Related papers: SWaT: Statistical Modeling of Video Watch Time thr…
Real-time understanding of continuous video streams is essential for interactive assistants and multimodal agents operating in dynamic environments. However, most existing video reasoning approaches follow a batch paradigm that defers…
Prior work has established Test-Time Training (TTT) as a general framework to further improve a trained model at test time. Before making a prediction on each test instance, the model is first trained on the same instance using a…
This work addresses the problem of Social Activity Recognition (SAR), a critical component in real-world tasks like surveillance and assistive robotics. Unlike traditional event understanding approaches, SAR necessitates modeling individual…
Choice decisions made by users of online applications can suffer from biases due to the users' level of engagement. For instance, low engagement users may make random choices with no concern for the quality of items offered. This biased…
Video surveillance is a well researched area of study with substantial work done in the aspects of object detection, tracking and behavior analysis. With the abundance of video data captured over a long period of time, we can understand…
Video anomaly detection is to determine whether there are any abnormal events, behaviors or objects in a given video, which enables effective and intelligent public safety management. As video anomaly labeling is both time-consuming and…
Unlike popular videos, which would have already achieved high viewership numbers by the time they are declared popular, YouTube trending videos represent content that targets viewers attention over a relatively short time, and has the…
Prefetching web pages is a well-studied solution to reduce network latency by predicting users' future actions based on their past behaviors. However, such techniques are largely unexplored on mobile platforms. Today's privacy regulations…
Video quality assessment (VQA) is an important processing task, aiming at predicting the quality of videos in a manner highly consistent with human judgments of perceived quality. Traditional VQA models based on natural image and/or video…
We propose a novel framework for predicting the factuality of reporting of news media outlets by studying the user attention cycles in their YouTube channels. In particular, we design a rich set of features derived from the temporal…
Short-format videos have exploded on platforms like TikTok, Instagram, and YouTube. Despite this, the research community lacks large-scale empirical studies into how people engage with short-format videos and the role of recommendation…
Applications that allow sharing of user-created short videos exploded in popularity in recent years. A typical short video application allows a user to swipe away the current video being watched and start watching the next video in a video…
A rapid increase in the video traffic together with an increasing demand for higher quality videos has put a significant load on content delivery networks in the recent years. Due to the relatively limited delivery infrastructure, the video…
A system capturing the association between video frames and textual queries offer great potential for better video analysis. However, training such a system in a fully supervised way inevitably demands a meticulously curated video dataset…
Video Quality Assessment (VQA), which aims to predict the perceptual quality of a video, has attracted raising attention with the rapid development of streaming media technology, such as Facebook, TikTok, Kwai, and so on. Compared with…
This work aims to predict the popularity of short videos using the videos themselves and their related features. Popularity is measured by four key engagement metrics: view count, like count, comment count, and share count. This study…
Given a sequence of sets, where each set has a timestamp and contains an arbitrary number of elements, temporal sets prediction aims to predict the elements in the subsequent set. Previous studies for temporal sets prediction mainly focus…
TikTok is a music-based video sharing social media app famous for users creating short meme and dance videos. TikTok videos are largely based on popular song snippets, which is why lip syncing and dance moves evolve as significant user…
Instrument playing is among the most common scenes in music-related videos, which represent nowadays one of the largest sources of online videos. In order to understand the instrument-playing scenes in the videos, it is important to know…
An ideal model for dense video captioning -- predicting captions localized temporally in a video -- should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to produce outputs before processing…