We propose semantic model vectors, an intermediate level semantic representation, as a basis for modeling and detecting complex events in unconstrained real-world videos, such as those from YouTube. The semantic model vectors are extracted using a set of discriminative semantic classifiers, each being an ensemble of SVM models trained from thousands of labeled web images, for a total of 280 generic concepts. Our study reveals that the proposed semantic model vectors representation outperforms—and is complementary to—other low-level visual descriptors for video event modeling. We hence present an end-to-end video event detection system, which combines semantic model vectors with other static or dynamic visual descriptors, extracted at the frame, segment, or full clip level. We perform a comprehensive empirical study on the 2010 TRECVID Multimedia Event Detection task (http://www.nist.gov/itl/iad/mig/med10.cfm), which validates the semantic model vectors representation not only as the best individual descriptor, outperforming state-of-the-art global and local static features as well as spatio-temporal HOG and HOF descriptors, but also as the most compact. We also study early and late feature fusion across the various approaches, leading to a 15% performance boost and an overall system performance of 0.46 mean average precision. In order to promote further research in this direction, we made our semantic model vectors for the TRECVID MED 2010 set publicly available for the community to use (http://www1.cs.columbia.edu/~mmerler/SMV.html).

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE :Semantic Neighbor Graph Hashing for Multimodal Retrieval - 2018ABSTRACT:Hashing strategies are widely used for approximate nearest neighbor search in recent years due to its computational and storage effectiveness.
PROJECT TITLE :Her2Net A Deep Framework for Semantic Segmentation and Classification of Cell Membranes and Nuclei in Breast Cancer Evaluation - 2018ABSTRACT:We tend to gift an economical deep learning framework for identifying,
PROJECT TITLE :Diagnosing and Minimizing Semantic Drift in Iterative Bootstrapping Extraction - 2018ABSTRACT:Semantic drift is a common problem in iterative information extraction. Previous approaches for minimizing semantic drift
PROJECT TITLE : Hierarchy-Cutting Model based Association Semantic for Analyzing Domain Topic on the Web - 2017 ABSTRACT: Association link network (ALN) can organize huge Web info to provide several intelligent services in
PROJECT TITLE : SLED: Semantic Label Embedding Dictionary Representation for Multi label Image Annotation - 2015 ABSTRACT: Most existing strategies on weakly supervised image annotation depend upon jointly unsupervised feature

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry