A distributed Content-Based Video Retrieval system for large datasets

Saoudi, El Mehdi; Andaloussi, Said Jai

doi:10.1186/s40537-021-00479-x

Cited by 18 publications

(8 citation statements)

References 74 publications

(92 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study by Saoudi et al [18] provides an extensive performance evaluation of a CBVR method, exploring its effectiveness, the influence of key frame extraction, and the impact of real-time distributed computation. Several benchmark datasets, including HOLLYWOOD2 Human Actions and Scenes Dataset, HMDB51 Human Motion Database, UCF50 Action Recognition Data Set, and the Olympic Sports Dataset, were utilized to assess the CBVR approach.…”

Section: Discrete Cosine Transformmentioning

confidence: 99%

Content Based Video Retrieval using Deep Learning

Palanivelu,

Jagdale,

Dubey

et al. 2024

Preprint

View full text Add to dashboard Cite

Content-based video retrieval (CBVR) is part of a search engine which is widely utilized in everyday life for retrieving relevant images/frames from given large datasets. Generally, the existing methods don't give the relevance and expected images as per the query images and also require more computational time. The CBVR systems depend on the feature representation and similarity measurements. In this project, a CBVR system is developed using deep learning models. The convolutional neural network (CNN) is used to extract features from an input image/frame, and then comparing those features with images in datasets to retrieve similar images/frames. The process involves three main phases namely feature extraction, feature comparison, and retrieval. In feature extraction, the CNN is trained on a dataset of images to learn to extract features that are relevant to the task at hand. In feature comparison, the features extracted from the input image are compared to the features of the images in the database using a similarity measure such as Euclidean distance. Finally, in the retrieval phase, the most similar images/frames from the datasets are returned as the results. The CBVR is carried out using a pre-trained deep learning model, such as VGG16 or ResNet, which is used to train over large image datasets and can extract useful features from new images. In this project, the retrieval of images are carried out and the performance is evaluated based on accuracy, precision, recall. Various CCN models are experimented to perform result analysis. Keywords: Control based video retrieval, Deep learning, Convolutional Neural Network, Information Retrieval, Feature extraction, Inception V3, Feature selection

show abstract

Section: Discrete Cosine Transformmentioning

confidence: 99%

Content Based Video Retrieval using Deep Learning

Palanivelu,

Jagdale,

Dubey

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In 2021, Saoudi, E.M., and Jai-Andaloussi, S [16] introduced a unique CBVR model. Key frame extraction algorithms produce a concise, compact video representation containing significant, salient information about video content.…”

Section: Literature Surveymentioning

confidence: 99%

Novel Fuzzy Entropy Based Leaky Shufflenet Content Based Video Retrival System

Kavitha

Simon²,

Sumathy³

2023

Preprint

View full text Add to dashboard Cite

Developing Content-Based Video Retrieval (CBVR) for large-scale videos is a major challenge due to the enormous growth of video content on the internet. One of the major downfalls associated with CBVR is high search response time and low accuracy. In this paper, a Novel Fuzzy entropy based Leaky ShuffleNet CBVR system has been proposed to reduce the search response time and for high accuracy. The proposed system has three major phases i) Data Processing, ii) Feature Extraction and iii) Feature selection and iv) Similarity search. Initially, the video is processed using Apache storm to convert video into keyframes. Consequently, facial landmarks, head pose, and eye gaze, edges are extracted using various feature extraction techniques. The most relevant features are selected in the feature selection phase by using the Fuzzy entropy measure. Finally, based on the selected features Leaky ShuffleNet retrieve the relevant videos based on the user query. Experiments were performed on two different datasets such as Hollywood2 and UCF50 in three different setups (Single Node, Vertical Scaling, Horizontal Scaling). Several metrics were analyzed to measure the effectiveness of the suggested strategy, including recall, specificity, accuracy, precision, and the F-measure. According to experimental results, the proposed system has a search reaction time of 0.75 seconds, which is lower than the existing methods. The proposed method improves the overall accuracy by 1.2%, 2.5%, and 3.2% better than the existing ECBVR-ACNN, FALKON, and EE-CBVR respectively.

show abstract

“…Nevertheless, video retrieval studies that have been performed fall within the scope of the SQVR. [23][24][25][26][27][28] Naturally, video datasets that have been prepared are consist of single video clips. [29][30][31][32] How to deal with retrieving multilabel videos is one of the research interests of video retrieval studies.…”

Section: Akbacakmentioning

confidence: 99%

“…There are few content‐based multiple query retrieval studies at the image level 19‐22 . Nevertheless, video retrieval studies that have been performed fall within the scope of the SQVR 23‐28 . Naturally, video datasets that have been prepared are consist of single video clips 29‐32 .…”

Section: Introductionmentioning

confidence: 99%

A novel multilabel video retrieval method using multiple video queries and deep hash codes

Akbacak

2022

Concurrency and Computation

View full text Add to dashboard Cite

Most videos consist of multiple clips. Namely, videos usually have multiple spatio-temporal information. However, existing video datasets are of single video clips.Additionally, content-based video retrieval methods have been implemented based on a single query clip. However, a single query may not be sufficient for better expressing intention concerning the query. Besides, it narrows the capability to search for multiple semantics. How to deal with retrieving videos having multiple clips has not been adequately investigated. This study proposes a novel multilabel video retrieval method that utilizes multiple video clips as queries. Whatever the number of queries, it transforms a multi-query video retrieval into a single-query video retrieval. The method is independent of both the video features and distance metric types. However, we propose a deep video hashing method to achieve speed and efficiency. Experiments performed on three prepared multilabel video datasets have proven the effectiveness of the proposed method. The source codes of the study are public. K E Y W O R D Scontent-based video retrieval, multi-query optimal point, multiple video queries, objective space, video hashing INTRODUCTIONContent-based video retrieval (CBVR) is the process of retrieving videos from a video database by querying them based on visual and temporal content. The visual content is usually an object, face, color, texture, or scene at the frame level. On the other hand, the temporal content is an action type at the video level. Videos frames, each of which is an image, usually have multilabel characters. At the video level, the temporal relation between frames also expresses a piece of semantic information. 1,2 It is called action type. An activity on a football field other than playing football tends to the football semantic in terms of frame-level. However, at the video level, the action type is not football.Neglecting temporal dependencies is sometimes an obligation, but sometimes a deficiency. [3][4][5] For face or object retrieval, for example, it is not necessitated. [6][7][8][9] However, some CBVR studies fundamentally ignore temporal properties. Janwe et al. used video segmentation to get the video shots. 10 From each shot, keyframes that adequately represent the semantic meaning of each shot are extracted. Then the keyframe features are extracted and are trained in a multi-stream CNN classifier. Finally, the classification scores of each shot are fused to obtain the final class score. Similar studies are based on the shot boundary detection and keyframe extraction technique. 11,12 In such studies, video semantics are only considered on the frame level. There have been various studies considering spatio-temporal characteristics. [13][14][15][16][17] On the other hand, few studies only consider actions but ignore pixel-level features. 14,18 The most concise video scene with at least one semantic meaning at the video level is called a clip. Naturally, videos made up of clips are multilabel. The use of a single video clip qu...

show abstract

A distributed Content-Based Video Retrieval system for large datasets

Cited by 18 publications

References 74 publications

Content Based Video Retrieval using Deep Learning

Content Based Video Retrieval using Deep Learning

Novel Fuzzy Entropy Based Leaky Shufflenet Content Based Video Retrival System

A novel multilabel video retrieval method using multiple video queries and deep hash codes

Contact Info

Product

Resources

About