Table of Contents

• Clothing Parsing using Extended U-NetGabriela Vozáriková, Richard Stana, Gabriel Semanisin. 15-24 [doi]
• Lightweight SSD: Real-time Lightweight Single Shot Detector for Mobile DevicesShi Guo, Yang Liu, Yong Ni, Wei Ni. 25-35 [doi]
• Reduction in Communication via Image Selection for Homomorphic Encryption-based Privacy-protected Person Re-identificationShogo Fukuda, Masashi Nishiyama, Yoshio Iwai. 36-47 [doi]
• Automatically Generating Websites from Hand-drawn MockupsJoão Silva Ferreira, André Restivo, Hugo Sereno Ferreira. 48-58 [doi]
• On the Transferability of Winning Tickets in Non-natural Image DatasetsMatthia Sabatelli, Mike Kestemont, Pierre Geurts. 59-69 [doi]
• Point Cloud Upsampling and Normal Estimation using Deep Learning for Robust Surface ReconstructionRajat Sharma, Tobias Schwandt, Christian Kunert, Steffen Urban, Wolfgang Broll. 70-79 [doi]
• Building Synthetic Simulated Environments for Configuring and Training Multi-camera Systems for Surveillance ApplicationsNerea Aranjuelo, Jorge García, Luis Unzueta, Sara García, Unai Elordi, Oihana Otaegui. 80-91 [doi]
• CUPR: Contrastive Unsupervised Learning for Person Re-identificationKhadija Khaldi, Shishir K. Shah. 92-100 [doi]
• Latent Video TransformerRuslan Rakhimov, Denis Volkhonskiy, Alexey Artemov, Denis Zorin, Evgeny Burnaev. 101-112 [doi]
• Feature Map Upscaling to Improve Scale Invariance in Convolutional Neural NetworksDinesh Kumar, Dharmendra Sharma 0001. 113-122 [doi]
• Image Synthesisation and Data Augmentation for Safe Object Detection in Aircraft Auto-landing SystemNajda Vidimlic, Alexandra Levin, Mohammad Loni, Masoud Daneshtalab. 123-135 [doi]
• A Human Ear Reconstruction AutoencoderHao Sun, Nick E. Pears, Hang Dai. 136-145 [doi]
• Few-shot Linguistic Grounding of Visual Attributes and Relations using Gaussian KernelsDaniel Koudouna, Kasim Terzic. 146-156 [doi]
• Detecting Object Defects with Fusioning Convolutional Siamese Neural NetworksAmr M. Nagy, László Czúni. 157-163 [doi]
• Towards Real-time Object Recognition and Pose Estimation in Point CloudsMarlon Marcon, Olga Regina Pereira Bellon, Luciano Silva. 164-174 [doi]
• A Neural Network with Adversarial Loss for Light Field Synthesis from a Single ImageSimon Evain, Christine Guillemot. 175-184 [doi]
• Domain Adaptation for Traffic Density EstimationLuca Ciampi, Carlos Santiago, João Paulo Costeira, Claudio Gennaro, Giuseppe Amato. 185-195
• Contextualise, Attend, Modulate and Tell: Visual StorytellingZainy M. Malakan, Nayyer Aafaq, Ghulam Mubashar Hassan, Ajmal Mian. 196-205 [doi]
• Fairer Evaluation of Zero Shot Action Recognition in VideosKaiqiang Huang, Sarah Jane Delany, Susan McKeever. 206-215 [doi]
• Global Point Cloud Descriptor for Place Recognition in Indoor EnvironmentsJacek Komorowski, Grzegorz Kurzejamski, Monika Wysoczanska, Tomasz Trzcinski. 216-224 [doi]
• Towards Combined Open Set Recognition and Out-of-Distribution Detection for Fine-grained ClassificationAlexander Gillert, Uwe Freiherr von Lukas. 225-233 [doi]
• Analysis of Recent Re-Identification Architectures for Tracking-by-Detection Paradigm in Multi-Object TrackingHaruya Ishikawa, Masaki Hayashi, Trong Huy Phan, Kazuma Yamamoto, Makoto Masuda, Yoshimitsu Aoki. 234-244 [doi]
• Facial Exposure Quality Estimation for Aesthetic EvaluationMathias Gudiksen, Sebastian Falk, Lasse Nymark Hansen, Frederik Brønnum Jensen, Andreas Møgelmose. 247-255 [doi]
• Learning Unsupervised Cross-domain Image-to-Image Translation using a Shared DiscriminatorRajiv Kumar, Rishabh Dabral, G. Sivakumar. 256-264 [doi]
• Approaching the Semantic Segmentation in Medical Problems: A Solution for Pneumothorax DetectionCalin Timbus, Vlad Miclea, Camelia Lemnaru. 265-272 [doi]
• Crowd Behavior Analysis based on Convolutional Neural Network: Social Distancing Control COVID-19Fatma Bouhlel, Hazar Mliki, Mohamed Hammami. 273-280 [doi]
• Three-step Alignment Approach for Fitting a Normalized Mask of a Person Rotating in A-Pose or T-Pose Essential for 3D Reconstruction based on 2D Images and CGI Derived Reference Target PoseGerald Zwettler, Christoph Praschl, David Baumgartner, Tobias Zucali, Dora Turk, Martin Hanreich, Andreas Schuler. 281-292 [doi]
• Weakly-supervised Human-object Interaction DetectionMasaki Sugimoto, Ryosuke Furuta, Yukinobu Taniguchi. 293-300 [doi]
• Online Point Cloud Object Recognition System using Local Descriptors for Real-time ApplicationsYacine Yaddaden, Sylvie Daniel, Denis Laurendeau. 301-308 [doi]
• ChartSight: An Automated Scheme for Assisting Visually Impaired in Understanding Scientific ChartsMandhatya Singh, Puneet Goyal. 309-318 [doi]
• Unsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object DetectionTobias Scheck, Ana Pérez Grassi, Gangolf Hirtz. 319-327 [doi]
• No Need for a Lab: Towards Multi-sensory Fusion for Ambient Assisted Living in Real-world Living HomesAlessandro Masullo, Toby Perrett, Dima Damen, Tilo Burghardt, Majid Mirmehdi. 328-337 [doi]
• Tropical Skin Disease Classification using Connected Attribute FiltersFred N. Kiwanuka, Omar Eltaher Abuelmaatti, Anang Hudaya Muhamad Amin, Brian J. Mukwaya. 338-345 [doi]
• Are Image Patches Beneficial for Initializing Convolutional Neural Network Models?Daniel Lehmann, Marc Ebner. 346-353 [doi]
• Improving Car Model Classification through Vehicle Keypoint LocalizationAlessandro Simoni, Andrea D'Eusanio, Stefano Pini, Guido Borghi, Roberto Vezzani. 354-361 [doi]
• Long-term Behaviour Recognition in Videos with Actor-focused Region AttentionLuca Ballan, Ombretta Strafforello, Klamer Schutte. 362-369 [doi]
• A Multi-level Rank Correlation Measure for Image RetrievalNikolas Gomes de Sá, Lucas Pascotti Valem, Daniel Carlos Guimarães Pedronette. 370-378 [doi]
• Learning Joint Twist Rotation for 3D Human Pose Estimation from a Single ImageChihiro Nakatsuka, Jianfeng Xu, Kazuyuki Tasaka. 379-386 [doi]
• Multimodal Neural Network for Sentiment Analysis in Embedded SystemsQuentin Portes, José Mendès Carvalho, Julien Pinquier, Frédéric Lerasle. 387-398 [doi]
• A Snapshot-based Approach for Self-supervised Feature Learning and Weakly-supervised Classification on Point Cloud DataXingye Li, Zhigang Zhu. 399-408 [doi]
• Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-aliased Indoor EnvironmentsSatyajit Tourani, Dhagash Desai, Udit Singh Parihar, Sourav Garg, Ravi Kiran Sarvadevabhatla, Michael Milford, K. Madhava Krishna. 409-416 [doi]
• 3D Object Classification via Part GraphsFlorian Teich, Timo Lüddecke, Florentin Wörgötter. 417-426 [doi]
• Graph Convolutional Networks Skeleton-based Action Recognition for Continuous Data Stream: A Sliding Window ApproachMickael Delamare, Cyril Laville, Adnane Cabani, Houcine Chafouk. 427-435 [doi]
• Multi-Stage Dynamic Batching and On-Demand I-Vector Clustering for Cost-effective Video SurveillanceDavid Montero, Luis Unzueta, Jon Goenetxea, Nerea Aranjuelo, Estíbaliz Loyo, Oihana Otaegui, Marcos Nieto. 436-443 [doi]
• Non-Maximum Suppression for Unknown Class Objects using Image SimilarityYoshiaki Homma, Toshiki Kikuchi, Yuko Ozasa. 444-449 [doi]
• Road Lane Detection and Classification in Urban and Suburban Areas based on CNNsNima Khairdoost, Steven S. Beauchemin, Michael A. Bauer 0001. 450-457 [doi]
• Detection of Distraction-related Actions on DMD: An Image and a Video-based Approach ComparisonPaola Cañas, Juan Diego Ortega, Marcos Nieto, Oihana Otaegui. 458-465 [doi]
• Lightweight Filtering of Noisy Web Data: Augmenting Fine-grained Datasets with Selected Internet ImagesJulia Böhlke, Dimitri Korsch, Paul Bodesheim, Joachim Denzler. 466-477 [doi]
• Line2depth: Indoor Depth Estimation from Line DrawingsSergey Pavlov, Yoshihiro Kanamori, Yuki Endo. 478-483 [doi]
• Automatic Annotation and Segmentation of Sign Language Videos: Base-level Features and Lexical Signs ClassificationHussein Chaaban, Michèle Gouiffès, Annelies Braffort. 484-491 [doi]
• Collaborative Learning of Generative Adversarial NetworksTakuya Tsukahara, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi. 492-499 [doi]
• LAMV: Learning to Predict Where Spectators Look in Live Music PerformancesArturo Fuentes, Francisco Javier Sánchez, Thomas Voncina, Jorge Bernal. 500-507 [doi]
• Occluded Iris Recognition using SURF FeaturesAnca Ignat, Ioan Pavaloi. 508-515 [doi]
• Convolutional Neural Networks with Fixed WeightsTyler C. Folsom. 516-523 [doi]
• Extracting Accurate Long-term Behavior Changes from a Large Pig DatasetLuca Bergamini, Stefano Pini, Alessandro Simoni, Roberto Vezzani, Simone Calderara, Rick B. D'Eath, Robert B. Fisher. 524-533 [doi]
• Multi-Task Architecture with Attention for Imaging Atmospheric Cherenkov Telescope Data AnalysisMikaël Jacquemont, Thomas Vuillaume, Alexandre Benoît, Gilles Maurin, Patrick Lambert. 534-544 [doi]
• GAPF: Curve Text Detection based on Generative Adversarial Networks and Pixel FluctuationsJun Yang, Zhaogong Zhang, Xuexia Wang. 545-552 [doi]
• Automated Infant Monitoring based on R-CNN and HMMCheng Li, Arash Pourtaherian, Lonneke van Onzenoort, Peter H. N. de With. 553-560 [doi]
• On Power Jaccard Losses for Semantic SegmentationDavid Duque-Arias, Santiago Velasco-Forero, Jean-Emmanuel Deschaud, François Goulette, Andrés Serna, Etienne Decencière, Beatriz Marcotegui. 561-568 [doi]
• 3D Object Detection with Normal-map on Point CloudsJishu Miao, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi. 569-576 [doi]
• Feature Sharing Cooperative Network for Semantic SegmentationRyota Ikedo, Kazuhiro Hotta. 577-584 [doi]
• Analysing Adversarial Examples for Deep LearningJason Jung, Naveed Akhtar, Ghulam Mubashar Hassan. 585-592 [doi]
• U-Net based Zero-hour Defect Inspection of Electronic Components and SemiconductorsFlorian Kälber, Okan Köpüklü, Nicolas H. Lehment, Gerhard Rigoll. 593-601 [doi]
• SCAN: Sequence-character Aware Network for Text RecognitionHeba Hassan, Marwan Torki, Mohamed E. Hussein. 602-609 [doi]
• Supervised versus Self-supervised Assistant for Surveillance of Harbor FrontsJinsong Liu, Mark P. Philipsen, Thomas B. Moeslund. 610-617 [doi]
• Segment My Object: A Pipeline to Extract Segmented Objects in Images based on Labels or Bounding BoxesRobin Deléarde, Camille Kurtz, Philippe Dejean, Laurent Wendling. 618-625 [doi]
• Embedding Human Knowledge into Deep Neural Network via Attention MapMasahiro Mitsuhara, Hiroshi Fukui, Yusuke Sakashita, Takanori Ogata, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi. 626-636 [doi]
• Temporal Bilinear Encoding Network of Audio-visual Features at Low Sampling RatesFeiyan Hu, Eva Mohedano, Noel E. O'Connor, Kevin McGuinness. 637-644 [doi]
• S*ReLU: Learning Piecewise Linear Activation Functions via Particle Swarm OptimizationMina Basirat, Peter M. Roth. 645-652 [doi]
• Player Identification in Different SportsAhmed Nady, Elsayed E. Hemayed. 653-660 [doi]
• Performance Benchmarking of YOLO Architectures for Vehicle License Plate Detection from Real-time Videos Captured by a Mobile RobotAmir Ismail, Maroua Mehri, Anis Sahbani, Najoua Essoukri Ben Amara. 661-668 [doi]
• Deep Emotion Recognition through Upper Body Movements and Facial ExpressionChaudhary Muhammad Aqdus Ilyas, Rita Nunes, Kamal Nasrollahi, Matthias Rehm, Thomas B. Moeslund. 669-679 [doi]
• Efficient Multi-task based Facial Landmark and Gesture Detection in Monocular ImagesJon Goenetxea, Luis Unzueta, Unai Elordi, Oihana Otaegui, Fadi Dornaika. 680-687 [doi]
• Audience Shot Detection for Automatic Analysis of Soccer Sports VideosKazimierz Choros. 688-695 [doi]
• A Lightweight Real-time Stereo Depth Estimation Network with Dynamic Upsampling ModulesYong Deng, Jimin Xiao, Steven ZhiYing Zhou. 701-710 [doi]
• BirdSLAM: Monocular Multibody SLAM in Bird's-eye ViewSwapnil Daga, Gokul B. Nair, Anirudha Ramesh, Rahul Sajnani, Junaid Ahmed Ansari, K. Madhava Krishna. 711-721 [doi]
• Independently Moving Object Trajectories from Sequential Hierarchical RansacMikael Persson, Per-Erik Forssén. 722-731 [doi]
• A Benchmark for 3D Reconstruction from Aerial Imagery in an Urban EnvironmentSusana Ruano, Aljosa Smolic. 732-741 [doi]
• Normalized Convolution Upsampling for Refined Optical Flow EstimationAbdelrahman Eldesokey, Michael Felsberg. 742-752 [doi]
• Investigating 3D Convolutional Layers as Feature Extractors for Anomaly Detection Systems Applied to Surveillance VideosTiago S. Nazaré, Rodrigo Fernandes de Mello, Moacir A. Ponti. 753-762 [doi]
• Real-time Monocular 6DoF Tracking of Textureless Objects using Photometrically-enhanced EdgesLucas Valença, Luca Silva, Thiago Chaves, Arlindo Gómes 0001, Lucas Figueiredo, Lucio Cossio, Sébastien Tandel, João Paulo Lima, Francisco Simões, Veronica Teichrieb. 763-773 [doi]
• Real-time and Online Segmentation Multi-target Tracking with Track Revival Re-identificationMartin Ahrnbom, Mikael G. Nilsson, Håkan Ardö. 777-784 [doi]
• Object based Hybrid Video CompressionRhoda Gbadeyan, Chris Joslin. 785-792 [doi]
• Modeling a priori Unknown Environments: Place Recognition with Optical Flow FingerprintsZachary Mueller, Sotirios Diamantas. 793-800 [doi]
• Quantifying Wind Turbine Blade Surface Roughness using Sandpaper Grit Sizes: An Initial ExplorationIvan A. Nikolov, Claus B. Madsen. 801-808 [doi]
• A Study on the Influence of Omnidirectional Distortion on CNN-based Stereo VisionJulian Seuffert, Ana Pérez Grassi, Tobias Scheck, Gangolf Hirtz. 809-816 [doi]
• Procam Calibration from a Single Pose of a Planar TargetGhani O. Lawal, Michael Greenspan. 817-827 [doi]
• Object Hypotheses as Points for Efficient Multi-Object TrackingShuhei Tarashima. 828-835 [doi]
• A Surface and Appearance-based Next Best View System for Active Object RecognitionPourya Hoseini, Shuvo Kumar Paul, Mircea Nicolescu, Monica N. Nicolescu. 841-851 [doi]
• Multi-view Planarity Constraints for Skyline Estimation from UAV Images in City Scale Urban EnvironmentsAyyappa Swamy Thatavarthy, Tanu Sharma, Harshit Sankhla, Mukul Khanna, K. Madhava Krishna. 852-860 [doi]
• Boosting Self-localization with Graph Convolutional Neural NetworksKoji Takeda, Kanji Tanaka. 861-868 [doi]
• Practical Auto-calibration for Spatial Scene-understanding from Crowdsourced Dashcamera VideosHemang Chawla, Matti Jukola, Shabbir Marzban, Elahe Arani, Bahram Zonooz. 869-880 [doi]
• Dual CNN-based Face Tracking Algorithm for an Automated Infant Monitoring SystemCheng Li, Genyu Song, Arash Pourtaherian, Peter H. N. de With. 881-887 [doi]
• Sewer Defect Classification using Synthetic Point CloudsJoakim Bruslund Haurum, Moaaz M. J. Allahham, Mathias S. Lynge, Kasper Schøn Henriksen, Ivan A. Nikolov, Thomas B. Moeslund. 891-900 [doi]
• Learning to Correct Reconstructions from Multiple ViewsStefan Saftescu, Paul Newman 0001. 901-909 [doi]
• Integration of Multiple RGB-D Data of a Deformed Clothing Item into Its Canonical ShapeYasuyo Kita, Ichiro Matsuda, Nobuyuki Kita. 910-918 [doi]
• Fiducial Points-supported Object Pose Tracking on RGB Images via Particle Filtering with Heuristic OptimizationMateusz Majcher, Bogdan Kwolek. 919-926 [doi]
• Visual-based Global Localization from Ceiling Images using Convolutional Neural NetworksPhilip Scales, Mykhailo Rimel, Olivier Aycard. 927-934 [doi]
• Unsupervised Gaze Prediction in Egocentric Videos by Energy-based Surprise ModelingSathyanarayanan N. Aakur, Arunkumar Bagavathi. 935-942 [doi]
• Detecting Anomalies from Human Activities by an Autonomous Mobile Robot based on "Fast and Slow" ThinkingMuhammad Fikko Fadjrimiratno, Yusuke Hatae, Tetsu Matsukawa, Einoshin Suzuki. 943-953 [doi]
• Unsupervised Domain Adaptation for 6DOF Indoor LocalizationDaniele Di Mauro, Antonino Furnari, Giovanni Signorello, Giovanni Maria Farinella. 954-961 [doi]