de O. Andrade, Igor Garcia Ballhausen Sampaio, Joris Guérin, José Viterbo. 437-444 [doi]
• 1D-SalsaSAN: Semantic Segmentation of LiDAR Point Cloud with Self-AttentionTakahiro Suzuki, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi. 445-452 [doi]
• Monocular Depth Estimation for Tilted Images via Gravity RectifierYuki Saito, Hideo Saito, Vincent Frémont. 453-463 [doi]
• Overcome Ethnic Discrimination with Unbiased Machine Learning for Facial Data SetsMichael Danner, Bakir Hadzic, Robert Radloff, Xueping Su, Le Ping Peng, Thomas Weber, Matthias Rätsch. 464-471 [doi]
• How far Generated Data Can Impact Neural Networks Performance?Sayeh Gholipour Picha, Dawood Al Chanti, Alice Caplier. 472-479 [doi]
• Object Detection in Floor Plans for Automated VR Environment GenerationTimothée Fréville, Charles Hamesse, Benoît Pairet, Rob Haelterman. 480-486 [doi]
• MixedTeacher: Knowledge Distillation for Fast Inference Textural Anomaly DetectionSimon Thomine, Hichem Snoussi, Mahmoud Soua. 487-494 [doi]
• Benchmarking Person Re-Identification Datasets and Approaches for Practical Real-World ImplementationsJose Huaman, Felix O. Sumari H., Luigy Machaca, Esteban Clua, Joris Guérin. 495-502 [doi]
• Surface-Graph-Based 6DoF Object-Pose Estimation for Shrink-Wrapped Items Applicable to Mixed Depalletizing RobotsTaiki Yano, Nobutaka Kimura, Kiyoto Ito. 503-511 [doi]
• Impact of Vehicle Speed on Traffic Signs Missed by DriversFarzan Heidari, Michael A. Bauer 0001. 512-519 [doi]
• Transfer Learning for Word Spotting in Historical Arabic Documents Based Triplet-CNNAbir Fathallah, Mounim A. El-Yacoubi, Najoua Essoukri Ben Amara. 520-527 [doi]
• Estimating Distances Between People Using a Single Overhead Fisheye Camera with Application to Social-Distancing OversightZhangchi Lu, Mertcan Cokbas, Prakash Ishwar, Janusz Konrad. 528-535 [doi]
• Banana Ripeness Level Classification Using a Simple CNN Model Trained with Real and Synthetic DatasetsLuis E. Chuquimarca, Boris Xavier Vintimilla, Sergio A. Velastin. 536-543 [doi]
• Using Continual Learning on Edge Devices for Cost-Effective, Efficient License Plate DetectionReshawn Ramjattan, Rajeev Ratan, Shiva Ramoudith, Patrick Hosein, Daniele Mazzei. 544-550 [doi]
• FedBID and FedDocs: A Dataset and System for Federated Document AnalysisDaniel Perazzo, Thiago de Souza, Pietro Masur, Eduardo de Amorim, Pedro de Oliveira, Kelvin B. da Cunha, Lucas Maggi, Francisco Simões, Veronica Teichrieb, Lucas N. Kirsten. 551-558 [doi]
• An Experimental Consideration on Gait SpoofingYuki Hirose, Kazuaki Nakamura, Naoko Nitta, Noboru Babaguchi. 559-566 [doi]
• Subjective Baggage-Weight Estimation from Gait: Can You Estimate How Heavy the Person Feels?Masaya Mizuno, Yasutomo Kawanishi, Tomohiro Fujita, Daisuke Deguchi, Hiroshi Murase. 567-574 [doi]
• Real-World Case Study of a Deep Learning Enhanced Elderly Person Fall Video-Detection SystemAmal El Kaid, Karim Baïna, Jamal Baïna, Vincent Barra. 575-582 [doi]
• Pyramid Swin Transformer: Different-Size Windows Swin Transformer for Image Classification and Object DetectionChenyu Wang, Toshio Endo, Takahiro Hirofuchi, Tsutomu Ikegami. 583-590 [doi]
• Human Fall Detection from Sequences of Skeleton Features using Vision TransformerAli Raza, Muhammad Haroon Yousaf, Sergio A. Velastin, Serestina Viriri. 591-598 [doi]
• Self-Modularized Transformer: Learn to Modularize Networks for Systematic GeneralizationYuichi Kamata, Moyuru Yamada, Takayuki Okatani. 599-606 [doi]
• Fast and Reliable Template Matching Based on Effective Pixel Selection Using Color and Intensity InformationRina Tagami, Hiroki Kobayashi, Shuichi Akizuki, Manabu Hashimoto. 607-614 [doi]
• Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise CorruptionJack W. Barker, Neelanjan Bhowmik, Yona Falinie A. Gaus, Toby P. Breckon. 615-625 [doi]
• An End-to-End Multi-Task Learning Model for Image-based Table RecognitionNam Tuan Ly, Atsuhiro Takasu. 626-634 [doi]
• PanDepth: Joint Panoptic Segmentation and Depth CompletionJuan Pablo Lagos, Esa Rahtu. 635-643 [doi]
• Multi-Scale Feature Based Fashion Attribute Extraction Using Multi-Task Learning for e-Commerce ApplicationsViral Parekh, Karimulla Shaik. 644-651 [doi]
• Domain Adaptive Pedestrian Detection Based on Semantic ConceptsPatrick Feifel, Frank Bonarens, Frank Köster. 652-659 [doi]
• Environmental Information Extraction Based on YOLOv5-Object Detection in Videos Collected by Camera-Collars Installed on Migratory Caribou and Black Bears in Northern QuebecJalila Filali, Denis Laurendeau, Steeve D. Côté. 660-667 [doi]
• A Robust Deep Learning-Based Video Watermarking Using Mosaic GenerationSouha Mansour, Saoussen Ben Jabra, Ezzeddine Zagrouba. 668-675 [doi]
• CrowdSim2: An Open Synthetic Benchmark for Object DetectorsPawel Foszner, Agnieszka Szczesna, Luca Ciampi, Nicola Messina, Adam Cygan, Bartosz Bizon, Michal Cogiel, Dominik Golba, Elzbieta Macioszek, Michal Staniszewski. 676-683 [doi]
• Neural Architecture Search in the Context of Deep Multi-Task LearningGuilherme Gadelha, Herman Martins Gomes, Leonardo Vidal Batista. 684-691 [doi]
• A Data Augmentation Strategy for Improving Age Estimation to Support CSEM DetectionDeisy Chaves, Nancy Agarwal, Eduardo Fidalgo, Enrique Alegre. 692-699 [doi]
• Shuffle Mixing: An Efficient Alternative to Self AttentionRyouichi Furukawa, Kazuhiro Hotta. 700-707 [doi]
• Semantic Segmentation by Semi-Supervised Learning Using Time Series ConstraintTakahiro Mano, Sota Kato, Kazuhiro Hotta. 708-714 [doi]
• Joint Training of Product Detection and Recognition Using Task-Specific DatasetsFloris De Feyter, Toon Goedemé. 715-722 [doi]
• The Effect of Covariate Shift and Network Training on Out-of-Distribution DetectionSimon Mariani, Sander R. Klomp, Rob Romijnders, Peter H. N. de With. 723-730 [doi]
• Improvement of Vision Transformer Using Word PatchesAyato Takama, Sota Kato, Satoshi Kamiya, Kazuhiro Hotta. 731-736 [doi]
• Algorithmic Fairness Applied to the Multi-Label Classification ProblemAna Paula dos Santos Dantas, Gabriel Bianchin de Oliveira, Daiane Mendes de Oliveira, Hélio Pedrini, Cid C. de Souza, Zanoni Dias. 737-744 [doi]
• A Novel 3D Face Reconstruction Model from a Multi-Image 2D SetMohamed Dhouioui, Tarek Frikha, Hassen Drira, Mohamed Abid. 745-753 [doi]
• VK-SITS: Variable Kernel Speed Invariant Time Surface for Event-Based RecognitionLaure Acin, Pierre Jacob, Camille Simon Chane, Aymeric Histace. 754-761 [doi]
• Synthetic Driver Image Generation for Human Pose-Related TasksRomain Guesdon, Carlos Fernando Crispim Junior, Laure Tougne Rodet. 762-769 [doi]
• How to Train an Accurate and Efficient Object Detection Model on any DatasetGalina Zalesskaya, Bogna Bylicka, Eugene Liu. 770-778 [doi]
• Real-Time Obstacle Detection using a Pillar-based Representation and a Parallel Architecture on the GPU from LiDAR MeasurementsMircea Paul Muresan, Robert Schlanger, Radu Danescu, Sergiu Nedevschi. 779-787 [doi]
• Prediction of Shuttle Trajectory in Badminton Using Player's PositionYuka Nokihara, Ryosuke Hori, Ryo Hachiuma, Hideo Saito. 788-795 [doi]
• Crane Spreader Pose Estimation from a Single ViewMaria Pateraki, Panagiotis Sapoutzoglou, Manolis I. A. Lourakis. 796-805 [doi]
• Few-Shot Gaze Estimation via Gaze TransferNikolaos Poulopoulos, Emmanouil Z. Psarakis. 806-813 [doi]
• Application of Deep Learning to the Detection of Foreign Object Debris at Aerodromes' Movement AreaJoão Almeida, Gonçalo Cruz, Diogo Silva, Tiago Oliveira 0003. 814-821 [doi]
• YCbCr Color Space as an Effective Solution to the Problem of Low Emotion Recognition Rate of Facial Expressions In-The-WildHadjer Boughanem, Haythem Ghazouani, Walid Barhoumi. 822-829 [doi]
• WSAM: Visual Explanations from Style Augmentation as Adversarial Attacker and Their Influence in Image ClassificationFelipe Moreno Vera, Edgar Medina, Jorge Poco. 830-837 [doi]
• Applying Positional Encoding to Enhance Vision-Language TransformersXuehao Liu, Sarah Jane Delany, Susan McKeever. 838-845 [doi]
• Brazilian Banknote Recognition Based on CNN for Blind PeopleOdalisio L. S. Neto, Felipe G. Oliveira, João M. B. Cavalcanti, José L. S. Pio. 846-853 [doi]
• Towards an Automatic System for Generating Synthetic and Representative Facial Data for AnonymizationNatália F. de C. Meira, Ricardo C. Câmara de M. Santos, Mateus C. Silva, Eduardo José da S. Luz, Ricardo A. R. Oliveira. 854-861 [doi]
• FPCD: An Open Aerial VHR Dataset for Farm Pond Change DetectionChintan Tundia, Rajiv Kumar, Om Damani, G. Sivakumar. 862-869 [doi]
• DEff-GAN: Diverse Attribute Transfer for Few-Shot Image SynthesisRajiv Kumar, G. Sivakumar. 870-877 [doi]
• Towards Human-Interpretable Prototypes for Visual Assessment of Image Classification ModelsPoulami Sinhamahapatra, Lena Heidemann, Maureen Monnet, Karsten Roscher. 878-887 [doi]
• Curriculum Learning for Compositional Visual ReasoningWafa Aissa, Marin Ferecatu, Michel Crucianu. 888-897 [doi]
• End-to-End Gaze Grounding of a Person Pictured from BehindHayato Yumiya, Daisuke Deguchi, Yasutomo Kawanishi, Hiroshi Murase. 898-905 [doi]
• Human Motion Prediction on the IKEA-ASM DatasetMattias Billast, Kevin Mets, Tom De Schepper, José Oramas, Steven Latré. 906-914 [doi]
• Smoothed Normal Distribution Transform for Efficient Point Cloud Registration During Space RendezvousLéo Renaut, Heike Frei, Andreas Nüchter. 919-930 [doi]
• On Computing Three-Dimensional Camera Motion from Optical Flow Detected in Two Consecutive FramesNorio Tagawa, Ming Yang. 931-942 [doi]
• Upper Bound Tracker: A Multi-Animal Tracking Solution for Closed Laboratory SettingsAlexander Dolokov, Niek Andresen, Katharina Hohlbaum, Christa Thöne-Reineke, Lars Lewejohann, Olaf Hellwich. 945-952 [doi]
• DeNos22: A Pipeline to Learn Object Tracking Using Simulated DepthDominik Penk, Maik Horn, Christoph Strohmeyer, Frank Bauer 0001, Marc Stamminger. 953-962 [doi]
• Flow-Based Visual-Inertial Odometry for Neuromorphic Vision Sensors Using non-Linear Optimization with Online CalibrationMahmoud Z. Khairallah, Abanob Soliman, Fabien Bonardi, David Roussel, Samia Bouchafa. 963-973 [doi]
• Multi-Camera 3D Pedestrian Tracking Using Graph Neural NetworksIsabella de Andrade, João Paulo Lima. 974-981 [doi]
• 3D Human Body Reconstruction from Head-Mounted Omnidirectional Camera and Light SourcesRitsuki Hasegawa, Fumihiko Sakaue, Jun Sato. 982-989 [doi]
• 3D Reconstruction of Occluded Luminous ObjectsAkira Nagatsu, Fumihiko Sakaue, Jun Sato. 990-996 [doi]
• System for 3D Acquisition and 3D Reconstruction Using Structured Light for Sewer Line InspectionJohannes Künzel, Darko Vehar, Rico Nestler, Karl-Heinz Franke, Anna Hilsmann, Peter Eisert. 997-1006 [doi]
• Low-Cost 3D Reconstruction of CavesJoão Marcelo X. N. Teixeira, Narjara Pimentel, Eder Barbier, Enrico Bernard, Veronica Teichrieb, Gimena Chaves. 1007-1014 [doi]
• 3D Mapping of Indoor Parking Space Using Edge Consistency Census Transform Stereo OdometryJunesuk Lee, Soon-Yong Park. 1015-1020 [doi]
• Real-Time Monitoring of Crowd Panic Based on Biometric and Spatiotemporal DataIlias Lazarou, Anastasios L. Kesidis, Andreas Tsatsaris. 1021-1027 [doi]