中文
相关论文

相关论文: SmartTennisTV: Automatic indexing of tennis videos

200 篇论文

Video Large Language Models (Video-LLMs) excel at understanding videos in-context, provided they have full access to the video when answering queries. However, these models face challenges in streaming scenarios where hour-long videos must…

计算机视觉与模式识别 · 计算机科学 2025-10-21 Vaggelis Dorovatas , Soroush Seifi , Gunshi Gupta , Rahaf Aljundi

Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider…

计算机视觉与模式识别 · 计算机科学 2016-05-12 Ozan Sener , Amir Roshan Zamir , Chenxia Wu , Silvio Savarese , Ashutosh Saxena

Video action recognition (VAR) is a primary task of video understanding, and untrimmed videos are more common in real-life scenes. Untrimmed videos have redundant and diverse clips containing contextual information, so sampling dense clips…

计算机视觉与模式识别 · 计算机科学 2021-04-22 Yunyan Hong , Ailing Zeng , Min Li , Cewu Lu , Li Jiang , Qiang Xu

We investigate methods of segmenting, visualizing, and indexing presentation videos by separately considering audio and visual data. The audio track is segmented by speaker, and augmented with key phrases which are extracted using an…

多媒体 · 计算机科学 2007-05-23 Alexander Haubold , John R. Kender

Robust scene segmentation and keyframe extraction are essential preprocessing steps in video understanding pipelines, supporting tasks such as indexing, summarization, and semantic retrieval. However, existing methods often lack…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Vasilii Korolkov

This paper presents a novel hierarchical approach for the simultaneous tracking of multiple targets in a video. We use a network flow approach to link detections in low-level and tracklets in high-level. At each step of the hierarchy, the…

计算机视觉与模式识别 · 计算机科学 2017-05-31 Ali Taalimi , Liu Liu , Hairong Qi

Enabling computational systems with the ability to localize actions in video-based content has manifold applications. Traditionally, such a problem is approached in a fully-supervised setting where video-clips with complete frame-by-frame…

计算机视觉与模式识别 · 计算机科学 2019-05-07 Kurt Degiorgio , Fabio Cuzzolin

Automated vision-based score estimation models can be used as an alternate opinion to avoid judgment bias. In the past works the score estimation models were learned by regressing the video representations to the ground truth score provided…

计算机视觉与模式识别 · 计算机科学 2020-02-28 Hiteshi Jain , Gaurav Harit , Avinash Sharma

Action detection and temporal segmentation of actions in videos are topics of increasing interest. While fully supervised systems have gained much attention lately, full annotation of each action within the video is costly and impractical…

计算机视觉与模式识别 · 计算机科学 2018-05-18 Alexander Richard , Hilde Kuehne , Juergen Gall

As large amount of visual Information is available on web in form of images, graphics, animations and videos, so it is important in internet era to have an effective video search system. As there are number of video search engine (blinkx,…

计算机视觉与模式识别 · 计算机科学 2014-01-03 Avinash N Bhute , B. B. Meshram

Detecting transitions between intro/credits and main content in videos is a crucial task for content segmentation, indexing, and recommendation systems. Manual annotation of such transitions is labor-intensive and error-prone, while…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Vasilii Korolkov , Andrey Yanchenko

Job transitions and upskilling are common actions taken by many industry working professionals throughout their career. With the current rapidly changing job landscape where requirements are constantly changing and industry sectors are…

机器学习 · 计算机科学 2019-07-26 Alan Chern , Phuong Hoang , Madhav Sigdel , Janani Balaji , Mohammed Korayem

Analyzing a player's technique in table tennis requires knowledge of the ball's 3D trajectory and spin. While, the spin is not directly observable in standard broadcasting videos, we show that it can be inferred from the ball's trajectory…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Daniel Kienzle , Robin Schön , Rainer Lienhart , Shin'Ichi Satoh

Comprehensive understanding of key players and actions in multiplayer sports broadcast videos is a challenging problem. Unlike in news or finance videos, sports videos have limited text. While both action recognition for multiplayer sports…

多媒体 · 计算机科学 2021-11-02 Avijit Shah , Topojoy Biswas , Sathish Ramadoss , Deven Santosh Shah

Recently, memory-based approaches show promising results on semi-supervised video object segmentation. These methods predict object masks frame-by-frame with the help of frequently updated memory of the previous mask. Different from this…

计算机视觉与模式识别 · 计算机科学 2022-08-04 Kwanyong Park , Sanghyun Woo , Seoung Wug Oh , In So Kweon , Joon-Young Lee

In the light of the need to achieve a ranking which is understood by all tennis supporters, the ATP ranking is exposed to constant complaints from players and at the same time exposes new players to be benefited with a good tournament to be…

社会与信息网络 · 计算机科学 2017-12-01 Alex Aronson

Human pose detection systems based on state-of-the-art DNNs are on the go to be extended, adapted and re-trained to fit the application domain of specific sports. Therefore, plenty of noisy pose data will soon be available from videos…

计算机视觉与模式识别 · 计算机科学 2020-04-22 Rainer Lienhart , Moritz Einfalt , Dan Zecha

Video ads segmentation and tagging is a challenging task due to two main reasons: (1) the video scene structure is complex and (2) it includes multiple modalities (e.g., visual, audio, text.). While previous work focuses mostly on activity…

计算机视觉与模式识别 · 计算机科学 2021-08-23 Tomoyuki Suzuki , Antonio Tejero-de-Pablos

Recognising actions in videos relies on labelled supervision during training, typically the start and end times of each action instance. This supervision is not only subjective, but also expensive to acquire. Weak video-level supervision…

计算机视觉与模式识别 · 计算机科学 2019-04-10 Davide Moltisanti , Sanja Fidler , Dima Damen

In this paper, we propose a novel approach for exploiting structural relations to track multiple objects that may undergo long-term occlusion and abrupt motion. We use a model-free approach that relies only on annotations given in the first…

计算机视觉与模式识别 · 计算机科学 2016-12-21 Henrique Morimitsu , Isabelle Bloch , Roberto M. Cesar-Jr