VERGE in VBS 2020

Andreadis, Stelios; Moumtzidou, Anastasia; Apostolidis, Konstantinos; Gkountakos, Konstantinos; Galanopoulos, Damianos; Michail, Emmanouil; Gialampoukidis, Ilias; Vrochidis, Stefanos; Mezaris, Vasileios; Kompatsiaris, Ioannis

doi:10.1007/978-3-030-37734-2_69

Cited by 3 publications

(2 citation statements)

References 14 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluated the proposed method at the 9 th Video Browser Showdown (VBS) co-located with the 2020 International Conference on Multimedia Modeling during a dedicated, private session using 10 different interactive video retrieval systems [4,20,23,24,25,26,27,29,31,36] in one dedicated evaluation session. This session was split into two tracks with 10 participants in each, leaving one participant per system.…”

Section: Discussionmentioning

confidence: 99%

Considering Human Perception and Memory in Interactive Multimedia Retrieval Evaluations

Rossetto

Bailer

Bernstein

2021

MultiMedia Modeling

View full text Add to dashboard Cite

Experimental evaluations dealing with visual known-item search tasks, where real users look for previously observed and memorized scenes in a given video collection, represent a challenging methodological problem. Playing a searched "known" scene to users prior to the task start may not be sufficient in terms of scene memorization for re-identification (i.e., the search need may not necessarily be successfully "implanted"). On the other hand, enabling users to observe a known scene played in a loop may lead to unrealistic situations where users can exploit very specific details that would not remain in their memory in a common case. To address these issues, we present a proof-of-concept implementation of a new visual known-item search task presentation methodology that relies on a recently introduced deep saliency estimation method to limit the amount of revealed visual video contents. A filtering process predicts and subsequently removes information which in an unconstrained setting would likely not leave a lasting impression in the memory of a human observer. The proposed presentation setting is compliant with a realistic assumption that users perceive and memorize only a limited amount of information, and at the same time allows to play the known scene in the loop for verification purposes. The new setting also serves as a search clue equalizer, limiting the rich set of present exploitable content features in video and thus unifies the perceived information by different users. The performed evaluation demonstrates the feasibility of such a task presentation by showing that retrieval is still possible based on query videos processed by the proposed method. We postulate that such information incomplete tasks constitute the necessary next step to challenge and assess interactive multimedia retrieval systems participating at visual known-item search evaluation campaigns.

show abstract

Section: Discussionmentioning

confidence: 99%

Considering Human Perception and Memory in Interactive Multimedia Retrieval Evaluations

Rossetto

Bailer

Bernstein

2021

MultiMedia Modeling

View full text Add to dashboard Cite

show abstract

“…The visual analysis component consists of several machine learning (ML) models either trained from scratch or fine-tuned from other efforts. The model performing semantic segmentation (Qiu et al, 2021) on images was trained to extract semantic labels and percentages per pixel on images while the Verge classifier (Andreadis et al, 2020) was deployed to classify the images (or video frames) to one or more classes based on context.…”

Section: Nature Of Datamentioning

confidence: 99%

XR4DRAMA a knowledge-based system for disaster management and media planning

Vassiliades,

Stathopoulos-Kampilis,

Antzoulatos

et al. 2024

The Knowledge Engineering Review

View full text Add to dashboard Cite

In the previous two decades, Knowledge Graphs (KGs) have evolved, inspiring developers to build ever-more context-related KGs. Because of this development, Artificial Intelligence (AI) applications can now access open domain-specific information in a format that is both semantically rich and machine comprehensible. In this article, we introduce the XR4DRAMA framework. The KG of the XR4DRAMA framework can represent data for media preparation and disaster management. More specifically, the KG of the XR4DRAMA framework can represent information about: (a) Observations and Events (e.g., data collection of biometric sensors, information in photos and text messages), (b) Spatio-temporal (e.g., highlighted locations and timestamps), (c) Mitigation and response plans in crisis (e.g., first responder teams). In addition, we provide a mechanism that allows Points of Interest (POI) to be created or updated based on videos, photos, and text messages sent by users. For improved disaster management and media coverage of a location, POI serve as markers to journalists and first responders. A task creation mechanism is also provided for the disaster management scenario with the XR4DRAMA framework, which indicates to first responders and citizens what tasks need to be performed in case of an emergency. Finally, the XR4DRAMA framework has a danger zone creation mechanism. Danger zones are regions in a map that are considered as dangerous for citizens and first responders during a disaster management scenario and are annotated by a severity score. The last two mechanisms are based on a Decision Support System (DSS).

show abstract