W2VV++ BERT Model at VBS 2021

Peška, Ladislav; Kovalčík, Gregor; Souček, Tomáš; Škrhák, Vít; Lokoč, Jakub

doi:10.1007/978-3-030-67835-7_46

Cited by 8 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In vitrivr, users can specify multiple temporally ordered queries which are independently evaluated and then aggregated with the scoring function rewarding videos which have matching segments for the individual queries in the correct order [17]. VIRET uses a context-aware ranking model [44] which requires that all independently formulated queries should be sufficiently answered by a segment of a video. Many teams allow users to specify two ordered queries, which are then executed independently.…”

Section: Fusion Approachesmentioning

confidence: 99%

Interactive video retrieval evaluation at a distance: comparing sixteen interactive video search systems in a remote setting at the 10th Video Browser Showdown

Heller

Gsteiger

Bailer

et al. 2022

Int J Multimed Info Retr

Self Cite

View full text Add to dashboard Cite

The Video Browser Showdown addresses difficult video search challenges through an annual interactive evaluation campaign attracting research teams focusing on interactive video retrieval. The campaign aims to provide insights into the performance of participating interactive video retrieval systems, tested by selected search tasks on large video collections. For the first time in its ten year history, the Video Browser Showdown 2021 was organized in a fully remote setting and hosted a record number of sixteen scoring systems. In this paper, we describe the competition setting, tasks and results and give an overview of state-of-the-art methods used by the competing systems. By looking at query result logs provided by ten systems, we analyze differences in retrieval model performances and browsing times before a correct submission. Through advances in data gathering methodology and tools, we provide a comprehensive analysis of ad-hoc video search tasks, discuss results, task design and methodological challenges. We highlight that almost all top performing systems utilize some sort of joint embedding for text-image retrieval and enable specification of temporal context in queries for known-item search. Whereas a combination of these techniques drive the currently top performing systems, we identify several future challenges for interactive video search engines and the Video Browser Showdown competition itself.

show abstract

Section: Fusion Approachesmentioning

confidence: 99%

Interactive video retrieval evaluation at a distance: comparing sixteen interactive video search systems in a remote setting at the 10th Video Browser Showdown

Heller

Gsteiger

Bailer

et al. 2022

Int J Multimed Info Retr

Self Cite

View full text Add to dashboard Cite

show abstract

“…We use both models to assign color terms to each pixel and then calculate the dominant colors for each of the 7x7 image cells. Finally, taking inspiration from [13] we are deploying in our system the CLIP features [14], aggregated through time, for text-to-video retrieval. In fact, with the increased dataset size, we need to better understand fine-grained actions.…”

Section: Changes To Some Features Used In Visionementioning

confidence: 99%

“…Therefore, we modified our user interface to improve the visualization and browsing of the results. In particular, inspired by other systems participating at VBS (e.g., [13,9]) we decided to place the search interface side by side with the browsing interface (respectively on the left and right of the GUI) and to display the search results by grouping those from the same video on a single row (Fig. 2).…”

Section: New User Interfacementioning

confidence: 99%