The challenge problem for automated detection of 101 semantic concepts in multimedia

By Cees G. M. Snoek, Marcel Worring, Jan van Gemert, Jan-Mark Geusebroek, Arnold M. W. Smeulders. ACM Multimedia, 2006

688 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/6ab5acb5f32ef2d28f91109d40e5e859a9c101bf

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Exploring Context and Content Links in Social Media: A Latent Space Method (2012, background): “There are the following two different fusion strategy—early-fusion and late-fusion [23].”
A Review on Multi-Label Learning Algorithms (2014, background): “During the past decade, multi-label learning has gradually attracted significant attentions from machine learning and related communities and has been widely applied to diverse problems from automatic annotation for multimedia contents including image [1], [7], [13], [93], [170], [171], [174], audio”
Performance evaluation of local colour invariants (2009, neutral): “Their study provides a theoretical overview of photometric invariant properties, and an evaluation of various colour SIFT descriptor on PASCAL VOC [32] data and TREC-VID data [ 59 ].”
An extensive experimental comparison of methods for multi-label learning (2012, methodology): “Mediamill [36] originates from the 2005 NIST TRECVID challenge dataset, 2 which contains data about annotated videos.”
Lift: Multi-Label Learning with Label-Specific Features (2011, background): “…and related communities, which has been successfully applied to diverse applications such as bioinformatics [1], [5], multimedia contents analysis including image [3], [4], [49], audio [27], [34], [42], and video [35], [41], [48], web mining [25], [33], [36], information retrieval [52], [54], etc.”
Mining Multi-label Data (2010, background): “043 6555 [5] rcv1v2 (avg) text 6000 0 47234 101 2.”
Script Data for Attribute-Based Recognition of Composite Activities (2012, background): “In the multimedia community, MediaMill[24] and LSCOM[25] are efforts to explore large scale video retrieval using mid-level concepts and exploring combination of textual and visual information.”
Privacy-Preserving Bandits (2019, methodology): “Additionally, as the multi-label clas-siﬁcation experiments (Figure 6) indicate, the performance gap between the non-private and differentially-private settings seems to be shrinking to within 3.6% and 2.6% for the text mining and MediaMill tasks respectively.”
Combining instance-based learning and logistic regression for multilabel classification (2009, background): “The trained classifier should be able to categorize an unseen instance to some of these 101 labels, e.g., face, car, male, soccer, and so on. More details about this data set can be found at Snoek et al. (2006) .”
A Survey on Visual Content-Based Video Indexing and Retrieval (2011, background): “Video annotation [4], [117], [241] is the allocation of video shots or video segments to different predefined semantic con-”
Kernel Codebooks for Scene Categorization (2008, background): “[17], who draw inspiration from Naphade and Huang [18].”
Multi-label Learning with Missing Labels Using Mixed Dependency Graphs (2018, methodology): “2006) and MediaMill (Snoek et al. 2006), with a semantic hierarchy drawn from Wordnet (Fellbaum 1998).”