IBM Research TRECVID-2003 Video Retrieval System

By Apostol Natsev, John R. Smith, Jelena Tešić, Lexing Xie, Rong Yan, Wei Jiang, Michele Merler. TREC Video Retrieval Evaluation, 2003

435 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/1f7121aa31b5462f0ad308363b4a718d83d51d0d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Survey on Visual Content-Based Video Indexing and Retrieval (2011, methodology): “[222] compute color histogram and color moments for video retrieval and concept detection.”
Multimodal Fusion for Video Search Reranking (2010, background): “The earlier work [6], [7], [8], [9], [10], [11], which is based on relevance feedback (RF) strategy, focuses mainly on the refinement of the initial search results in an interactive fashion.”
Video search reranking via information bottleneck principle (2006, methodology): “score threshold es and linearly stretching those scores above or under es to be within [0, 1].”
Unified Video Annotation via Multigraph Learning (2009, methodology): “For example, Wang et al. [38] have shown the effectiveness of combining different features and Amir et al. [2] have integrated different learning algorithms, including support vector machine, Gaussian mixture model, maximum entropy methods, a modified nearest neighbor method, and multiple-instance l”
Early versus late fusion in semantic video analysis (2005, methodology): “To cope with both issues, a recent trend in semantic video analysis are generic indexing approaches using machine learning [1] [3] [6] [9] [10].”
Correlative multi-label video annotation (2007, unknown): “This is one of the most widely used data sets by many groups in the area of multimedia concept modeling[2][3][7].”
Concept-Based Video Retrieval (2009, methodology): “They explore synergy with other classifiers such as Gaussian mixture models [1], neural networks [6], Fisher’s linear discriminant [219], and logistic regression [219].”
XRCE ’ s participation to ImagEval (2007, background): “The visual vocabulary provides a “mid-level” representation which helps to bridge the semantic gap between the low-level features extracted from an image and the high-level concepts to be categorized [2].”
A Discriminative Kernel-Based Approach to Rank Images from Text Queries (2008, background): “This classification problem is typically addressed using Support Vector Machines (SVMs) [33], [46] or boosting classifiers [43], as these large margin approaches enjoy good generalization properties [45].”