L
Luca Zappella
Researcher at Johns Hopkins University
Publications - 27
Citations - 842
Luca Zappella is an academic researcher from Johns Hopkins University. The author has contributed to research in topics: Segmentation & Computer science. The author has an hindex of 12, co-authored 21 publications receiving 710 citations. Previous affiliations of Luca Zappella include University of Girona & Metaio GmbH.
Papers
More filters
Journal ArticleDOI
A Dataset and Benchmarks for Segmentation and Recognition of Gestures in Robotic Surgery
Narges Ahmidi,Lingling Tao,Shahin Sefati,Yixin Gao,Colin Lea,Benjamin Bejar Haro,Luca Zappella,Sanjeev Khudanpur,René Vidal,Gregory D. Hager +9 more
TL;DR: The results reported in this paper provide the first systematic and uniform evaluation of surgical activity recognition techniques on the benchmark database, a public dataset that is created to support comparative research benchmarking.
Journal ArticleDOI
Surgical gesture classification from video and kinematic data
TL;DR: This paper proposes several methods for automatic surgical gesture classification from video data and shows that methods based on video data perform equally well, if not better, than state-of-the-art approaches based on kinematic data.
Book ChapterDOI
Surgical Gesture Segmentation and Recognition
TL;DR: This paper proposes a framework for joint segmentation and recognition of surgical gestures from kinematic and video data using a combined Markov/semi-Markov conditional random field (MsM-CRF) model, and shows that the proposed model improves over a Markov or semi- Markov CRF when using video data alone, gives results that are comparable to state-of-the-art methods on kinematics data alone.
Book ChapterDOI
Surgical gesture classification from video data
TL;DR: This paper shows that in a typical surgical training setup, video data can be equally discriminative and proposes and evaluates three approaches to surgical gesture classification from video.
Proceedings Article
Motion Segmentation: a Review
TL;DR: A classification of all the motion segmentation techniques into different categories according to their main principle and features is proposed, pointing out their strengths and weaknesses and suggesting further research directions.