FIVR: Fine-Grained Incident Video Retrieval

Kordopatis-Zilos, Giorgos; Papadopoulos, Symeon; Patras, Ioannis; Kompatsiaris, Ioannis

doi:10.1109/tmm.2019.2905741

Cited by 52 publications

(36 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the refine stage, an m-Pattern-based Dynamic Programming scheme was devised to localize near-duplicate segments and to re-rank results of the filter stage. Yang et al [57] proposed a multi-scale video sequence matching method, which [29] 11,256 11,503 Video Copy Detection VCDB [19] 528 100,528 Partial Video Copy Detection EVVE [38] 620 102,375 Event Video Retrieval FIVR-200K [26] 100 225,960 Fine-grained Incident Video Retrieval Table 4.4: Publicly available video datasets developed for retrieval tasks related to NDVR.…”

Section: Filter-and-refine Matchingmentioning

confidence: 99%

“…Finally, the FIVR-200K [26] dataset was developed to simulate the problem of Fine-grained Incident Video Retrieval (FIVR). For the dataset collection, the major events occurring in the time span from January 2013 to December 2017 were collected by crawling Wikipedia.…”

Section: Benchmark Datasetsmentioning

confidence: 99%

“…In the present work, all videos annotated with any symbol but X are considered near-duplicates. The dataset contains a total of 13,129 videos consisting of 397,965 keyframes.In addition, we use the FIVR-200K[26] dataset for validating the results on a second independent dataset. It consists of 225,960 videos collected based on the 4,687 events, and contains 100 video queries.Table 4.5 depicts the annotation labels used in the dataset and their definitions.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Finding Near-Duplicate Videos in Large-Scale Collections

Kordopatis-Zilos

Papadopoulos

Patras

et al. 2019

Video Verification in the Fake News Era

Self Cite

View full text Add to dashboard Cite

This chapter discusses the problem of Near-Duplicate Video Retrieval (NDVR). The main objective of a typical NDVR approach is: given a query video, retrieve all near-duplicate videos in a video repository and rank them based on their similarity to the query. Several approaches have been introduced in the literature, which can be roughly classified in three categories based on the level of video matching, i.e. (i) video-level, (ii) frame-level and (iii) filter-and-refine matching. Two methods based on video-level matching are presented in this chapter. The first is an unsupervised scheme that relies on a modified Bag-of-Word (BoW) video representation. The second is a supervised method based on Deep Metric Learning (DML). For the development of both methods, features are extracted from the intermediate layers of Convolutional Neural Networks and leveraged as frame descriptors, since they offer a compact and informative image representation, and lead to increased system efficiency. Extensive evaluation has been conducted on publicly available benchmark datasets, and the presented methods are compared with state-of-art approaches, achieving the best results in all evaluation setups.

show abstract

Section: Filter-and-refine Matchingmentioning

confidence: 99%

Section: Benchmark Datasetsmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Finding Near-Duplicate Videos in Large-Scale Collections

Kordopatis-Zilos

Papadopoulos

Patras

et al. 2019

Video Verification in the Fake News Era

Self Cite

View full text Add to dashboard Cite

show abstract

“…This method has the disadvantage of losing video time information. Another kind of method is the video retrieval method for specific video content [7][8].…”

Section: Introductionmentioning

confidence: 99%

Video Key Frame Monitoring Algorithm and Virtual Reality Display Based on Motion Vector

Wang

Zhu

2020

IEEE Access

View full text Add to dashboard Cite

In this paper, a motion vector-based video key frame detection algorithm is proposed to solve the problem of miss election and missing selection caused by the difficulty in detecting the moving target characteristics of the video key frame. Firstly, the entropy of adjacent frame difference and the twodimensional entropy of image are introduced, and the combination of the two is taken as the measurement of the difference between video frames. Secondly, outliers are detected by statistical tools to obtain the lens boundary, thus realizing the adaptive lens detection of video content. Then, ViBe algorithm is used to detect the foreground object in the video sequence and extract the scale-invariant feature transformation features of the foreground moving object. Finally, the motion vector is introduced, and the sum of the block matching results is motion vector by partitioning the two adjacent frames and performing block matching. The magnitude of motion vector reflects the intensity of motion in the video, so active and inactive motion regions are obtained, and the similarity of video frames is calculated according to the defined formula, and key frames are extracted in these regions respectively. The experimental results show that the detection algorithm proposed in this paper improves the video results with rich motion information obviously, and the objective indexes and subjective scores are improved to some extent, which improves the universality of the algorithm. In addition, this paper also studies the display mode of key frame extraction results in virtual reality environment. The key frame display mode of video in virtual reality is optimized mainly by changing the display mode of information and changing the scene and testing the result of user task execution.INDEX TERMS Video; key Frame; monitoring algorithm; virtual reality display; motion vector.

show abstract

“…Also, for realizing retrieval of new contents, it is necessary to prepare an enormous amount of training annotation data. Content-based methods [8]- [10], [20]- [23], which retrieve contents by computing similarities in content spaces, have recently attracted attention with the development of deep learning techniques [24], [25]. Since content-based methods do not rely on annotated information but directly use content information, they tend to overcome the above-mentioned problems [26], [27].…”

Section: Introductionmentioning

confidence: 99%

Query is GAN: Scene Retrieval With Attentional Text-to-Image Generative Adversarial Network

et al. 2019

View full text Add to dashboard Cite

Scene retrieval from input descriptions has been one of the most important applications with the increasing number of videos on the Web. However, this is still a challenging task since semantic gaps between features of texts and videos exist. In this paper, we try to solve this problem by utilizing a textto-image Generative Adversarial Network (GAN), which has become one of the most attractive research topics in recent years. The text-to-image GAN is a deep learning model that can generate images from their corresponding descriptions. We propose a new retrieval framework, ''Query is GAN'', based on the textto-image GAN that drastically improves scene retrieval performance by simple procedures. Our novel idea makes use of images generated by the text-to-image GAN as queries for the scene retrieval task. In addition, unlike many studies on text-to-image GANs that mainly focused on the generation of high-quality images, we reveal that the generated images have reasonable visual features suitable for the queries even though they are not visually pleasant. We show the effectiveness of the proposed framework through experimental evaluation in which scene retrieval is performed from real video datasets. INDEX TERMS Scene retrieval, deep learning, generative adversarial network, text-to-image translation.

show abstract

FIVR: Fine-Grained Incident Video Retrieval

Cited by 52 publications

References 42 publications

Finding Near-Duplicate Videos in Large-Scale Collections

Finding Near-Duplicate Videos in Large-Scale Collections

Video Key Frame Monitoring Algorithm and Virtual Reality Display Based on Motion Vector

Query is GAN: Scene Retrieval With Attentional Text-to-Image Generative Adversarial Network

Contact Info

Product

Resources

About