Content-based multimedia information retrieval: State of the art and challenges

By Michael S. Lew, Nicu Sebe, C. Djeraba, Ramesh C. Jain. 2006

1,837 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Image-Based Recommendations on Styles and Substitutes (2015, methodology): “We label the process we develop for exploiting this data a visual and relational recommender system as we aim to model human visual preferences, and the system might be used to recommend one object on the basis of a user’s apparent interest in another.”
Self-taught hashing for fast similarity search (2010, methodology): “It is of great importance to many Information Retrieval (IR) [30] applications, such as near-duplicate detection [18], plagiarism analysis [43], collaborative filtering [26], caching [32], and content-based multimedia retrieval [28].”
Describable Visual Attributes for Face Verification and Image Search (2011, neutral): “Early work in appearance-based face verification [29], [57] looked at the L 2 distance between pairs of images in a lower-dimensional subspace obtained using Principal Components Analysis (PCA).”
Finding meaning on YouTube: Tag recommendation and category discovery (2010, background): “Image Annotation: In the context of content-based multimedia information retrieval, researchers use visual features to search large image collections [12].”
Image retrieval: Ideas, influences, and trends of the new age (2008, neutral): “Multimedia information retrieval, as a broader research area covering video, audio, image, and text analysis has been extensively surveyed [Sebe et al. 2003; Lew et al. 2006].”
HashNet: Deep Learning to Hash by Continuation (2017, methodology): “Parallel to the traditional indexing methods [21], another advantageous solution is hashing methods [35], which transform high-dimensional media data into compact binary codes and generate similar binary codes for similar data items.”
NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing (2018, background): “Fast and accurate similarity search is at the core of many information retrieval applications, such as plagiarism analysis (Stein et al., 2007), collaborative filtering (Koren, 2008), content-based multimedia retrieval (Lew et al., 2006) and caching (Pandey et al., 2009).”
A Multimedia Retrieval Framework Based on Semi-Supervised Ranking and Relevance Feedback (2012, neutral): “In recent years, researchers also proposed numerous content-based retrieval systems for new media types, including 3D data, cultural artifacts, motion data, and biological data [4], [20], [22].”
A Visual Analytics Approach Using the Exploration of Multidimensional Feature Spaces for Content-Based Medical Image Retrieval (2015, background): “[22] suggested that the ability of humans to explore and understand retrieved images is hindered by the gap in search systems that leverage user experiences and knowledge.”
Structure-Measure: A New Way to Evaluate Foreground Maps (2017, methodology): “Image Retrieval Application We use the publicly available content based image retrieval system LIRE (Lew et al., 2000) as our application.”
Deep Cauchy Hashing for Hamming Space Retrieval (2018, methodology): “Parallel to the traditional indexing methods [18] for candidates pruning, another advantageous solution is hashing methods [31] for data compression, which transform high-dimensional media data into compact binary codes and generate similar binary codes for similar data items.”
A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, neutral): “[2] in 2000, [20] in 2002, [21] in 2004, [22] in 2006, [23] in 2007, [24] in 2008, [25] in 2014 and [26] in 2017.”
Multimodal Fusion for Video Search Reranking (2010, methodology): “In this paper, we present a flexible and effective reranking method, called CR-Reranking, to improve the retrieval effectiveness.”
Remote Sensing Image Retrieval With Global Morphological Texture Descriptors (2014, background): “For an in-depth study of the issues related to CBIR and comprehensive reviews of the field, the reader is referred to [8]–[10].”
Audio event and scene recognition: A unified approach using strongly and weakly labeled data (2016, background): “These include but are not limited to content based indexing and retrieval of multimedia recordings [2], [3], [4], improving human computer (robot) interaction by making computers (robots) aware of acoustic scene or”