An Image Retrieval System for Video

@inproceedings{Bolettieri2019AnIR,
  title={An Image Retrieval System for Video},
  author={Paolo Bolettieri and Fabio Carrara and Franca Debole and F. Falchi and Claudio Gennaro and Lucia Vadicamo and Claudio Vairo},
  booktitle={SISAP},
  year={2019}
}
Since the 1970’s the Content-Based Image Indexing and Retrieval (CBIR) has been an active area. Nowadays, the rapid increase of video data has paved the way to the advancement of the technologies in many different communities for the creation of Content-Based Video Indexing and Retrieval (CBVIR). However, greater attention needs to be devoted to the development of effective tools for video search and browse. In this paper, we present Visione, a system for large-scale video retrieval. The system… 

Efficient Content Based Video Retrieval System by Applying AlexNet on Key Frames

The proposed video retrieval system is based on the AlexNet model of CNN and color histogram, and extracted features from the frames are together to store in the feature vector, and shows a dramatic and outstanding performance.

References

SHOWING 1-10 OF 18 REFERENCES

An Approach to Content-Based Image Retrieval Based on the Lucene Search Engine Library

This paper proposes to exploit an approach to perform approximate similarity search in metric spaces developed by [3, 6] to set up a robust information retrieval system that combines full-text search with content-based image retrieval capabilities.

Video Search Based on Semantic Extraction and Locally Regional Object Proposal

A semantic concept-based video browsing system which mainly exploits the spatial information of both object and action concepts, using a deep neural network based on YOLO detector for action detection and developing a color-based sketch board to quickly remove irrelevant shots.

TRECVid Semantic Indexing of Video: A 6-year Retrospective

The data, protocol and metrics used for the main and the secondary tasks, the results obtained and the main approaches used by participants are described.

VISIONE at VBS2019

This paper encoding all the visual and textual descriptors extracted from the videos into (surrogate) textual representations that are then efficiently indexed and searched using an off-the-shelf text search engine.

Particular object retrieval with integral max-pooling of CNN activations

This work revisits both retrieval stages, namely initial search and re-ranking, by employing the same primitive information derived from the CNN, and significantly improves existing CNN-based recognition pipeline.

End-to-End Learning of Deep Visual Representations for Image Retrieval

This article uses a large-scale but noisy landmark dataset and develops an automatic cleaning method that produces a suitable training set for deep retrieval, and builds on the recent R-MAC descriptor, which can be interpreted as a deep and differentiable architecture, and presents improvements to enhance it.

On Influential Trends in Interactive Video Retrieval: Video Browser Showdown 2015–2017

This work presents the experience with a class of interactive video retrieval scenarios and the methodology to stimulate the evolution of new interactive video retrieved approaches, focusing on the years 2015–2017.

Revisiting SIRET Video Retrieval Tool

A major revision of the SIRET interactive video retrieval tool is presented, which employs three different query initialization approaches and provides several result visualization methods for effective navigation and browsing in sets of ranked keyframes.

Searching and annotating 100M Images with YFCC100M-HNfc6 and MI-File

An image search engine that allows searching by similarity about 100M images included in the YFCC100M dataset, and annotate query images, and the effectiveness of the metadata cleaning algorithm, to identify a relevant training set for annotation is demonstrated.

Interactive Search or Sequential Browsing? A Detailed Analysis of the Video Browser Showdown 2018

The results collected at the VBS evaluation server confirm that searching for one particular scene in the collection when given a limited time is still a challenging task for many of the approaches, and reveal that user-centric interfaces are still required to mediate access to specific content.