• Publications
  • Influence
Retinal Blood Vessel Segmentation Using Line Operators and Support Vector Classification
  • E. Ricci, R. Perfetti
  • Computer Science, Medicine
  • IEEE Transactions on Medical Imaging
  • 1 October 2007
TLDR
In the framework of computer-aided diagnosis of eye diseases, retinal vessel segmentation based on line operators is proposed. Expand
  • 668
  • 66
Learning Deep Representations of Appearance and Motion for Anomalous Event Detection
TLDR
We present a novel unsupervised deep learning framework for anomalous event detection in complex video scenes, showing competitive performance with respect to state of the art approaches. Expand
  • 266
  • 35
  • PDF
Multi-scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation
TLDR
This paper addresses the problem of depth estimation from a single image. Expand
  • 217
  • 21
  • PDF
Detecting anomalous events in videos by learning deep representations of appearance and motion
TLDR
We propose Appearance and Motion DeepNet (AMDN), a novel approach based on deep neural networks to automatically learn feature representations for detecting abnormal events in complex video surveillance scenes. Expand
  • 156
  • 19
Self-Adaptive Matrix Completion for Heart Rate Estimation from Face Videos under Realistic Conditions
TLDR
We propose a principled data-driven approach to automatically detect the face parts useful for HR measurement, that is to estimate the time-varying mask of useful observations, and dynamically select face regions useful for robust HR estimation. Expand
  • 126
  • 14
  • PDF
We are not All Equal: Personalizing Models for Facial Expression Analysis with Transductive Parameter Transfer
TLDR
We propose a new transfer learning method to compute personalized models without labeled target data, using publicly available datasets and showing its advantages with respect to the state-of-the-art both in term of accuracy and computational cost. Expand
  • 78
  • 13
  • PDF
AutoDIAL: Automatic Domain Alignment Layers
TLDR
This paper introduces novel Domain Alignment layers (DA-layers) (Fig.1) which are embedded at different levels of the deep architecture to align the ar X iv :1 70 4. Expand
  • 136
  • 12
  • PDF
SALSA: A Novel Dataset for Multimodal Group Behavior Analysis
TLDR
We propose SALSA, a novel dataset facilitating multimodal and Synergetic sociAL Scene Analysis, and make two main contributions to research on automated social interaction analysis: (1) SALSA records social interactions among 18 participants in a natural, indoor environment. Expand
  • 81
  • 10
  • PDF
Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
TLDR
We propose a novel approach for monocular depth estimation which uses a continuous CRF to fuse multi-scale information derived from different layers of a front-end Convolutional Neural Network. Expand
  • 105
  • 9
  • PDF
Animating Arbitrary Objects via Deep Motion Transfer
TLDR
This paper introduces a framework for motion-driven image animation to automatically generate videos by combining the appearance information derived from a source image (e.g. depicting the face or the body silhouette of a certain person) with motion patterns extracted from a driving video. Expand
  • 52
  • 9
  • PDF