Related papers: StreamReady: Learning What to Answer and When in L…
In modern interactive speech-based systems, speech is consumed and transcribed incrementally prior to having disfluencies removed. This post-processing step is crucial for producing clean transcripts and high performance on downstream tasks…
In many practical LLM deployments, a single guardrail is used for both prompt and response moderation. Prompt moderation operates on fully observed text, whereas streaming response moderation requires safety decisions to be made over…
Image generative models have made significant progress in generating realistic and diverse images, supported by comprehensive guidance from various evaluation metrics. However, current video generative models struggle to generate even short…
Live streaming recommender system is specifically designed to recommend real-time live streaming of interest to users. Due to the dynamic changes of live content, improving the timeliness of the live streaming recommender system is a…
In recent years, with the rapid development of sensing technology and the Internet of Things (IoT), sensors play increasingly important roles in traffic control, medical monitoring, industrial production and etc. They generated high volume…
The increasing complexity of Industry 4.0 systems brings new challenges regarding predictive maintenance tasks such as fault detection and diagnosis. A corresponding and realistic setting includes multi-source data streams from different…
Recent Video-Language Models (VLMs) achieve promising results on long-video understanding, but their performance still lags behind that achieved on tasks involving images or short videos. This has led to great interest in improving the long…
An unsupervised online streaming model is considered where samples arrive in an online fashion over $T$ slots. There are $M$ classifiers, whose confusion matrices are unknown a priori. In each slot, at most one sample can be labeled by any…
How can we tell whether a video has been sped up or slowed down? How can we generate videos at different speeds? Although videos have been central to modern computer vision research, little attention has been paid to perceiving and…
We propose ReKV, a novel training-free approach that enables efficient streaming video question-answering (StreamingVQA), by seamlessly integrating with existing Video Large Language Models (Video-LLMs). Traditional VideoQA systems struggle…
Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can…
The state of the art in video understanding suffers from two problems: (1) The major part of reasoning is performed locally in the video, therefore, it misses important relationships within actions that span several seconds. (2) While there…
Multimodal reward models (MRMs) play a crucial role in the training, inference, and evaluation of Large Vision Language Models (LVLMs) by assessing response quality. However, existing benchmarks for evaluating MRMs in the video domain…
Video Question Answering (VideoQA) has made significant strides by leveraging multimodal learning to align visual and textual modalities. However, current benchmarks overwhelmingly focus on questions answerable through explicit visual…
We propose a digital twin-assisted adaptive preloading scheme to enhance bandwidth efficiency and user quality of experience (QoE) in short video streaming. We first analyze the relationship between the achievable throughput and video…
Precise video retrieval requires multi-modal correlations to handle unseen vocabulary and scenes, becoming more complex for lengthy videos where models must perform effectively without prior training on a specific dataset. We introduce a…
This paper addresses the problem of self-supervised video representation learning from a new perspective -- by video pace prediction. It stems from the observation that human visual system is sensitive to video pace, e.g., slow motion, a…
In this paper we present a deep graph reinforcement learning model to predict and improve the user experience during a live video streaming event, orchestrated by an agent/tracker. We first formulate the user experience prediction problem…
With the reduced hardware costs of omnidirectional cameras and the proliferation of various extended reality applications, more and more $360^\circ$ videos are being captured. To fully unleash their potential, advanced video analytics is…
Today, we have to deal with many data (Big data) and we need to make decisions by choosing an architectural framework to analyze these data coming from different area. Due to this, it become problematic when we want to process these data,…