Related papers: Content-based Analysis of the Cultural Differences…
In January 2025, the U.S. government enacted a nationwide ban on TikTok, prompting a wave of American users -- self-identified as ``TikTok Refugees'' -- to migrate to alternative platforms, particularly the Chinese social media app RedNote…
The rise of a trending topic on Twitter or Facebook leads to the temporal emergence of a set of users currently interested in that topic. Given the temporary nature of the links between these users, being able to dynamically identify…
Rapid progress in adversarial learning has enabled the generation of realistic-looking fake visual content. To distinguish between fake and real visual content, several detection techniques have been proposed. The performance of most of…
Real-world user-generated short videos, especially those distributed on platforms such as WeChat Channel and TikTok, dominate the mobile internet. However, current large multimodal models lack essential temporally-structured, detailed, and…
Objects are entities we act upon, where the functionality of an object is determined by how we interact with it. In this work we propose a Dual Attention Network model which reasons about human-object interactions. The dual-attentional…
TikTok has skyrocketed in popularity over recent years, especially among younger audiences. However, there are public concerns about the potential of this platform to promote and amplify harmful content. This study presents the first…
Recent advances in Computer Vision and Deep Learning made possible the efficient extraction of a schema from frames of streaming video. As such, a stream of objects and their associated classes along with unique object identifiers derived…
Short video platforms like TikTok, Instagram Reels, and YouTube Shorts have gained immense popularity in the last few years and are responsible for a large and growing fraction of Internet traffic. We identify two unique opportunities for…
The goal of video-based person re-identification is to match two input videos, so that the distance of the two videos is small if two videos contain the same person. A common approach for person re-identification is to first extract image…
This study explores global video on demand content consumption patterns through a network-based approach. We used Netflix's 'TV-shows' ranking data, spanning 822 days across 71 countries, to construct a network where countries are…
To facilitate the research on intelligent and human-like chatbots with multi-modal context, we introduce a new video-based multi-modal dialogue dataset, called TikTalk. We collect 38K videos from a popular video-sharing platform, along with…
Recent tracking-by-detection approaches use deep object detectors as target detection baseline, because of their high performance on still images. For effective video object tracking, object detection is integrated with a data association…
Online narratives spread unevenly across platforms, with content emerging on one site often appearing on others, hours, days or weeks later. Existing cross-platform information diffusion models often treat platforms as isolated systems,…
With the rise of short video platforms as prominent channels for news dissemination, major platforms in China have gradually evolved into fertile grounds for the proliferation of fake news. However, distinguishing short video rumors poses a…
Social media users share billions of items per year, only a small fraction of which is geotagged. We present a data- driven approach for identifying non-geotagged content items that can be associated with a hyper-local geographic area by…
Short videos have become one of the leading media used by younger generations to express themselves online and thus a driving force in shaping online culture. In this context, TikTok has emerged as a platform where viral videos are often…
Recent advancements in video diffusion models based on Diffusion Transformers (DiTs) have achieved remarkable success in generating temporally coherent videos. Yet, a fundamental question persists: how do these models internally establish…
Location-based social media make it possible to understand social and geographic aspects of human activities. However, previous studies have mostly examined these two aspects separately without looking at how they are linked. The study aims…
Predicting the future popularity of online content is highly important in many applications. Preferential attachment phenomena is encountered in scale free networks.Under it's influece popular items get more popular thereby resulting in…
We present a methodology to support the analysis of culture from text such as news events and demonstrate its usefulness on categorizing news events from different categories (society, business, health, recreation, science, shopping,…