Niccolò's Personal Website
  • Bio
  • Papers
  • News
  • Experience
  • Projects
  • Teaching
  • Blog
    • 🎉 The new website is live!
  • Publications
    • EPOCH: Jointly Estimating the 3D Pose of Cameras and Humans
    • Signal processing for haptic surface modeling: A review
    • Skeleton-Aware Motion Retargeting Using Masked Pose Modeling
    • SplatTouch: Explicit 3D Representation Binding Vision and Touch
    • Agglomerator++: Interpretable part-whole hierarchies and latent space representations in neural networks
    • All skeletons are created equal! a domain adaptation transformer to handle multiple topologies
    • EPOCH: Jointly Estimating the 3D Pose of Cameras and Humans
    • MapFlow: Multi-Agent Pedestrian Trajectory Prediction Using Normalizing Flow
    • MoMa: Skinned motion retargeting using masked pose modeling
    • Signal Processing for Haptic Surface Modeling: a Review
    • Ski Pose Estimation
    • Unicrowd simulator: Visual and behavioral fidelity for the generation of crowd datasets
    • A Case Study for the Automatic Supervision of Body-Weight Exercises: The Squat
    • A Unified Simulation Framework for Visual and Behavioral Fidelity in Crowd Analysis
    • Meta-Trainer: An Augmented Reality Trainer for Home Fitness with Real-Time Feedback
    • Accessible video analytics: the use case of basketball
    • Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks
    • Ag-gan: An attentive group-aware gan for pedestrian trajectory prediction
    • DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders
    • Embedding group and obstacle information in lstm networks for human trajectory prediction in crowded scenes
    • Out-of-distribution detection using union of 1-dimensional subspaces
    • Panoptop: a framework for generating viewpoint-invariant human pose estimation datasets
    • Where are they going? Predicting human behaviors in crowded scenes
    • Dynamic camera reconfiguration with reinforcement learning and stochastic methods for crowd surveillance
    • On simulating and predicting pedestrian trajectories in a crowd
    • Camera network optimization: maximize coverage in a 3D virtual environment
    • Virtual crowds: An LSTM-based framework for crowd simulation
    • Dry granular flows of monodisperse particles: an optical method to compute the particles flow field
    • Dynamic camera network reconfiguration for crowd surveillance
    • Group lstm: Group trajectory prediction in crowded scenarios
    • On modeling and analyzing crowds from videos
    • Virtual camera modeling for multi-view simulation of surveillance scenes
    • Data-driven crowd simulation
  • Projects
  • Projects
    • La Grande Mappa delle Pappe e delle delle Bande
  • Experience
  • Teaching
    • Computer Vision course
    • Signal Vision and Recognition

Agglomerator++: Interpretable part-whole hierarchies and latent space representations in neural networks

Jan 1, 2024·
Zeno Sambugaro
,
Nicola Garau
,
Niccoló Bisagno
,
Nicola Conci
· 0 min read
Cite
Type
Journal article
Publication
Computer Vision and Image Understanding
Last updated on Jan 1, 2024
← SplatTouch: Explicit 3D Representation Binding Vision and Touch Jan 1, 2025
All skeletons are created equal! a domain adaptation transformer to handle multiple topologies Jan 1, 2024 →

© 2025 Me. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.