Interactive Video Retrieval in the Age of Deep Learning – Detailed Evaluation of VBS 2019

Rossetto, Luca; Gasser, Ralph; Lokoč, Jakub; Bailer, Werner; Schoeffmann, Klaus; Muenzer, Bernd; Souček, Tomáš; Nguyen, Phuong Anh; Bolettieri, Paolo; Leibetseder, Andreas; Vrochidis, Stefanos

doi:10.1109/tmm.2020.2980944

Cited by 69 publications

(46 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sharing the same large-scale dataset 6 and evaluating each task simultaneously in one room, Video Browser Showdown [24,25,32] Poster Session B2: Deep Learning for Multimedia & Emerging Multimedia Applications MM '20, October 12-16, 2020, Seattle, WA, USA provides a reputable platform for comparative evaluations of various models and interactive search strategies. Each team participates with two tools/users cooperating on solving the currently evaluated task.…”

Section: Vbs 2020 Competition: Settings and Resultsmentioning

confidence: 99%

A W2VV++ Case Study with Automated and Interactive Text-to-Video Retrieval

Lokoč

Souček

Veselý

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

As reported by respected evaluation campaigns focusing both on automated and interactive video search approaches, deep learning started to dominate the video retrieval area. However, the results are still not satisfactory for many types of search tasks focusing on high recall. To report on this challenging problem, we present two orthogonal task-based performance studies centered around the state-of-the-art W2VV++ query representation learning model for video retrieval. First, an ablation study is presented to investigate which components of the model are effective in two types of benchmark tasks focusing on high recall. Second, interactive search scenarios from the Video Browser Showdown are analyzed for two winning prototype systems implementing a selected variant of the model and providing additional querying and visualization components. The analysis of collected logs demonstrates that even with the state-of-the-art text search video retrieval model, it is still auspicious to integrate users into the search process for task types, where high recall is essential. CCS CONCEPTS • Information systems → Video search.

show abstract

Section: Vbs 2020 Competition: Settings and Resultsmentioning

confidence: 99%

A W2VV++ Case Study with Automated and Interactive Text-to-Video Retrieval

Lokoč

Souček

Veselý

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…A first release of VISIONE [1,6], which participated in the 2019 edition of the Video Browser Showdown (VBS) [11], is described in details in [2]. VBS is an international video search competition that is held annually since 2012 [13].…”

Section: Introductionmentioning

confidence: 99%

VISIONE at Video Browser Showdown 2021

Amato

Bolettieri

Falchi

et al. 2021

MultiMedia Modeling

Self Cite

View full text Add to dashboard Cite

This paper presents the second release of VISIONE, a tool for effective video search on large-scale collections. It allows users to search for videos using textual descriptions, keywords, occurrence of objects and their spatial relationships, occurrence of colors and their spatial relationships, and image similarity. One of the main features of our system is that it employs specially designed textual encodings for indexing and searching video content using the mature and scalable Apache Lucene full-text search engine.

show abstract

“…As the volume of multimedia data increases, there is a need for valid experimental comparisons between competing approaches. The Video Browser Showdown (VBS) meets this need by providing a means of comparing interactive search systems using known-item search tasks over large video collections (partly) in front of a live audience [8]. In this work, we introduce an experimental VBS prototype developed by a DCU and HCMUS-based team participating for the first time.…”

Section: Introductionmentioning

confidence: 99%

A VR Interface for Browsing Visual Spaces at VBS2021

Tran

Nguyen

et al. 2021

MultiMedia Modeling

View full text Add to dashboard Cite

The Video Browser Showdown (VBS) is an annual competition in which each participant prepares an interactive video retrieval system and partakes in a live comparative evaluation at the annual MMM Conference. In this paper, we introduce Eolas, which is a prototype video/image retrieval system incorporating a novel virtual reality (VR) interface. For VBS'21, Eolas represented each keyframe of the collection by an embedded feature in a latent vector space, into which a query would also be projected to facilitate retrieval within a VR environment. A user could then explore the space and perform one of a number of filter operations to traverse the space and locate the correct result.

show abstract

Interactive Video Retrieval in the Age of Deep Learning – Detailed Evaluation of VBS 2019

Cited by 69 publications

References 61 publications

A W2VV++ Case Study with Automated and Interactive Text-to-Video Retrieval

A W2VV++ Case Study with Automated and Interactive Text-to-Video Retrieval

VISIONE at Video Browser Showdown 2021

A VR Interface for Browsing Visual Spaces at VBS2021

Contact Info

Product

Resources

About