L
Lei Bao
Researcher at Chinese Academy of Sciences
Publications - 18
Citations - 410
Lei Bao is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: TRECVID & Interface (computing). The author has an hindex of 9, co-authored 18 publications receiving 365 citations. Previous affiliations of Lei Bao include Carnegie Mellon University.
Papers
More filters
Journal ArticleDOI
Multimedia classification and event detection using double fusion
TL;DR: This paper introduces a fusion scheme named double fusion, which simply combines early fusion and late fusion together to incorporate their advantages, and reports the best reported results to date.
Book ChapterDOI
Double fusion for multimedia event detection
TL;DR: This paper introduces a fusion scheme named double fusion, which combines early fusion and late fusion together to incorporate their advantages and results are reported on TRECVID MED 2010 and 2011 data sets.
Proceedings ArticleDOI
Beyond audio and video retrieval: towards multimedia summarization
Duo Ding,Florian Metze,Shourabh Rawat,Peter Schulam,Susanne Burger,Ehsan Younessian,Lei Bao,Michael G. Christel,Alexander G. Hauptmann +8 more
TL;DR: This paper extracts visual concept features and ASR transcription features from a given video, and develops a template-based natural language generation system to produce a textual recounting based on the extracted features.
Journal ArticleDOI
Boosted Near-miss Under-sampling on SVM ensembles for concept detection in large-scale imbalanced datasets
TL;DR: Experiments on TRECVID benchmark datasets show that the BNU-SVMs outperforms the previous methods significantly, which demonstrates that the SVM ensembles is a both effective and efficient solution to concept detection in large-scale imbalanced datasets.
Proceedings ArticleDOI
VideoMap: an interactive video retrieval system of MCG-ICT-CAS
TL;DR: This paper presents the highlights of the interactive video retrieval system VideoMap, which has a map based displaying interface, which gives the user a global view about the similarity relationships among the whole video collection, and provides an active annotating manner to quickly localize the potential positive samples.