{"id":19,"date":"2024-01-04T17:54:09","date_gmt":"2024-01-04T17:54:09","guid":{"rendered":"https:\/\/vision.projects.unibz.it\/?page_id=19"},"modified":"2026-03-16T13:38:14","modified_gmt":"2026-03-16T13:38:14","slug":"publications","status":"publish","type":"page","link":"https:\/\/vision.projects.unibz.it\/?page_id=19","title":{"rendered":"PUBLICATIONS"},"content":{"rendered":"\n

Publications (since 2022)<\/h2>\n\n\n\n
<\/div>\n\n\n\n

T-M. Tai, S. Casarin, A. Pilzer, W. Nutt, O. Lanz: Action-Guided Attention for Video Action Anticipation<\/strong>. International Conference on Learning Representations, ICLR 2026.<\/p>\n\n\n\n

E. Zaranis et.al: Movie Facts and Fibs (MF2<\/sup>): A Benchmark for Long Movie Understanding<\/strong>. International Conference on Learning Representations, Workshop on Multimodal Intelligence @ ICLR 2026.<\/em><\/p>\n\n\n\n

E. Caruso, F. Pelosin, A. Simoni, O. Lanz: Bounding Box-Guided Diffusion\u00a0for Synthesizing Industrial Images and Segmentation Maps<\/strong>. Journal of Imaging, Vol 12(3), 2026.<\/p>\n\n\n\n

S. Casarin, S. Escalera, O. Lanz: NAS just once: Neural Architecture Search for joint Image-Video Recognition<\/strong>. Findings Workshop, IEEE\/CVF International Conference on Computer Vision, Findings @ ICCV 2025.<\/p>\n\n\n\n

S. Casarin, S. Escalera, O. Lanz: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformers<\/strong>. IEEE\/CVF International Conference on Computer Vision and Pattern Recognition, CVPR 2025.<\/p>\n\n\n\n

E. Bianchi, O. Lanz: Gate-Shift-Pose: Enhancing Action Recognition in Sports with Skeleton Information<\/strong>. Workshop on Computer Vision for Winter Sports, IEEE\/CVF Winter Conference on Applications of Computer Vision, CV4WS @ WACV 2025.<\/p>\n\n\n\n

M. Mozaffari, A. Dign\u00f6s, O. Lanz, D. Matt, G. Pasetti Monizza, M. Gauly and J. Gamper: A Substitute Recommendation System in Food Recipes<\/strong>, International Conference on Database and Expert Systems Applications, DEXA 2025.<\/p>\n\n\n\n

C.I. Ugwu, E. Caruso, O. Lanz: Fractals as Pre-Training Datasets for Anomaly Detection and Localization<\/strong>. Fractal and Fractional, Vol. 8(11), 2024.<\/p>\n\n\n\n

E. Caruso, F. Pelosin, A. Simoni, M. Boschetti: Dynamic Label Injection for Imbalanced Industrial Defect Segmentation<\/strong>. Workshop on Vision-based Industrial Inspection, European Conference on Computer Vision, VISION @ ECCV 2024.<\/p>\n\n\n\n

S. Casarin, C.I. Ugwu, S. Escalera, O. Lanz: Your Image is My Video: Reshaping the Receptive Field via Image-To-Video Differentiable AutoAugmentation and Fusion<\/strong>. IEEE\/CVF International Conference on Computer Vision and Pattern Recognition, CVPR 2024.<\/p>\n\n\n\n

S. Casarin, E. Caruso, O. Lanz: GRASP-GCN: Graph-Shape Prioritization for Neural Architecture Search under Distribution Shifts<\/strong>. Fifth Workshop on Neural Architecture Search, IEEE\/CVF International Conference on Computer Vision and Pattern Recognition, NAS @ CVPR 2024.<\/p>\n\n\n\n

C.I. Ugwu, S. Casarin, O. Lanz: Fractals as Pre-training Datasets for Anomaly Detection and Localization<\/strong>. Workshop on Fair, Data-efficient and Trusted Computer Vision, IEEE\/CVF International Conference on Computer Vision and Pattern Recognition, TCV @ CVPR 2024.<\/p>\n\n\n\n

A. Falcon, G. Serra, O. Lanz: Improving Semantic Video Retrieval Models by Training with a Relevance-aware Online Mining Strategy<\/strong>. Computer Vision and Image Understanding, Vol. 245, 2024.<\/p>\n\n\n\n

G. Cavaliere, O. Lanz, Y. Borgianni, E. Savio: Deep learning-supported machine vision-based hybrid system combining inhomogeneous 2D and 3D data for the identification of surface defects<\/strong>. Production & Manufacturing Research, Vol. 12(1), 2024.<\/p>\n\n\n\n

E. Caruso, S. Casarin, T. Pfund, F. Schupp, O. Lanz: Automated visual inspection via differentiable physically-based rendering under unknown illumination<\/strong>. International Symposium on Industrial Engineering and Automation, ISIEA 2024.<\/p>\n\n\n\n

E. Bianchi, O. Lanz: Egocentric video-based human action recognition in industrial environments<\/strong>. International Symposium on Industrial Engineering and Automation, ISIEA 2024.<\/p>\n\n\n\n

A. Rosani, I. Donadello, M. Calvanese, A. Torcinovich, G. Di Fatta, M. Montali and O. Lanz: Video Analytics for Volleyball: Preliminary Results and Future Prospects of the 5VREAL Project<\/strong>. Workshop AI per l’Industria, Convegno Nazionale CINI sull’Intelligenza Artificiale, Ital-IA 2024.<\/p>\n\n\n\n

G. Pasetti Monizza, M. Mozaffari, S. Fabbrizzi, J. Gamper, O. Lanz and D. Matt: Defining a Cognitive Digital Twin architecture in food supply chains: the early outcomes of DSS4LCO initiative<\/strong>. International Food Operations & Processing Simulation Workshop, FoodOPS 2024.<\/p>\n\n\n\n

S. Casarin, E. Caruso, O. Lanz: GRASP-GCN: Graph-Shape Prioritization for Neural Architecture Search under Distribution Shifts<\/strong>. Fifth Workshop on Neural Architecture Search, International Conference on Learning Representations, presentation at DMLR @ ICLR 2024.<\/p>\n\n\n\n

C.I. Ugwu, S. Casarin, O. Lanz: Fractals as Pre-training Datasets for Anomaly Detection and Localization<\/strong>. Workshop on Fair, Data-efficient and Trusted Computer Vision, International Conferrence on Learning Representations, presentation at DMLR @ ICLR 2024.<\/p>\n\n\n\n

J. Rabensteiner, C.I. Ugwu, O. Lanz: Improving Semantic Segmentation Models through Synthetic Data Generation via Diffusion Models<\/strong>. Workshop on Data-centric Machine Learning Research, International Conference on Learning Representations, presentation at DMLR @ ICLR 2024.<\/p>\n\n\n\n

S. Casarin, C.I. Ugwu: DDS-NAS-Bench: Towards predictors under Data Distribution Shift<\/strong>. International Conference on Machine Vision and Applications, ICMVA 2024.<\/p>\n\n\n\n

C.I. Ugwu, S. Casarin, O. Lanz: Spatiotemporal Modeling Encounters 3D Medical Image Analysis: Slice-Shift UNet with Multi-View Fusion<\/strong>. International Conference on Machine Vision and Applications, ICMVA 2024.<\/p>\n\n\n\n

S. Sudhakaran, S. Escalera, O. Lanz: Gate-Shift-Fuse for Video Action Recognition<\/strong><\/strong>. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45(9), 2023.<\/p>\n\n\n\n

S. Sudhakaran, S. Escalera, O. Lanz: Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries<\/strong>. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45(6), 2023.<\/p>\n\n\n\n

A. Falcon, G. Serra, O. Lanz: Video Question Answering supported by a Multi-task Learning Objective<\/strong>. Multimedia Tools and Applications, Vol. 82, 2023.<\/p>\n\n\n\n

M. Lakhal, O. Lanz, A. Cavallaro: Multi-View Video Synthesis through Progressive Synthesis and Refinement<\/strong>. International Conference on Computer Vision Theory and Applications, VISAPP 2023.<\/p>\n\n\n\n

A. Falcon, G. D\u2019Agostino, O. Lanz, G. Brajnik, C. Tasso, G. Serra: Neural Turing Machines for the Remaining Useful Life estimation problem<\/strong>. Computers in Industry, Vol. 143, 2022.<\/p>\n\n\n\n

A. Falcon, G. Serra, O. Lanz: A Feature-Space Multimodal Data Augmentation Technique for Text-Video Retrieval<\/strong>. ACM International Conference on Multimedia, ACMMM 2022.<\/p>\n\n\n\n

T-M. Tai, G. Fiameni, C-K. Lee, Simon See, O. Lanz: Unified Recurrence Modeling for Video Action Anticipation<\/strong>. International Conference on Pattern Recognition, ICPR 2022.<\/p>\n\n\n\n

A. Falcon, S. Sudhakaran, G. Serra, S. Escalera, O. Lanz: Relevance-based Margin for Contrastively-trained Video Retrieval Models<\/strong>. International Conference on Multimedia Retrieval, ICMR 2022.<\/p>\n\n\n\n

T-M. Tai, G. Fiameni, C-K. Lee, O. Lanz: Higher Order Recurrent Network with Space-Time Attention for Video Early Action Recognition<\/strong>. IEEE International Conference on Image Processing, ICIP 2022.<\/p>\n\n\n\n

M. Lakhal, O. Lanz, A. Cavallaro: Implicit Texture Mapping for Multi-View Video Synthesis<\/strong>. British Machine Vision Conference, BMVC 2022.<\/p>\n","protected":false},"excerpt":{"rendered":"

Publications (since 2022) T-M. Tai, S. Casarin, A. Pilzer, W. Nutt, O. Lanz: Action-Guided Attention for Video Action Anticipation. International Conference on Learning Representations, ICLR 2026. E. Zaranis et.al: Movie Facts and Fibs (MF2): A Benchmark for Long Movie Understanding. International Conference on Learning Representations, Workshop on Multimodal Intelligence @ ICLR 2026. E. Caruso, F. Pelosin, A. Simoni, O. Lanz: Bounding Box-Guided Diffusion\u00a0for Synthesizing Industrial Images and Segmentation Maps. Journal of Imaging, Vol 12(3), 2026. S. Casarin, S. Escalera, O. Lanz: NAS just once: Neural Architecture Search for joint Image-Video Recognition. Findings Workshop, IEEE\/CVF International Conference on Computer Vision, Findings […]<\/p>\n","protected":false},"author":8,"featured_media":0,"parent":0,"menu_order":4,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-19","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/vision.projects.unibz.it\/index.php?rest_route=\/wp\/v2\/pages\/19","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/vision.projects.unibz.it\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/vision.projects.unibz.it\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/vision.projects.unibz.it\/index.php?rest_route=\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/vision.projects.unibz.it\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=19"}],"version-history":[{"count":38,"href":"https:\/\/vision.projects.unibz.it\/index.php?rest_route=\/wp\/v2\/pages\/19\/revisions"}],"predecessor-version":[{"id":261,"href":"https:\/\/vision.projects.unibz.it\/index.php?rest_route=\/wp\/v2\/pages\/19\/revisions\/261"}],"wp:attachment":[{"href":"https:\/\/vision.projects.unibz.it\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=19"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}