About
The Computer Vision Trento Symposium (CVTS) is organised to bring together scientists, researchers, students, practitioners, and enthusiasts who share an interest in computer vision. This one-day event will showcase an invited keynote and series of oral and poster presentations. This year, 11 presentations will be featured on works that will be presented at IEEE Computer Vision and Pattern Recognition 2024 conference. CVTS will be held on Wednesday 12th June 2024. There will also be a link to join remotely. Free registration is required to attend in person.
![#CVTS2024](https://elias-ai.eu/wp-content/uploads/2024/04/CVTS2024.png)
Programme
Time | Event | Speakers |
---|---|---|
9:00 | Welcome | Fabio Poiesi |
9:10 | Keynote: Semantic 3D reconstruction and understanding from images | Alessio Del Bue |
10:00 | Open-vocabulary object 6D pose estimation | Jaime Corsetti, Davide Boscaini, Changjae Oh, Andrea Cavallaro, Fabio Poiesi |
10:20 | Geometrically-driven aggregation for zero-shot 3D point cloud understanding | Guofeng Mei, Luigi Riz, Yiming Wang, Fabio Poiesi |
10:40 | Point cloud pre-training with diffusion models | Xiao Zheng, Xiaoshui Huang, Guofeng Mei, Yuenan Hou, Zhaoyang Lyu, Bo Dai, Wanli Ouyang, Yongshun Gong |
11:00 | Coffee break | |
11:20 | DiffAssemble: A unified graph-diffusion model for 2D and 3D reassembly | Gianluca Scarpellini, Stefano Fiorini, Francesco Giuliari, Pietro Morerio, Alessio Del Bue |
11:40 | PAIR Diffusion: A comprehensive multimodal object-level image editor | Vidit Goel, Elia Peruzzo, Yifan Jiang, Dejia Xu, Xingqian Xu, Nicu Sebe, Trevor Darrell, Zhangyang Wang, Humphrey Shi |
12:00 | Test-time zero-shot temporal action localization | Benedetta Liberatori, Alessandro Conti, Paolo Rota, Yiming Wang, Elisa Ricci |
12:20 | SHiNe: Semantic hierarchy nexus for open-vocabulary object detection | Mingxuan Liu, Tyler Hayes, Elisa Ricci, Gabriela Csurka, Riccardo Volpi |
12:40 | Lunch break | |
14:00 | Poster session | |
15:00 | Coffee break | |
15:20 | Riemannian multiclass logistics regression for SPD neural networks | Ziheng Chen, Yue Song, Gaowen Liu, Ramana Kompella, Xiaojun Wu, Nicu Sebe |
15:40 | Harnessing large language models for training-free video anomaly detection | Luca Zanella, Willi Menapace, Massimiliano Mancini, Yiming Wang, Elisa Ricci |
16:00 | MULTIFLOW: Shifting towards task-agnostic vision-language pruning | Matteo Farina, Massimiliano Mancini, Elia Cunegatti, Gaowen Liu, Giovanni Iacca, Elisa Ricci |
16:20 | OpenBias: Open-set bias detection in generative model | Moreno D'Incà, Elia Peruzzo, Massimiliano Mancini, Dejia Xu, Vidit Goel, Xingqian Xu, Zhangyang Wang, Humphrey Shi, Nicu Sebe |
16:40 | Closing | Fabio Poiesi |