Media Integration and Communication Center

Visual Information and Media Lab

Skip to content
  • Home
  • Active thesis
  • Datasets
    • 3D faces
    • Audio events in Soccer Videos
    • Florence 3D actions dataset
    • Florence Superface
    • Hand pose
    • Logging of face imagery
    • MICC Flickr 101
    • Micc People Counting
    • Multiple Target Tracking
    • MuseumVisitors
    • PTZ camera pose recovery
  • No Access
  • Opensource
    • Loki: A Cross-Media Search Engine
  • People
  • Publications
  • Contact us

Pose invariant face recognition

This entry was posted in Thesis on June 4, 2014 by dpezzatini.

Post navigation

← Object-occlusion for SoA tracker DSN Image annotation KCCA by Deep Network →

Datasets

  • Datasets
    • 3D faces
    • Audio events in Soccer Videos
    • Florence 3D actions dataset
    • Florence Superface
    • Hand pose
    • Logging of face imagery
    • MICC Flickr 101
    • Micc People Counting
    • Multiple Target Tracking
    • MuseumVisitors
    • PTZ camera pose recovery
  • No Access

Opensource

  • No Access
  • Opensource
    • Loki: A Cross-Media Search Engine

Tags

  • 3D face recognition
  • Accademia della Crusca
  • action recognition
  • archeology
  • bag of words
  • Cocoa
  • collaborative
  • computer vision
  • content retrieval
  • Core Animation
  • cultural heritage
  • Digester
  • information architecture
  • localization
  • Lucéne
  • mapping
  • multi-touch
  • multi-user
  • multimedia interfaces
  • natural interfaces
  • neurocognitive rehabilitation
  • neuromotor rehabilitation
  • ontologies
  • Palazzo Medici Riccardi
  • ptz-camera
  • Quartz 2D
  • RIA
  • semantic
  • Shawbak
  • SIFT
  • smart object
  • sound
  • sports videos
  • tableTop
  • TANGerINE
  • tracking
  • Tuscany
  • user experience
  • video annotation
  • Video retrieval
  • videosurveillance
  • VIDI-Video
  • vision
  • visual tracker
  • web interface

Recent news