A Survey on Visual Content-Based Video Indexing and Retrieval

By Weiming Hu, Nianhua Xie, Li Li, Xianglin Zeng, S. Maybank. IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews), 2011

665 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9b64f980a95806460b1056e91bd6c017226613b4

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

1. Tao Mei
2. Dacheng Tao
3. Xuelong Li
4. Luc Van Gool
5. Xiaogang Wang
6. Tat-seng Chua
7. Wu Liu
8. Xinchen Liu

Citations in the corpus

• Toward Scalable Systems for Big Data Analytics: A Technology Tutorial (2014, background): “Multimedia indexing and retrieval concerns the description, storage, and organization of multimedia information to help people find multimedia resources conveniently and quickly [218].”
• Summarization of Egocentric Videos: A Comprehensive Survey (2017, background): “Whereas TPV segmentation approaches typically try to identify the shot boundaries comparing consecutive frames, or even using the frames’ time-stamp [33], [34], this methodology cannot be directly applied over FPV, since egocentric videos consist of a single shot with extremely smooth transitions be”
• Big Data: A Survey (2014, methodology): “Generally, multimedia indexing and retrieval include five procedures: structural analysis, feature extraction, data mining, classification and annotation, query and retrieval [131].”
• Focus: Querying Large Video Datasets with Low Latency and Low Cost (2018, background): “A large body of works in multimedia and information retrieval research propose various content-based video indexing and retrieval techniques to facilitate queries on videos (e.g., [40,48,68,69]).”
• Distance based similarity models for content based multimedia retrieval (2013, methodology): “In general, similarity models play a fundamental role in any multimedia retrieval approach, such as content-based approaches to image retrieval [Smeulders et al., 2000, Datta et al., 2008], video retrieval [Hu et al., 2011], and audio retrieval [Mitrovic et al., 2010].”
• Extracting code from programming tutorial videos (2016, background): “Automatic understanding of general video content is a challenging problem [6].”
• Optical flow modeling and computation: A survey (2015, background): “Optical flow can also be a determinant feature in video indexing and retrieval [123,202,230].”
• Video Summarization Using Deep Neural Networks: A Survey (2021, methodology): “[6] classify the summarization methods into those that target minimum visual redundancy, those that rely on object or event detection, and others that are based on multimodal integration.”
• Reducto: On-Camera Filtering for Resource-Efficient Real-Time Video Analytics (2020, background): “Table 2 shows a representative list [37] of (high- and low-level) features we considered, and summarizes their computation overheads (in terms of fps) in both on-camera and server settings.”
• PROVID: Progressive and Multimodal Vehicle Reidentification for Large-Scale Urban Surveillance (2018, background): “image retrieval [8], [9], content-based video search [10], and object instance search [11], vehicle Re-Id is to find the vehi-”