English
Related papers

Related papers: Flash-VStream: Memory-Based Real-Time Understandin…

200 papers

The integration of Large Language Models (LLMs) with visual encoders has recently shown promising performance in visual understanding tasks, leveraging their inherent capability to comprehend and generate human-like text for visual…

Computer Vision and Pattern Recognition · Computer Science 2024-12-04 Heqing Zou , Tianze Luo , Guiyang Xie , Victor , Zhang , Fengmao Lv , Guangcong Wang , Junyang Chen , Zhuochen Wang , Hansheng Zhang , Huaijian Zhang

Current motion-conditioned video generation methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present MotionStream, enabling sub-second latency with up to 29 FPS…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Joonghyuk Shin , Zhengqi Li , Richard Zhang , Jun-Yan Zhu , Jaesik Park , Eli Shechtman , Xun Huang

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Shiwei Wu , Joya Chen , Kevin Qinghong Lin , Qimeng Wang , Yan Gao , Qianli Xu , Tong Xu , Yao Hu , Enhong Chen , Mike Zheng Shou

Current video-language models struggle with long-video understanding due to limited context lengths and reliance on sparse frame subsampling, often leading to information loss. This paper introduces $\infty$-Video, which can process…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Saul Santos , António Farinhas , Daniel C. McNamee , André F. T. Martins

We investigate whether off-the-shelf Multimodal Large Language Models (MLLMs) can tackle Online Episodic-Memory Video Question Answering (OEM-VQA) without additional training. Our pipeline converts a streaming egocentric video into a…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Giuseppe Lando , Rosario Forte , Giovanni Maria Farinella , Antonino Furnari

Long video understanding is a complex task that requires both spatial detail and temporal awareness. While Vision-Language Models (VLMs) obtain frame-level understanding capabilities through multi-frame input, they suffer from information…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Ziyi Wang , Haoran Wu , Yiming Rong , Deyang Jiang , Yixin Zhang , Yunlong Zhao , Shuang Xu , Bo XU

Media streaming has been adopted for a variety of applications such as entertainment, visualization, and design. Unlike video/audio streaming where the content is usually consumed sequentially, 3D applications such as gaming require…

Human-Computer Interaction · Computer Science 2022-01-11 Shaoyu Chen , Budmonde Duinkharjav , Xin Sun , Li-Yi Wei , Stefano Petrangeli , Jose Echevarria , Claudio Silva , Qi Sun

Standard Large Language Models (LLMs) are predominantly designed for static inference with pre-defined inputs, which limits their applicability in dynamic, real-time scenarios. To address this gap, the streaming LLM paradigm has emerged.…

Computation and Language · Computer Science 2026-04-21 Junlong Tong , Zilong Wang , YuJie Ren , Peiran Yin , Hao Wu , Wei Zhang , Xiaoyu Shen

Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily…

Machine Learning · Statistics 2016-10-06 Rocco De Rosa , Ilaria Gori , Fabio Cuzzolin , Barbara Caputo , Nicolò Cesa-Bianchi

Recent advancements in multi-view scene reconstruction have been significant, yet existing methods face limitations when processing streams of input images. These methods either rely on time-consuming offline optimization or are restricted…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Zhuoguang Chen , Minghui Qin , Tianyuan Yuan , Zhe Liu , Hang Zhao

Understanding and tuning the performance of extreme-scale parallel computing systems demands a streaming approach due to the computational cost of applying offline algorithms to vast amounts of performance log data. Analyzing large…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-01-28 Suraj P. Kesavan , Takanori Fujiwara , Jianping Kelvin Li , Caitlin Ross , Misbah Mubarak , Christopher D. Carothers , Robert B. Ross , Kwan-Liu Ma

Generating realistic, dyadic talking head video requires ultra-low latency. Existing chunk-based methods require full non-causal context windows, introducing significant delays. This high latency critically prevents the immediate,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Bohong Chen , Haiyang Liu

Ultra long video understanding remains an open challenge, as existing vision language models (VLMs) falter on such content due to limited context length and inefficient long term memory retention. To address this, recent works have…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Hongbo Jin , Qingyuan Wang , Wenhao Zhang , Yang Liu , Sijie Cheng

The rapid growth of data in velocity, volume, value, variety, and veracity has enabled exciting new opportunities and presented big challenges for businesses of all types. Recently, there has been considerable interest in developing systems…

Systems and Control · Electrical Eng. & Systems 2019-07-23 Shihao Ge , Haruna Isah , Farhana Zulkernine , Shahzad Khan

Long-form video understanding remains challenging for Vision-Language Models (VLMs) due to the inherent tension between computational constraints and the need to capture information distributed across thousands of frames. Existing…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Junbo Zou , Ziheng Huang , Shengjie Zhang , Liwen Zhang , Weining Shen

A versatile video depth estimation model should (1) be accurate and consistent across frames, (2) produce high-resolution depth maps, and (3) support real-time streaming. We propose FlashDepth, a method that satisfies all three…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Gene Chou , Wenqi Xian , Guandao Yang , Mohamed Abdelfattah , Bharath Hariharan , Noah Snavely , Ning Yu , Paul Debevec

Video understanding tasks have traditionally been modeled by two separate architectures, specially tailored for two distinct tasks. Sequence-based video tasks, such as action recognition, use a video backbone to directly extract…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Yucheng Zhao , Chong Luo , Chuanxin Tang , Dongdong Chen , Noel Codella , Zheng-Jun Zha

Hospitals around the world collect massive amounts of physiological data from their patients every day. Recently, there has been an increase in research interest to subject this data to statistical analysis to gain more insights and provide…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-03-04 Anand Jayarajan , Kimberly Hau , Andrew Goodwin , Gennady Pekhimenko

Despite recent progress on the short-video Text-Visual Question Answering (ViteVQA) task - largely driven by benchmarks such as M4-ViteVQA - existing datasets still suffer from limited video duration and narrow evaluation scopes, making it…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Yangyang Zhong , Ji Qi , Yuan Yao , Pengxin Luo , Yunfeng Yan , Donglian Qi , Zhiyuan Liu , Tat-Seng Chua

This work proposes TimeChat, a time-sensitive multimodal large language model specifically designed for long video understanding. Our model incorporates two key architectural contributions: (1) a timestamp-aware frame encoder that binds…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Shuhuai Ren , Linli Yao , Shicheng Li , Xu Sun , Lu Hou