Efficient video search using image queries

Araujo, André; Makar, Mina; Chandrasekhar, Vijay; Chen, D.; Tsai, Shiou‐Chuan; Chen, H.; Angst, Roland; Girod, Bernd

doi:10.1109/icip.2014.7025623

Cited by 18 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recent scene retrieval approaches use temporal aggregation methods to improve scalability and reduce memory requirements. [2,5] extract hand-crafted local features from frames, track them along time and aggregate them into a single vector. Other proposals [26,3,4] produce a single scene descriptor, which improves efficiency but involves a more difficult comparison against the static query image.…”

Section: Related Workmentioning

confidence: 99%

Dress Like a Star: Retrieving Fashion Products from Videos

García

Vogiatzis

2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

This work proposes a system for retrieving clothing and fashion products from video content. Although films and television are the perfect showcase for fashion brands to promote their products, spectators are not always aware of where to buy the latest trends they see on screen. Here, a framework for breaking the gap between fashion products shown on videos and users is presented. By relating clothing items and video frames in an indexed database and performing frame retrieval with temporal aggregation and fast indexing techniques, we can find fashion products from videos in a simple and non-intrusive way. Experiments in a large-scale dataset conducted here show that, by using the proposed framework, memory requirements can be reduced by 42.5X with respect to linear search, whereas accuracy is maintained at around 90%. 4

show abstract

Section: Related Workmentioning

confidence: 99%

Dress Like a Star: Retrieving Fashion Products from Videos

García

Vogiatzis

2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

show abstract

“…Apostolidis et al proposed a method for fast and accurate object detection in video and to use the GPU-based processing for the object detection part, new structure-based keyframe sampling technique, and SURF descriptors [25] robustified to scale variations [26]. Araujo et al addressed video search using image query and studied solutions to reduce storage requirements of the video database [27]. They proposed a compression algorithm and reported that the search quality was also improved by the storage reduction strategy.…”

Section: Other Methodsmentioning

confidence: 99%

Bayesian Exponential Inverse Document Frequency and Region-of-Interest Effect for Enhancing Instance Search Accuracy

Murata

Nagano

Hiramatsu

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this paper, we first analyze the discriminative power in the Best Match (BM) 25 formula and provide its calculation method from the Bayesian point of view. The resulting, derived discriminative power is quite similar to the exponential inverse document frequency (EIDF) that we have previously proposed [1] but retains more preferable theoretical advantages. In our previous paper [1], we proposed the EIDF in the framework of the probabilistic information retrieval (IR) method BM25 to address the instance search task, which is a specific object search for videos using an image query. Although the effectiveness of our EIDF was experimentally demonstrated, we did not consider its theoretical justification and interpretation. We also did not describe the use of region-of-interest (ROI) information, which is supposed to be input to the instance search system together with the original image query showing the instance. Therefore, here, we justify the EIDF by calculating the discriminative power in the BM25 from the Bayesian viewpoint. We also investigate the effect of the ROI information for improving the instance search accuracy and propose two search methods incorporating the ROI effect into the BM25 video ranking function. We validated the proposed methods through a series of experiments using the TREC Video Retrieval Evaluation instance search task dataset.

show abstract

“…There has been research in this area [1,6,7], but no practical system has emerged. We introduce a system that continuously indexes new videos and allows search using images.…”

Section: Introductionmentioning

confidence: 99%

Real-time query-by-image video search system

Araujo

Chen

Vajda

et al. 2014

Proceedings of the 22nd ACM International Conference on Multimedia

View full text Add to dashboard Cite

We demonstrate a novel multimedia system that continuously indexes videos and enables real-time search using images, with a broad range of potential applications. Television shows are recorded and indexed continuously, and iconic images from recent events are discovered automatically. Users can query an uploaded image or an image in the web. When a result is served, the user can play the video clip from the beginning or from the point in time where the retrieved image was found.

show abstract

Efficient video search using image queries

Cited by 18 publications

References 15 publications

Dress Like a Star: Retrieving Fashion Products from Videos

Dress Like a Star: Retrieving Fashion Products from Videos

Bayesian Exponential Inverse Document Frequency and Region-of-Interest Effect for Enhancing Instance Search Accuracy

Real-time query-by-image video search system

Contact Info

Product

Resources

About