TeV's news

2023

19 September 2023

Three new Journal and three new conference publications

C. Saltori, F. Galasso, G. Fiameni, N. Sebe, F. Poiesi, E. Ricci, Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI, 2023 (arXiv)

R. Jiao, Y. Wan, F. Poiesi, Y. Wang, Survey on video anomaly detection in dynamic scenes with moving cameras, Artificial Intelligence Review, 2023 (arXiv)

M. Lecca. Backlight and Spotlight Image Enhancement Based on Von Kries Model. SN Computer Science 4(5):680, 2023 [doi]

and

M.L. Mekhalfi, D.Boscaini, F. Poiesi, Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object Detection, British Machine Vision Conference - BMVC, Aberdeen, UK, November 2023 (arXiv)

J. Corsetti, D. Boscaini, F. Poiesi, Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation, International Conference on Computer Vision Workshops, Oct 2023, (arXiv)

M. Bortolon, A. Del Bue, F. Poiesi, VM-NeRF: Tackling Sparsity in NeRF with View Morphing, International Conference on Image Analysis and Processing - ICIAP, Udine, Italy, Sep 2023 (arXiv)

31 July 2023

Two new Journal publications

Y. Zhou, G. Mei, Y. Wang, F. Poiesi, Y. Wan, Attentive Multimodal Fusion for Optical and Scene Flow. IEEE Robotics Automation Letters, 2023 (arXiv)

D. Boscaini and F. Poiesi, PatchMixer: Rethinking network design to boost generalization for 3D point cloud understanding. Image and Vision Computing, 2023 (arxiv)

23 March 2023

New paper accepted at CVPR 2023

L. Riz, C. Saltori, E. Ricci, F. Poiesi, Novel class discovery for 3D point cloud semantic segmentation (pdf, code). IEEE Conference on Computer Vision and Pattern Recognition - CVPR 2023, Vancouver, Canada,  June 2023

13 March 2023

Alex Falcon discusses his PhD thesis "Semantics for vision and language understanding" 

8-9 February 2023

FEROX project meeting hosted by FBK (Trento - Italy)

19 January 2023 - Kick-off AGILEHAND project

Meeting in Ancona (Italy)

2022

27 November 2022 - Fabio Poiesi's Keynote at Shandong University (China)

A brief overview of how the Technologies of Vision applies deep machine vision in real-world applications for digital industry: Deep machine vision in digital industry [youtube]


24 October 2022 -  Published a new journal paper 

M. Lecca, G. Gianini, and R.P. Serapioni. Mathematical insights into the original Retinex algorithm for image enhancement. Journal of the Optical Society of America A, Vol. 39, pp. 2063-2072 (2022) [doi]


4 October 2022 - Kick off AI PRISM project

AI Prism kick off meeting


4  July 2022 -  TeV ranked 1st place at EPIC_Kitchens Multi-Instance Retrieval Challenge at CVPR 2022

TeV (FBK) with AILAB (Uni Udine), Computer Vision Center (Uni Barcelona), and Scienze e Tecnologie Informatiche (Uni Bolzano), achieved joint 1st place at the EPIC_Kitchens Multi-Instance Retrieval Challenge. The challenging task was about semantic text-video retrieval: given a query caption, retrieve and rank videos with semantic content relevant to the textual query. Here the talk. Congratulation to the team: Alex Falcon, Giuseppe Serra, Giorgio Escalera, Oswald Lanz


3 July 2022 - Two papers accepted at ECCV 2022

C. Saltori, E. Krivosheev, S. Lathuilière, N. Sebe, F. Galasso, G. Fiameni, E. Ricci and F. Poiesi. GIPSO: Geometrically informed propagation for online adaptation in 3D LiDAR segmentation. European Conference on Computer Vision - ECCV 2022. Tel-Aviv, Isreal, October 2022

C. Saltori, F. Galasso, G. Fiameni, N. Sebe, E. Ricci and F. Poiesi. CoSMix: Compositional semantic mix for domain adaptation in 3D LiDAR segmentation. European Conference on Computer Vision, European Conference on Computer Vision - ECCV 2022. Tel-Aviv, Isreal, October 2022


20 May 2022 - Published paper on PAMI

F. Poiesi and D. Boscaini. Learning general and distinctive 3D local deep descriptors for point cloud registration. IEEE Transactions on Pattern Analysis and Machine Intelligence. Early Access, 2022


18 April 2022 - Accepted paper at ICMR 2022

A. Falcon, S. Sudhakaran, G. Serra, S. Escalera and O. Lanz. Relevance-based Margin for Contrastively-trained Video Retrieval Models. ACM International Conference on Multimedia Retrieval - ICMR 2022. Newark, NJ, USA, June 2022


22 March 2022 - FBK coordinates a new european project. 

FEROX, Fostering and Enabling AI, Data and Robotics Technologies for Supporting Human Workers in Harvesting Wild Food, 36 month starting from 1st April. TeV and  3DOM the involved research units.


16 March 2022 - Published a new journal paper

M. Lecca and F. Poiesi. Performance Comparison of Image Enhancers with and without Deep Learning. Journal of the Optical Society of America A - Optics Image  Science and Vision - JOSA, vol. 39, pp. 610-620, 2022 [doi] 


3 January 2022 - We are partner of AI-PRISM project

AI-PRISM, AI Powered human-centred Robot Interactions for Smart Manufacturing, is an industrial end-user-oriented project within the scope of Horizon Europe Program Cluster 4, Industry Area. With 26 partners from 12 different countries coordinated by Everis Spain, it will provide a human-centred AI-based solutions ecosystem targeted to manufacturing scenarios with tasks difficult to automate and where speed and versatility are essential.

2021

A vision-based robotic manipulation realized within the X Loader 4.0 project

The final system developed inside the Veneeresult project presented at MECSPE Bologna, Italy

M. Bortolon, L. Bazzanella, F. Poiesi, Multi-view data capture for dynamic object reconstruction using handheld augmented reality mobiles. Journal of Real-Time Image Processing 18, pp. 345–355 (2021) [doi] [pre-print]

2020

Oswald Lanz (FBK-TeV) is one of the 2019 Q4 recipients of AWS Machine Learning Research Awards with the project "Structured Representation Learning for Video Recognition and Question Answering". 

S. Sudhakaran, S. Escalera, O. Lanz, Gate-Shift Networks for Video Action Recognition, CVPR 2020, Seattle, Washington, June 16-18, 2020

P. Gainza, F. Sverrisson, F. Monti, E. Rodolà, D. Boscaini, M. M. Bronstein, B. E. Correia, Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning. Nature Methods Volume 17, pages 184–192 (2020) [doi]

B.R. Barricelli, E. Casiraghi, M. Lecca, A. Plutino and A. Rizzi,  A cockpit of multiple measures for assessing film restoration quality. Pattern Recognition Letters, 2020


2019

M. Bortolon, P. Chippendale, S. Messelodi and F. Poiesi, Multi-view data capture using edge-synchronised mobiles, 15th International Conference on Computer Vision Theory and Applications - VISAPP 2020, La Valletta, Malta, 27-29 February, 2020

A. Simonelli, S. Rota Bulo', L. Porzi, M. Lopez-Antequera and P. Kontschieder, Disentangling Monocular 3D Object Detection, ICCV 2019, Seoul, Korea

M.I. Lakhal, O. Lanz and A. Cavallaro, View-LSTM: Novel-View Video Synthesis Through View Decomposition, ICCV 2019, Seoul, Korea

Invited Talk at EPIC@ICCV2019: O. Lanz, Leveraging Spatial Attention and Gating for Fine-grained Action Recognition

F. Cermelli, M. Mancini, E. Ricci and B. Caputo, The RGB-D Triathlon: Towards Agile Visual Toolboxes for Robots,  IROS 2019, Macau, China

P. Gainza, F. Sverrisson, F. Monti, E. Rodolà, D. Boscaini, M. M. Bronstein, B. E. Correia,  Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning, Nature Methods

Please follow us at ICIAP 2019 also on www.facebook.com/iciap2019

Swathikiran Sudhakaran, Oswald Lanz (FBK-TeV, Trento) and Sergio Escalera (Uni Barcelona) ranked in the 3rd position in EPIC-Kitchens 2019 Action Recognition Challenge at CVPR with LSTA: Long Short-Term Attention for Egocentric Action Recognition

EPIC-Kitchens is the largest dataset in first-person vision recordings in native environment. Given a trimmed action segment, the challenge was to classify the segment into its action class composed of the pair of verb and noun classes (e.g. wash cup, cut tomato, dry hand...)

The  20th International Conference on Image Analysis and Processing - ICIAP 2019 is organized by UniTN-DISI and FBK-TeV in Trento, Italy, September 9-13, 2019

on five submissions!

X. Qian, A. Brutti, O. Lanz, M. Omologo and A. Cavallaro, Multi-speaker tracking from an audio-visual sensing device, IEEE Transactions on Multimedia, 2019

M. Gottardi and M. Lecca,  A 64 x 64 Pixel Vision Sensor for Local Binary Pattern Computation, IEEE Transactions on Circuits and Systems 1 (2019)