Improving semantic image segmentation via label fusion in semantically textured meshes (English)
Free access
- New search for: Fervers, Florian
- New search for: Breuer, Timo
- New search for: Stachowiak, Gregor
- New search for: Bullinger, Sebastian
- New search for: Bodensteiner, Christoph
- New search for: Arens, Michael
- New search for: Fervers, Florian
- New search for: Breuer, Timo
- New search for: Stachowiak, Gregor
- New search for: Bullinger, Sebastian
- New search for: Bodensteiner, Christoph
- New search for: Arens, Michael
In:
Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) ; Volume 5
; 509-516
;
2022
- Conference paper / Electronic Resource
-
Title:Improving semantic image segmentation via label fusion in semantically textured meshes
-
Contributors:Fervers, Florian ( author ) / Breuer, Timo ( author ) / Stachowiak, Gregor ( author ) / Bullinger, Sebastian ( author ) / Bodensteiner, Christoph ( author ) / Arens, Michael ( author )
-
Conference:VISAPP ; 17. ; 2022 ; Online
-
Published in:
-
Publisher:
- New search for: SciTePress - Science and Technology Publications, Lda.
-
Place of publication:Setúbal
-
Publication date:2022
-
Remarks:Digital preservation by Technische Informationsbibliothek (TIB) / Leibniz-Informationszentrum Technik und Naturwissenschaften und Universitätsbibliothek
-
DOI:
-
Type of media:Conference paper
-
Type of material:Electronic Resource
-
Language:English
-
Licence:
-
Source:
The tables of contents are generated automatically and are based on the data records of the individual contributions available in the index of the TIB portal. The display of the Tables of Contents may therefore be incomplete.
- 27
-
Self-supervised learning from semantically imprecise dataBrust, Clemens-Alexander / Barz, Björn / Denzler, Joachim et al. | 2022
- 36
-
Animal fiber Identification under the open set conditionRippel, Oliver / Gülçelik, Sergen / Rahimi, Khosrow / Kurniadi, Juliana / Herrmann, Andreas / Merhof, Dorit et al. | 2022
- 48
-
Who did It? Identifying foul subjects and objects in broadcast soccer videosSong, Chunbo / Rasmussen, Christopher et al. | 2022
- 55
-
CGT: consistency guided training in semi-supervised learningHasan, N. / Ghorban, Farzin / Velten, Jörg / Kummert, Anton et al. | 2022
- 65
-
Unidentified floating object detection in maritime environmentVenkatrayappa, Darshan / Desolneux, Agnès / Hubert, Jean-Michel / Manceau, Josselin et al. | 2022
- 75
-
Milking CowMask for semi-supervised image classificationFrench, Geoff / Oliver, Avital / Salimans, Tim et al. | 2022
- 85
-
Anomaly detection for industrial inspection using convolutional autoencoder and deep feature-based one-class classificationSaeedi, Jamal / Giusti, Alessandro et al. | 2022
- 97
-
3D detection of vehicles from 2D images in traffic surveillanceZwemer, M. H. / Scholte, D. / Wijnhoven, R. G. J. / With, P. H. N. et al. | 2022
- 107
-
Iterative 3D deformable registration from single-view RGB images using differentiable renderingPeriyasamy, Arul Selvam / Schwarz, Max / Behnke, Sven et al. | 2022
- 117
-
SieveNet: estimating the particle size distribution of kernel fragments in whole plant corn silageRasmussen, Christoffer / Kirk, Kristian / Moeslund, Thomas B. et al. | 2022
- 125
-
GAN-based face mask removal using facial landmarks and pixel errors in masked regionYoshihashi, Hitoshi / Ienaga, Naoto / Sugimoto, Maki et al. | 2022
- 134
-
Fine-grained action recognition using attribute vectorsYenduri, Sravani / Perveen, Nazil / Chalavadi, Vishnu / Krishna Mohan, C. et al. | 2022
- 144
-
Hear me out: fusional approaches for audio augmented temporal action localizationBagchi, Anurag / Mahmood, Jazib / Fernandes, Dolton / Sarvadevabhatla, Ravi Kiran et al. | 2022
- 155
-
SemSegDepth: a combined model for semantic segmentation and depth completionLagos, Juan Pablo / Rahtu, Esa et al. | 2022
- 166
-
On the cross-dataset generalization in license plate recognitionLaroca, Rayson / Cardoso, Everton V. / Lucio, Diego R. / Estevam, Valter / Menotti, David et al. | 2022
- 179
-
Leveraging local domains for image-to-image translationDell'Eva, Anthony / Pizzati, Fabio / Bertozzi, Massimo / Charette, Raoul et al. | 2022
- 190
-
CAM-SegNet: a context-aware dense material segmentation network for sparsely labelled datasetsHeng, Yuwen / Wu, Yihong / Dasmahapatra, Srinandan / Kim, Hansung et al. | 2022
- 202
-
The MVTec 3D-AD dataset for unsupervised 3D anomaly detection and localizationBergmann, Paul / Jin, Xin / Sattlegger, David / Steger, Carsten et al. | 2022
- 214
-
Improving the sample-complexity of deep classification networks with invariant integrationRath, Matthias / Condurache, Alexandru Paul et al. | 2022
- 226
-
Segregational soft dynamic time warping and its application to action predictionManousaki, Victoria / Argyros, Antonis et al. | 2022
- 236
-
Vehicle pair activity classification using QTC and long short term memory neural networkRadhakrishnan, Rahulan / Alzoubi, Alaa et al. | 2022
- 248
-
ETL: efficient transfer learning for face tasksJohn, Thrupthi Ann / Dua, Isha / Balasubramanian, Vineeth N. / Jawahar, C. V. et al. | 2022
- 258
-
Reinforced damage minimization in critical events for self-driving vehiclesMerola, Francesco / Falchi, Fabrizio / Gennaro, Claudio / Di Benedetto, Marco et al. | 2022
- 267
-
Evolutional normal maps: 3D face representations for 2D-3D face recognition, face modelling and data augmentationDanner, Michael / Weber, Thomas / Huber, Patrik / Awais, Muhammad / Raetsch, Matthias / Kittler, Josef et al. | 2022
- 275
-
Bispectral pedestrian detection augmented with saliency maps using transformerMarnissi, Mohamed Amine / Hattab, Ikram / Fradi, Hajer / Sahbani, Anis / Ben Amara, Najoua Essoukri et al. | 2022
- 287
-
Weakly-supervised localization of multiple objects in images using cosine lossBarz, Björn / Denzler, Joachim et al. | 2022
- 297
-
DeepPupil Net: deep residual network for precise pupil center localizationPoulopoulos, Nikolaos / Psarakis, Emmanouil Z. et al. | 2022
- 305
-
High resolution Mask R-CNN-based damage detection on Titanium Nitride coated milling tools for condition monitoring by using a new illumination techniqueBilal, Mühenad / Kancharana, Sunil / Mayer, Christian / Pfaller, Daniel / Koval, Leonid / Bregulla, Markus / Cupek, Rafal / Ziębiński, Adam et al. | 2022
- 315
-
Neural network pruning based on filter importance values approximated with Monte Carlo gradient estimationSándor, Csanád / Pável, Szabolcs / Csató, Lehel et al. | 2022
- 323
-
The MIS Check-Dam dataset for object detection and instance segmentation tasksTundia, Chintan / Kumar, Rajiv / Damani, Om / Sivakumar, G. et al. | 2022
- 331
-
Oil spill detection and visualization from UAV images using convolutional neural networksRodrigues Junior, Valério N. / Cavalcante, Roberto J.M. / Almeida, João A.G.R. / Fé, Tiago P.M. / Malhado, Ana C.M. / Vieira, Thales / Oliveira, Krerley et al. | 2022
- 339
-
Generating proposals from corners in RPN to detect bees in dense scenesKriouile, Yassine / Ancourt, Corinne / Wegrzyn-Wolska, Katarzyna / Bougueroua, Lamine et al. | 2022
- 351
-
Feature extraction using downsampling for person re-identification with low-resolution imageNishiyama, Masashi / Endo, Takuya / Iwai, Yoshio et al. | 2022
- 359
-
Applying center loss to multidimensional feature space in deep neural networks for open-set recognitionKanaoka, Daiju / Tanaka, Yuichiro / Tamukoh, Hakaru et al. | 2022
- 366
-
Automated human movement segmentation by means of human pose estimation in RGB-D videos for climbing motion analysisBeltrán Beltrán, Raul / Richter, Julia / Heinkel, Ulrich et al. | 2022
- 374
-
A general two-branch decoder architecture for improving encoder-decoder image segmentation modelsHu, Sijie / Bonardi, Fabien / Bouchafa, Samia / Sidibé, Désiré et al. | 2022
- 382
-
Automated damage inspection of power transmission towers from UAV imagesCambeiro Barreiro, Aleixo / Seibold, Clemens / Hilsmann, Anna / Eisert, Peter et al. | 2022
- 390
-
Monocular estimation of translation, pose and 3D shape on detected objects using a convolutional autoencoderPersson, Ivar / Ahrnbom, Martin / Nilsson, Mikael et al. | 2022
- 397
-
Tennis strokes recognition from generated stick figure video overlaysBačić, Boris / Bandara, Ishara et al. | 2022
- 405
-
PodNet: ensemble-based classification of podocytopathy on kidney glomerular imagesOliveira Barros, George / Campos Wanderley, David / Oliveira Rebouças, Luciano et al. | 2022
- 413
-
Detecting patches on road pavement images acquired with 3D laser sensors using object detection and deep learningHassan, Syed Ibrahim / O'sullivan, Dympna / Mckeever, Susan / Power, David / Mcgowan, Ray / Feighan, Kieran et al. | 2022
- 421
-
Weakly supervised segmentation of histopathology images: an insight in feature maps ability for learning models interpretationFeng, Yanbo / Hafiane, Adel / Laurent, Hélène et al. | 2022
- 428
-
Multitask metamodel for keypoint visibility prediction in human pose estimationGuesdon, Romain / Crispim-Junior, Carlos / Tougne, Laure et al. | 2022
- 437
-
Evaluation of long-term deep visual place recognitionAlijani, Farid / Peltomäki, Jukka / Puura, Jussi / Huttunen, Heikki / Kämäräinen, Joni-Kristian / Rahtu, Esa et al. | 2022
- 448
-
Human activity recognition: a spatio-temporal image encoding of 3D skeleton data for online action detectionMokhtari, Nassim / Nédélec, Alexis / Loor, Pierre et al. | 2022
- 456
-
Deep set conditioned latent representations for action recognitionSingh, Akash / Schepper, Tom / Mets, Kevin / Hellinckx, Peter / Oramas, José / Latré, Steven et al. | 2022
- 467
-
Streamlining action recognition in autonomous shared vehicles with an audiovisual cascade strategyRibeiro Pinto, João / Carvalho, Pedro / Pinto, Carolina / Sousa, Afonso / Capozzi, Leonardo / Cardoso, Jaime S. et al. | 2022
- 475
-
Video-based behavior understanding of children for objective diagnosis of autismAli, Abid / Negin, Farhood / Thümmler, Susanne / Bremond, Francois et al. | 2022
- 485
-
Buildings extraction from historical topographic maps via a deep convolution neural networkXydas, Christos / Kesidis, Anastasios L. / Kalogeropoulos, Kleomenis / Tsatsaris, Andreas et al. | 2022
- 493
-
Subclass-based undersampling for class-imbalanced image classificationLehmann, Daniel / Ebner, Marc et al. | 2022
- 501
-
Multimodal personality recognition using cross-attention transformer and behaviour encodingAgrawal, Tanay / Agarwal, Dhruv / Balazia, Michal / Sinha, Neelabh / Bremond, François et al. | 2022
- 509
-
Improving semantic image segmentation via label fusion in semantically textured meshesFervers, Florian / Breuer, Timo / Stachowiak, Gregor / Bullinger, Sebastian / Bodensteiner, Christoph / Arens, Michael et al. | 2022
- 517
-
Honeybee re-identification in video: new datasets and impact of self-supervisionChan, Jeffrey / Carrión, Hector / Mégret, Rémi / Rivera, José L. Agosto / Giray, Tugrul et al. | 2022
- 526
-
Describing image focused in cognitive and visual details for visually impaired people: an approach to generating inclusive paragraphsFernandes, Daninel L. / Ribeiro, Marcos H.F. / Cerqueira, Fabio R. / Silva, Michel M. et al. | 2022
- 535
-
Augmented radar points connectivity based on image processing techniques for object detection and classificationSabry, Mohamed / Hussein, Ahmed / Elmougy, Amr / Abdennadher, Slim et al. | 2022
- 543
-
Using student action recognition to enhance the efficiency of tele-educationDimitriadou, Eleni / Lanitis, Andreas et al. | 2022
- 550
-
TVNet: Temporal Voting Network for action localizationWang, Hanyuan / Damen, Dima / Mirmehdi, Majid / Perrett, Toby et al. | 2022
- 559
-
HRI-gestures: gesture recognition for human-robot interactionKollakidou, Avgi / Haarslev, Frederik / Odabasi, Cagatay / Bodenhagen, Leon / Krüger, Norbert et al. | 2022
- 567
-
StructureNet: deep context attention learning for structural component recognitionKaothalkar, Akash / Mandal, Bappaditya / Puhan, Niladri. B. et al. | 2022
- 574
-
Pose guided feature learning for 3D object tracking on RGB videosMajcher, Mateusz / Kwolek, Bogdan et al. | 2022
- 582
-
Fusion of different features by cross cooperative learning for semantic segmentationIkedo, Ryota / Hotta, Kazuhiro et al. | 2022
- 590
-
Detecting object states vs detecting objects: a new dataset and a quantitative experimental studyGouidis, Filippos / Patkos, Theodore / Argyros, Antonis / Plexousakis, Dimitris et al. | 2022
- 601
-
Skeleton-based online sign language recognition using monotonic attentionTakayama, Natsuki / Benitez-Garcia, Gibran / Takahashi, Hiroki et al. | 2022
- 609
-
Seeing the differences in artistry among art fields by using multi-task learningSato, Ryo / Sakaue, Fumihiko / Sato, Jun et al. | 2022
- 617
-
Diversifying image synthesis using data classificationSuzuki, Yuta / Sakaue, Fumihiko / Sato, Jun et al. | 2022
- 623
-
Combining text and image knowledge with GANs for zero-shot action recognition in videosHuang, Kaiqiang / Miralles-Pechuán, Luis / Mckeever, Susan et al. | 2022
- 632
-
Exploitation of noisy automatic data annotation and its application to hand posture classificationLydakis, Georgios / Oikonomidis, Iason / Kosmopoulos, Dimitrios / Argyros, Antonis A. et al. | 2022
- 642
-
Transfer learning via test-time neural networks aggregationCasella, Bruno / Chisari, Alessio / Battiato, Sebastiano / Giuffrida, Mario et al. | 2022
- 650
-
Evaluation of RGB and LiDAR combination for robust place recognitionAlijani, Farid / Peltomäki, Jukka / Puura, Jussi / Huttunen, Heikki / Kämäräinen, Joni-Kristian / Rahtu, Esa et al. | 2022
- 659
-
Using contrastive learning and pseudolabels to learn representations for retail product image classificationSrivastava, Muktabh Mayank et al. | 2022
- 664
-
Don't miss the fine print! An enhanced framework to extract text from low resolution imagesDugar, Pranay / Vikram, Aditya / Chatterjee, Anirban / Banerjee, Kunal / Agneeswaran, Vijay et al. | 2022
- 672
-
Attention-based gender recognition on masked facesCarletti, Vincenzo / Greco, Antonio / Saggese, Alessia / Vento, Mario et al. | 2022
- 679
-
Class-conditional importance weighting for deep learning with noisy labelsNagarajan, Bhalaji / Marques, Ricardo / Mejia, Marcos / Radeva, Petia et al. | 2022
- 691
-
MOD SLAM: mixed method for a more robust SLAM without loop closingBelos, Thomas / Monasse, Pascal / Dokladalova, Eva et al. | 2022
- 702
-
Event-based extraction of navigation features from unsupervised learning of optic flow patternsFricker, Paul / Chauhan, Tushar / Hurter, Christophe / Cottereau, Benoit R. et al. | 2022
- 711
-
Scan2Part: fine-grained and hierarchical part-level understanding of real-world 3D scansNotchenko, Alexandr / Ishimtsev, Vladislav / Artemov, Alexey / Selyutin, Vadim / Bogomolov, Emil / Burnaev, Evgeny et al. | 2022
- 723
-
Classification performance of RanSaC algorithms with automatic threshold estimationRiu, Clément / Nozick, Vincent / Monasse, Pascal / Dehais, Joachim et al. | 2022
- 734
-
BRDF-based irradiance image estimation to remove radiometric differences for stereo matchingPeng, Kebin / Quarles, John / Desai, Kevin et al. | 2022
- 745
-
Combining local and global pose estimation for precise tracking of similar objectsGard, Niklas / Hilsmann, Anna / Eisert, Peter et al. | 2022
- 757
-
Pushing the efficiency of StereoNet: exploiting spatial sparsityZampokas, Georgios / Bouganis, Christos-Savvas / Tzovaras, Dimitrios et al. | 2022
- 769
-
3-D tennis ball trajectory estimation from multi-view videos and its parameterization by parabola fittingSohara, Kenta / Sugaya, Yasuyuki et al. | 2022
- 777
-
Seg2Pose: pose estimations from instance segmentation masks in one or multiple views for traffic applicationsAhrnbom, Martin / Persson, Ivar / Nilsson, Mikael et al. | 2022
- 785
-
Motion-constrained road user tracking for real-time traffic analysisBo Bo, Nyan / Veelaert, Peter / Philips, Wilfried et al. | 2022
- 793
-
3D object reconstruction using stationary RGB cameraSantos Júnior, José Guedes et al. | 2022
- 801
-
Error evaluation of semantic VSLAM algorithms for smart farmingKalisz, Adam / Sun, Mingjun / Gedschold, Jonas / Wegner, Tim Erich / Del Galdo, Giovanni / Thielecke, Jörn et al. | 2022
- 811
-
Viewpoint-independent single-view 3D object reconstruction using reinforcement learningIto, Seiya / Ju, Byeongjun / Kaneko, Naoshi / Sumi, Kazuhiko et al. | 2022
- 820
-
Generalizable online 3D pedestrian tracking with multiple camerasLyra, Victor / Andrade, Isabella / Lima, João Paulo / Roberto, Rafael / Figueiredo, Lucas / Teixeira, João Marcelo / Thomas, Diego / Uchiyama, Hideaki / Teichrieb, Veronica et al. | 2022
- 828
-
LiMoSeg: real-time Bird's Eye View based LiDAR motion segmentationMohapatra, Sambit / Hodaei, Mona / Yogamani, Senthil / Milz, Stefan / Gotzig, Heinrich / Simon, Martin / Rashed, Hazem / Mäder, Patrick et al. | 2022
- 836
-
Evaluating the impact of head motion on monocular visual odometry with synthetic dataHamesse, Charles / Luong, Hiep / Haelterman, Rob et al. | 2022
- 844
-
An occlusion aware five-view stereo system and its application in video post-productionZhu, Changan / Laurendeau, Taryn / Joslin, Chris et al. | 2022
- 855
-
Human pose estimation through a novel multi-view schemeCharco, Jorge L. / Sappa, Angel D. / Vintimilla, Boris X. et al. | 2022
- 863
-
Visual tilt correction for vehicle-mounted camerasKastantin, Firas / Hajder, Levente et al. | 2022
- 871
-
Semi-supervised anomaly detection for weakly-annotated videosEl-Tahan, Khaled / Torki, Marwan et al. | 2022