N
Nuno Vasconcelos
Researcher at University of California, San Diego
Publications - 309
Citations - 28627
Nuno Vasconcelos is an academic researcher from University of California, San Diego. The author has contributed to research in topics: Image retrieval & Object detection. The author has an hindex of 72, co-authored 286 publications receiving 21902 citations. Previous affiliations of Nuno Vasconcelos include Hewlett-Packard & University of California, Los Angeles.
Papers
More filters
Proceedings ArticleDOI
Cascade R-CNN: Delving Into High Quality Object Detection
Zhaowei Cai,Nuno Vasconcelos +1 more
TL;DR: Cascade R-CNN as mentioned in this paper proposes a multi-stage object detection architecture, which consists of a sequence of detectors trained with increasing IoU thresholds, to be sequentially more selective against close false positives.
Proceedings ArticleDOI
Anomaly detection in crowded scenes
TL;DR: A novel framework for anomaly detection in crowded scenes is presented and the proposed representation is shown to outperform various state of the art anomaly detection techniques.
Book ChapterDOI
A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
TL;DR: A unified deep neural network, denoted the multi-scale CNN (MS-CNN), is proposed for fast multi- scale object detection, which is learned end-to-end, by optimizing a multi-task loss.
Proceedings ArticleDOI
A new approach to cross-modal multimedia retrieval
Nikhil Rasiwasia,Jose Costa Pereira,Emanuele Coviello,Gabriel Doyle,Gert R. G. Lanckriet,Roger Levy,Nuno Vasconcelos +6 more
TL;DR: It is shown that accounting for cross-modal correlations and semantic abstraction both improve retrieval accuracy and are shown to outperform state-of-the-art image retrieval systems on a unimodal retrieval task.
Proceedings ArticleDOI
Privacy preserving crowd monitoring: Counting people without people models or tracking
TL;DR: A privacy-preserving system for estimating the size of inhomogeneous crowds, composed of pedestrians that travel in different directions, without using explicit object segmentation or tracking is presented.