In the rapidly evolving landscape of digital content, the task of summarizing multimedia documents, which encompass textual, visual, and auditory elements, presents intricate challenges. These challenges include extracting pertinent information from diverse formats, maintaining the structural integrity and semantic coherence of the original content, and generating concise yet informative summaries. This paper introduces a novel framework for multimedia document summarization that capitalizes on the inherent structure of the document to craft coherent and succinct summaries. Central to this framework is the incorporation of a rhetorical structure for structural analysis, augmented by a graph-based representation to facilitate the extraction of pivotal information. Weighting algorithms are employed to assign significance values to document units, thereby enabling effective ranking and selection of relevant content. Furthermore, the framework is designed to accommodate user preferences and time constraints, ensuring the production of personalized and contextually relevant summaries. The summarization process is elaborately delineated, encompassing document specification, graph construction, unit weighting, and summary extraction, supported by illustrative examples and algorithmic elucidation. This proposed framework represents a significant advancement in automatic summarization, with broad potential applications across multimedia document processing, promising transformative impacts in the field.

As synthetic media becomes progressively more realistic and barriers to using it continue to lower, the technology has been increasingly utilized for malicious purposes, from financial fraud to nonconsensual pornography. Today, the principal defense against being misled by synthetic media relies on the ability of the human observer to visually and auditorily discern between real and fake. However, it remains unclear just how vulnerable people actually are to deceptive synthetic media in the course of their day to day lives. We conducted a perceptual study with 1276 participants to assess how accurate people were at distinguishing synthetic images, audio only, video only, and audiovisual stimuli from authentic. To reflect the circumstances under which people would likely encounter synthetic media in the wild, testing conditions and stimuli emulated a typical online platform, while all synthetic media used in the survey was sourced from publicly accessible generative AI technology. We find that overall, participants struggled to meaningfully discern between synthetic and authentic content. We also find that detection performance worsens when the stimuli contains synthetic content as compared to authentic content, images featuring human faces as compared to non face objects, a single modality as compared to multimodal stimuli, mixed authenticity as compared to being fully synthetic for audiovisual stimuli, and features foreign languages as compared to languages the observer is fluent in. Finally, we also find that prior knowledge of synthetic media does not meaningfully impact their detection performance. Collectively, these results indicate that people are highly susceptible to being tricked by synthetic media in their daily lives and that human perceptual detection capabilities can no longer be relied upon as an effective counterdefense.

AI-generated media has become a threat to our digital society as we know it. These forgeries can be created automatically and on a large scale based on publicly available technology. Recognizing this challenge, academics and practitioners have proposed a multitude of automatic detection strategies to detect such artificial media. However, in contrast to these technical advances, the human perception of generated media has not been thoroughly studied yet. In this paper, we aim at closing this research gap. We perform the first comprehensive survey into people's ability to detect generated media, spanning three countries (USA, Germany, and China) with 3,002 participants across audio, image, and text media. Our results indicate that state-of-the-art forgeries are almost indistinguishable from "real" media, with the majority of participants simply guessing when asked to rate them as human- or machine-generated. In addition, AI-generated media receive is voted more human like across all media types and all countries. To further understand which factors influence people's ability to detect generated media, we include personal variables, chosen based on a literature review in the domains of deepfake and fake news research. In a regression analysis, we found that generalized trust, cognitive reflection, and self-reported familiarity with deepfakes significantly influence participant's decision across all media categories.

Bing recently hit 100M daily users (and 100M chats)! Today, we're excited to share new AI-powered experiences that extend these capabilities to millions of additional people across devices and around the globe! In recent weeks, we've added a variety of new ways to access and interact with the new Bing. Today, we are announcing yet another, with powerful updates to SwiftKey that put the Bing AI experience one touch away across any iOS or Android mobile experience that supports a third-party keyboard. An updated SwiftKey represents a growing set of access points and improvements to Bing experiences, including new updates to existing app integrations spanning Bing, Skype, Microsoft Start, and Microsoft Edge apps.

As a highlighting research topic in the multimedia area, cross-media retrieval aims to capture the complex correlations among multiple media types. Learning better shared representation and distance metric for multimedia data is important to boost the cross-media retrieval. Motivated by the strong ability of deep neural network in feature representation and comparison functions learning, we propose the Unified Network for Cross-media Similarity Metric (UNCSM) to associate cross-media shared representation learning with distance metric in a unified framework. First, we design a two-pathway deep network pretrained with contrastive loss, and employ double triplet similarity loss for fine-tuning to learn the shared representation for each media type by modeling the relative semantic similarity. Second, the metric network is designed for effectively calculating the cross-media similarity of the shared representation, by modeling the pairwise similar and dissimilar constraints. Compared to the existing methods which mostly ignore the dissimilar constraints and only use sample distance metric as Euclidean distance separately, our UNCSM approach unifies the representation learning and distance metric to preserve the relative similarity as well as embrace more complex similarity functions for further improving the cross-media retrieval accuracy. The experimental results show that our UNCSM approach outperforms 8 state-of-the-art methods on 4 widely-used cross-media datasets.

On the heels of a report showing the inefficacy of government-run cyber security, it's imperative to understand the limitations of your system and model. As that article shows, in addition to bureaucratic risk the government also needs to worry about gaming-the-bureaucracy risk! Government snafus aside, data science has enjoyed considerable success in the past few years. Despite this success, models can fail in surprising ways. Last year we saw how deep neural nets for image recognition fail on noisy data.

RESTful services on the Web expose information through retrievable resource representations that represent self-describing descriptions of resources, and through the way how these resources are interlinked through the hyperlinks that can be found in those representations. This basic design of RESTful services means that for extracting the most useful information from a service, it is necessary to understand a service's representations, which means both the semantics in terms of describing a resource, and also its semantics in terms of describing its linkage with other resources. Based on the Resource Linking Language (ReLL), this paper describes a framework for how RESTful services can be described, and how these descriptions can then be used to harvest information from these services. Building on this framework, a layered model of RESTful service semantics allows to represent a service's information in RDF/OWL. Because REST is based on the linkage between resources, the same model can be used for aggregating and interlinking multiple services for extracting RDF data from sets of RESTful services.