English
Related papers

Related papers: THIA: Accelerating Video Analytics using Early Inf…

200 papers

Recent advances in video processing utilizing deep learning primitives achieved breakthroughs in fundamental problems in video analysis such as frame classification and object detection enabling an array of new applications. In this paper…

Databases · Computer Science 2020-02-26 Nick Koudas , Raymond Li , Ioannis Xarchakos

Temporal language localization in videos aims to ground one video segment in an untrimmed video based on a given sentence query. To tackle this task, designing an effective model to extract ground-ing information from both visual and…

Computer Vision and Pattern Recognition · Computer Science 2020-08-07 Xiaoye Qu , Pengwei Tang , Zhikang Zhou , Yu Cheng , Jianfeng Dong , Pan Zhou

Video diffusion transformers (vDiTs) have made tremendous progress in text-to-video generation, but their high compute demands pose a major challenge for practical deployment. While studies propose acceleration methods to reduce workload at…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Haosong Liu , Yuge Cheng , Wenxuan Miao , Zihan Liu , Aiyue Chen , Jing Lin , Yiwu Yao , Chen Chen , Jingwen Leng , Yu Feng , Minyi Guo

Recent adaptive methods for efficient video recognition mostly follow the two-stage paradigm of "preview-then-recognition" and have achieved great success on multiple video benchmarks. However, this two-stage paradigm involves two visits of…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Ye Tian , Mengyu Yang , Lanshan Zhang , Zhizhen Zhang , Yang Liu , Xiaohui Xie , Xirong Que , Wendong Wang

Millions of cameras at edge are being deployed to power a variety of different deep learning applications. However, the frames captured by these cameras are not always pristine - they can be distorted due to lighting issues, sensor noise,…

Image and Video Processing · Electrical Eng. & Systems 2021-10-27 Sibendu Paul , Utsav Drolia , Y. Charlie Hu , Srimat T. Chakradhar

How can we benefit from large models without sacrificing inference speed, a common dilemma in self-driving systems? A prevalent solution is a dual-system architecture, employing a small model for rapid, reactive decisions and a larger model…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Shadi Hamdan , Chonghao Sima , Zetong Yang , Hongyang Li , Fatma Güney

The advent of edge computing has made real-time intelligent video analytics feasible. Previous works, based on traditional model architecture (e.g., CNN, RNN, etc.), employ various strategies to filter out non-region-of-interest content to…

Multimedia · Computer Science 2024-09-27 Haosong Peng , Wei Feng , Hao Li , Yufeng Zhan , Ren Jin , Yuanqing Xia

In this paper, we present Mondrian, an edge system that enables high-performance object detection on high-resolution video streams. Many lightweight models and system optimization techniques have been proposed for resource-constrained…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Changmin Jeon , Seonjun Kim , Juheon Yi , Youngki Lee

MOTIVATION: Microarray technology makes it possible to measure thousands of variables and to compare their values under hundreds of conditions. Once microarray data are quantified, normalized and classified, the analysis phase is…

Quantitative Methods · Quantitative Biology 2007-09-11 Claude Pasquier , Fabrice Girardot , Karim Jevardat De Fombelle , Richard Christen

Video cameras are pervasively deployed in city scale for public good or community safety (i.e. traffic monitoring or suspected person tracking). However, analyzing large scale video feeds in real time is data intensive and poses severe…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-05-17 Hongpeng Guo , Shuochao Yao , Zhe Yang , Qian Zhou , Klara Nahrstedt

Human video comprehension demonstrates dynamic coordination between reasoning and visual attention, adaptively focusing on query-relevant details. However, current long-form video question answering systems employ rigid pipelines that…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Zixuan Dong , Baoyun Peng , Yufei Wang , Lin Liu , Xinxin Dong , Yunlong Cao , Xiaodong Wang

Querying the content of images, video, and other non-textual data sources requires expensive content extraction methods. Modern extraction techniques are based on deep convolutional neural networks (CNNs) and can classify objects within…

Databases · Computer Science 2019-04-23 Michael R. Anderson , Michael Cafarella , German Ros , Thomas F. Wenisch

Content-based video retrieval is one of the most challenging tasks in surveillance systems. In this study, Latent Dirichlet Allocation (LDA) topic model is used to annotate surveillance videos in an unsupervised manner. In scene…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Mohammad Kianpisheh

Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The task of FGIA targets analyzing visual objects from…

Computer Vision and Pattern Recognition · Computer Science 2021-11-22 Xiu-Shen Wei , Yi-Zhe Song , Oisin Mac Aodha , Jianxin Wu , Yuxin Peng , Jinhui Tang , Jian Yang , Serge Belongie

The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Yuxiang Huang , Mingye Li , Xu Han , Chaojun Xiao , Weilin Zhao , Ao Sun , Ziqi Yuan , Hao Zhou , Fandong Meng , Zhiyuan Liu

Mobile-centric AI applications have high requirements for resource-efficiency of model inference. Input filtering is a promising approach to eliminate the redundancy so as to reduce the cost of inference. Previous efforts have tailored…

Artificial Intelligence · Computer Science 2023-06-08 Mu Yuan , Lan Zhang , Fengxiang He , Xueting Tong , Miao-Hui Song , Zhengyuan Xu , Xiang-Yang Li

Anticipating future actions based on spatiotemporal observations is essential in video understanding and predictive computer vision. Moreover, a model capable of anticipating the future has important applications, it can benefit…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Tsung-Ming Tai , Giuseppe Fiameni , Cheng-Kuang Lee , Simon See , Oswald Lanz

Image enhancement holds extensive applications in real-world scenarios due to complex environments and limitations of imaging devices. Conventional methods are often constrained by their tailored models, resulting in diminished robustness…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Yixuan Zhu , Wenliang Zhao , Ao Li , Yansong Tang , Jie Zhou , Jiwen Lu

Long-form video understanding requires efficient navigation of extensive visual data to pinpoint sparse yet critical information. Current approaches to longform video understanding either suffer from severe computational overhead due to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Te Yang , Xiangyu Zhu , Bo Wang , Quan Chen , Peng Jiang , Zhen Lei

Recent vision transformer based video models mostly follow the ``image pre-training then finetuning" paradigm and have achieved great success on multiple video benchmarks. However, full finetuning such a video model could be computationally…

Computer Vision and Pattern Recognition · Computer Science 2023-02-07 Taojiannan Yang , Yi Zhu , Yusheng Xie , Aston Zhang , Chen Chen , Mu Li