• Publications
  • Influence
TRECVID 2015 - An Overview of the Goals, Tasks, Data, Evaluation Mechanisms and Metrics
The TREC Video Retrieval Evaluation (TRECVID) 2011 was a TREC-style video analysis and retrieval evaluation, the goal of which remains to promote progress in content-based exploitation of digitalExpand
TRECVID 2016: Evaluating Video Search, Video Event Detection, Localization, and Hyperlinking
TLDR
TRECVID 2016: Evaluating Video Search, Video Event Detection, Localization, and Hyperlinking George Awad, Jonathan Fiscus, David Joy, Martial Michel, Alan Smeaton, Wessel Kraaij, Maria Eskevich, Robin Aly, Roeland Ordelman, Marc Ritter, et al. Expand
TRECVID 2017: Evaluating Ad-hoc and Instance Video Search, Events Detection, Video Captioning and Hyperlinking
TLDR
Evaluating Ad-hoc and Instance Video Search, Events Detection, Video Captioning, and Hyperlinking George Awad, Asad Butt, Jonathan Fiscus, David Joy, Andrew Delgado, Willie Mcclinton, Martial Michel, Alan Smeaton, Yvette Graham, Wessel Kraaij, et al. Expand
TRECVID 2018: Benchmarking Video Activity Detection, Video Captioning and Matching, Video Storytelling Linking and Video Search
The TREC Video Retrieval Evaluation (TRECVID) 2018 was a TREC-style video analysis and retrieval evaluation, the goal of which remains to promote progress in research and development of contentbasedExpand
Evaluation of active learning strategies for video indexing
TLDR
Three active learning strategies for indexing concepts in video shots using subsets of a fully annotated dataset are compared and the "most probable" and "most uncertain" strategies are roughly equivalent for moderately difficult and difficult concepts. Expand
TRECVID 2019: An evaluation campaign to benchmark Video Activity Detection, Video Captioning and Matching, and Video Search & retrieval
TLDR
This paper is an introduction to the evaluation framework, tasks, data, and measures used in the TRECVID 2019, a TREC-style video analysis and retrieval evaluation. Expand
Video Corpus Annotation Using Active Learning
TLDR
This paper describes the collaborative annotation system used to annotate the High Level Features (HLF) in the development set of TRECVID 2007 and shows that Active Learning allows simultaneously getting the most useful information from the partial annotation and significantly reducing the annotation effort per participant relatively to previous collaborative annotations. Expand
Particle image velocimetry with optical flow
Abstract An optical Flow technique based on the use of Dynamic Programming has been applied to Particle Image Velocimetry thus yielding a significant increase in the accuracy and spatial resolutionExpand
The 'orthogonal algorithm' for optical flow detection using dynamic programming
  • G. Quénot
  • Computer Science
  • [Proceedings] ICASSP-92: IEEE International…
  • 23 March 1992
TLDR
An algorithm for optical flow detection based on an iterative search for a displacement field that minimizes the L/sub 1/ or L/ sub 2/ distance between two images that provides very-high-quality matching for calibrated patterns as well as for human visual sensation. Expand
...
1
2
3
4
5
...