In 2026, the Multimedia Modeling conference in Prague hosted the fifteenth edition of the Video Browser Showdown (VBS) competition. Yet, for the first time, two participating systems implemented full-scale interaction logging frameworks, enabling a detailed analysis of the search process beyond traditional score-based evaluation. In this paper, both systems are introduced and described with a focus on their user interactions. To enable compact presentation and analysis of logs, all interaction types are further grouped into more abstract events, forming an interaction taxonomy hierarchy. Finally, we reveal the applied search strategies and analyze which factors drive success and failure. The results reveal a clear dominance of iterative, high-frequency text query reformulation with result set inspection, leveraging the power of modern CLIP-based models across most competition categories. In around 10% of cases, users also relied on advanced system features to achieve good performance at VBS, mostly on challenging homogeneous datasets.

Unlike traditional retrieval, dynamic exploration of multimedia collections may require complex aggregation queries whose performance is highly sensitive to dataset size, filters and grouping applied at any time. Such queries often yield unstable response times, thus undermining interactivity. Inspired by the online aggregation approach from the database community, we investigate whether progressively refined intermediate results, accompanied by quality estimates, can enable users to decide whether to accept partial results or continue processing. We evaluate this approach within the Multidimensional Media Model, where media collections are explored through metadata tagsets and hierarchies. Our study analyses operator placement, showing that moving deduplication and grouping from the database to the server reduces time-to-first-result by over 90% while maintaining steady quality improvement. We further examine join ordering and selectivity estimation for reliable progress prediction. Our results demonstrate that online aggregation principles can substantially improve responsiveness in multimedia exploration systems.

Exquisitor is an interactive multimedia retrieval platform that unites deep learning of visual, textual, and multimodal embeddings with conversational search and relevance feedback, enabling rapid, exploratory navigation of large video collections. Successive competition cycles, most notably the Video Browser Showdown (VBS) and Lifelog Search Challenge (LSC), have driven its evolution, culminating in a redesigned “text-first, feedback-second” workflow and a grouping view that clusters keyframes by video, giving users an immediate, context-rich overview. These changes markedly boosted expert performance, yet a clear proficiency gap persists between experts and novices. The upcoming VR4B session will focus on novices alone, providing a controlled setting to pinpoint the remaining barriers and guide the next round of interface and onboarding refinements.

We introduce multiXview, an interactive retrieval framework for synchronized multi-camera video collections. It features a multi-index search engine that supports natural-language queries over visual embeddings, speech transcripts, and scene descriptions. It supports a synchronized multi-stream player offering parallel playback, and a timeline-based navigation view for temporal scoping and faceted exploration. These components address the redundancy and fragmentation of overlapping egocentric and exocentric video feeds and enable users to locate, aggregate, and reconstruct events across partial perspectives. This paper focuses on system design and implementation, with quantitative and qualitative evaluation to take place at the CASTLE 2025 Grand Challenge Interactive Track.

The Exquisitor search system employs two distinct paradigms for searching media collections: conversational search and user relevance feedback. These paradigms can be used independently or cooperatively within the search process. While we posit that these techniques are complementary, as conversational search can find specific examples for relevance feedback and relevance feedback can help the user better understand the collection and lead to improved queries, empirical user behavior in real-world search scenarios remains poorly understood. To explore how these approaches interact within Exquisitor, we must gather more data about user actions during sessions, as well as their post-session feedback on the system. At IVR4B, we intend to obtain this information through user interaction logs and postsession interviews.

The way we create, consume and interact with multimedia content has changed significantly in recent years with the advent of affordable recording devices and easy sharing and access in the form of mobile phones. With the imminent wave of affordable devices that enable mixed reality experiences and the large variety of devices on the market, interaction with multimedia content is expected to continue to evolve rapidly. This will also drastically affect the entire area of multimedia information retrieval in eXtended Reality (XR), for instance by novel ways to express user needs in VR, result presentation that takes the specific capabilities of XR devices into account, and/or result feedback. This tutorial on Multimedia Retrieval in XR discusses and demonstrates existing solutions and highlights key challenges in this evolving field.

User relevance feedback is an important component of the multimedia analytics toolbox. In the Exquisitor project, we have primarily focused on the scalability of user relevance feedback over media collections. We have also, however, developed a proof-of-concept user interface and applied the system in interactive retrieval competitions. In this short paper, we describe the main user interface components of the Exquisitor system, along with anecdotal evidence about their effectiveness, or lack thereof.

This companion paper supports the replication of the development and evaluation of “MeTILDA - Platform for Melodic Transcription in Language Documentation and Application” that we presented in the ICMR 2021. MeTILDA aims to help document and analyze pitch patterns of endangered languages including Blackfoot, whose prosodic system is characterized by pitch movements. It develops a new form of audio analysis (termed MeT scale which is a perceptual scale) and automates the process of creating visual aids (Pitch Art) to provide more effective visuals of perceived changes in pitch movement. In this paper, we explain the file structure of the source code and publish the details of our data as well as system operations. Moreover, we provide a link to the demo video for facilitating the use of our platform.

User Relevance Feedback (URF) is a class of interactive learning methods that rely on the interaction between a human user and a system to analyze a media collection. To improve URF system evaluation and design better systems, it is important to understand the impact that different interaction strategies can have. Based on the literature and observations from real user sessions from the Lifelog Search Challenge and Video Browser Showdown, we analyze interaction strategies related to (a) labeling positive and negative examples, and (b) applying filters based on users' domain knowledge. Experiments show that there is no single optimal labeling strategy, as the best strategy depends on both the collection and the task. In particular, our results refute the common assumption that providing more training examples is always beneficial: strategies with a smaller number of prototypical examples lead to better results in some cases. We further observe that while expert filtering is unsurprisingly beneficial, aggressive filtering, especially by novice users, can hinder the completion of tasks. Finally, we observe that combining URF with filters leads to better results than using filters alone.

Analyzing multimedia collections in order to gain insight is a common desire amongst industry and society. Recent research has shown that while machines are getting better at analyzing multimedia data, they still lack the understanding and flexibility of humans. A central conjecture in Multimedia Analytics is that interactive learning is a key method to bridge the gap between human and machine. We investigate the requirements and design of the Exquisitor system, a very large-scale interactive learning system that aims to verify the validity of this conjecture. We describe the architecture and initial scalability results for Exquisitor, and propose research directions related to both performance and result quality.

In this demonstration, we present Exquisitor, a media explorer capable of learning user preferences in real-time during interactions with the 99.2 million images of YFCC100M. Exquisitor owes its efficiency to innovations in data representation, compression, and indexing. Exquisitor can complete each interaction round, including learning preferences and presenting the most relevant results, in less than 30 ms using only a single CPU core and modest RAM. In short, Exquisitor can bring large-scale interactive learning to standard desktops and laptops, and even high-end mobile devices.