Filters








2,643 Hits in 5.3 sec

Find Objects and Focus on Highlights: Mining Object Semantics for Video Highlight Detection via Graph Neural Networks

Yingying Zhang, Junyu Gao, Xiaoshan Yang, Chang Liu, Yan Li, Changsheng Xu
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Firstly, most existing approaches only focus on learning holistic visual representations of videos but ignore object semantics for inferring video highlights.  ...  and focus on hard examples from the former stage.  ...  To the best of our knowledge, our method is among the first to advance graph neural networks and object semantics for video highlight detection. • By carefully designing a decomposed spatial-temporal graph  ... 
doi:10.1609/aaai.v34i07.6988 fatcat:biaanlopgvbw3nbt44niavse2m

Less Is More: Learning Highlight Detection From Video Duration

Bo Xiong, Yannis Kalantidis, Deepti Ghadiyaram, Kristen Grauman
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In experiments on two challenging public video highlight detection benchmarks, our method substantially improves the state-of-the-art for unsupervised highlight detection.  ...  Highlight detection has the potential to significantly ease video browsing, but existing methods often suffer from expensive supervision requirements, where human viewers must manually identify highlights  ...  Related Work Video Highlight Detection Many prior approaches focus on highlight detection for sports video [30, 37, 34, 35] .  ... 
doi:10.1109/cvpr.2019.00135 dblp:conf/cvpr/XiongKGG19 fatcat:daaqnaq5vndqvctzy7pmmhseuq

Less is More: Learning Highlight Detection from Video Duration [article]

Bo Xiong, Yannis Kalantidis, Deepti Ghadiyaram, Kristen Grauman
2019 arXiv   pre-print
In experiments on two challenging public video highlight detection benchmarks, our method substantially improves the state-of-the-art for unsupervised highlight detection.  ...  Highlight detection has the potential to significantly ease video browsing, but existing methods often suffer from expensive supervision requirements, where human viewers must manually identify highlights  ...  Related Work Video Highlight Detection Many prior approaches focus on highlight detection for sports video [30, 37, 34, 35] .  ... 
arXiv:1903.00859v1 fatcat:qqrefgksavar7peth3fcyyefgm

A Survey of Content-Aware Video Analysis for Sports

Huang-Chia Shih
2018 IEEE transactions on circuits and systems for video technology (Print)  
We believe that our findings can advance the field of research on content-aware video analysis for broadcast sports.  ...  Previous surveys have focused on the methodologies of sports video analysis from the spatiotemporal viewpoint instead of a content-based viewpoint, and few of these studies have considered semantics.  ...  Highlight Detection and Event Recognition Because an increasing amount of research is focused on large-scale content-based multimedia mining, there is a lack of systematic surveys specifically designed  ... 
doi:10.1109/tcsvt.2017.2655624 fatcat:rwqzu46sgfb7tpkcav4ysmh6ae

A review of deep learning in medical imaging: Image traits, technology trends, case studies with progress highlights, and future promises [article]

S. Kevin Zhou, Hayit Greenspan, Christos Davatzikos, James S. Duncan, Bram van Ginneken, Anant Madabhushi, Jerry L. Prince, Daniel Rueckert, Ronald M. Summers
2020 arXiv   pre-print
We cover the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, etc.  ...  It is known that the success of AI is mostly attributed to the availability of big data with annotations for a single task and the advances in high performance computing.  ...  In [78] , the feature importance scores are calculated for graph neural network by comparing its interpretation ability with Random Forest. Li et al.  ... 
arXiv:2008.09104v1 fatcat:z2gic7or4vgnnfcf4joimjha7i

Exchange-based diffusion in Hb-Graphs

Xavier Ouvrard, Jean-Marie Le Goff, Stéphane Marchand-Maillet
2020 Multimedia tools and applications  
He has recently introduced an e-adjacency tensor for general hypergraphs and hyper-bag-graphs, that are families of multisets.  ...  Complex networks, where entities can have multiple relationships, call for a modeling based on hypergraphs.  ...  The authors are thankful to Roderic BOUESSE (University of Geneva) to have selected the tool needed for the image use case.  ... 
doi:10.1007/s11042-020-09176-y fatcat:jteharocjnaddjhb26qq4dqoay

Research on Salient Object Detection using Deep Learning and Segmentation Methods

2019 International journal of recent technology and engineering  
It not only focuses on the methods to detect saliency objects, but also reviews the works related to spatio temporal video attention detection technique in video sequences.  ...  Detecting and segmenting salient objects in natural scenes, often referred to as salient object detection has attracted a lot of interest in computer vision and recently various heuristic computational  ...  Second, it adopts a two-stage scheme for salient detection via affinity propagation clustering and graph-based manifold ranking.  ... 
doi:10.35940/ijrte.b1046.0982s1119 fatcat:6ofq53vb7zhx7boq4ndpraphs4

Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks [article]

Wenguan Wang, Xiankai Lu, Jianbing Shen, David Crandall, Ling Shao
2020 arXiv   pre-print
This work proposes a novel attentive graph neural network (AGNN) for zero-shot video object segmentation (ZVOS).  ...  The extensive experiments verify that AGNN is able to learn the underlying semantic/appearance relationships among video frames or related images, and discover the common objects.  ...  Young Professionals, and the National Science Foundation (CAREER IIS-1253549).  ... 
arXiv:2001.06807v1 fatcat:il4hh2aes5h4nh2fayb3ysvz6m

A study on video data mining

V. Vijayakumar, R. Nedunchezhian
2012 International Journal of Multimedia Information Retrieval  
The objective of video data mining is to discover and describe interesting patterns from the huge amount of video data as it is one of the core problem areas of the data-mining research community.  ...  Data mining is a process of extracting previously unknown knowledge and detecting the interesting patterns from a massive set of data.  ...  These relations are represented by association rules between video unit feature(s) and feature(s). The current researches on it focus on mining object semantic information and event detection.  ... 
doi:10.1007/s13735-012-0016-2 fatcat:xuuf3w3b2rfcxlyevzndz6v62e

VIREO/ECNU @ TRECVID 2013: A Video Dance of Detection, Recounting and Search with Motion Relativity and Concept Learning from Wild

Chong-Wah Ngo, Feng Wang, Wei Zhang, Chun Chet Tan, Zhanhu Sun, Shiai Zhu, Ting Yao
2013 TREC Video Retrieval Evaluation  
Semantic Indexing (SIN): This year, we focused on a new feature representation extracted using deep neural networks (DNN).  ...  weighting strategy; and (3) a re-ranking step based on objects mining.  ...  We also thank BBC for providing the EastEnders dataset: Programme material c ⃝ BBC.  ... 
dblp:conf/trecvid/NgoW0TSZY13 fatcat:jpbx3fr25jg35oiexaohdxntzy

Multi-modal Deep Analysis for Multimedia

Wenwu Zhu, Xin Wang, Hongzhi Li
2019 IEEE transactions on circuits and systems for video technology (Print)  
answering, multi-modal video summarization, multi-modal visual pattern mining and multi-modal recommendation.  ...  More specifically, on data-driven correlational representation, we highlight three important categories of methods, such as multi-modal deep representation, multi-modal transfer learning, and multi-modal  ...  ACKNOWLEDGMENT We thank Guohao Li, Shengze Yu and Yitian Yuan for providing relevant materials and valuable opinions. This work will never be accomplished without their useful suggestions.  ... 
doi:10.1109/tcsvt.2019.2940647 fatcat:l4tchrkgrnaeradvc4nhfan2w4

Joint Processing of Language and Visual Data for Better Automated Understanding (Dagstuhl Seminar 19021)

Marie-Francine Moens, Lucia Specia, Tinne Tuytelaars, Michael Wagner
2019 Dagstuhl Reports  
This report documents the program and the outcomes of Dagstuhl Seminar 19021 "Joint Processing of Language and Visual Data for Better Automated Understanding".  ...  It includes a discussion of the motivation and overall organization, the abstracts of the talks, and a report of each working group.  ...  For texts, this can be done via dependency parsing or semantic role labelling. For images, one can consider scene graphs, such as in the Visual Genome dataset [15] .  ... 
doi:10.4230/dagrep.9.1.1 dblp:journals/dagstuhl-reports/MoensST19 fatcat:ozdlb2cxpje65pyj2elxfzxxna

Machine and cognitive intelligence for human health: systematic review

Xieling Chen, Gary Cheng, Fu Lee Wang, Xiaohui Tao, Haoran Xie, Lingling Xu
2022 Brain Informatics  
There are several promising topics, for example, random forests, support vector machines, and conventional neural networks for disease detection and diagnosis, semantic Web, ontology mining, and topic  ...  modeling for clinical or biomedical text mining, artificial neural networks and logistic regression for prediction, and convolutional neural networks and support vector machines for monitoring and classification  ...  More specifically, we highlight the use of: (1) random forests, SVMs, and CNNs for disease detection and diagnosis, (2) semantic Web, ontology mining, and topic modeling for clinical or biomedical text  ... 
doi:10.1186/s40708-022-00153-9 pmid:35150379 pmcid:PMC8840949 fatcat:whia7d7zyze5rd6susl54ozcqq

A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications [article]

Fei Wu, Qingzhong Wang, Jian Bian, Haoyi Xiong, Ning Ding, Feixiang Lu, Jun Cheng, Dejing Dou
2022 arXiv   pre-print
In this paper, we present a survey on video action recognition for sports analytics.  ...  Reducing the ambiguity of actions and in the last decade, many works focused on datasets, novel models and learning approaches have improved video action recognition to a higher level.  ...  Note that the fast branch is designed to capture object motion instead of high-level semantics, thus it can be a lightweight neural network.  ... 
arXiv:2206.01038v1 fatcat:eqctk6342zdcrdbqggixmprp4e

Scene Graph Generation: A Comprehensive Survey [article]

Guangming Zhu, Liang Zhang, Youliang Jiang, Yixuan Dang, Haoran Hou, Peiyi Shen, Mingtao Feng, Xia Zhao, Qiguang Miao, Syed Afaq Ali Shah, Mohammed Bennamoun
2022 arXiv   pre-print
Scene Graph Generation (SGG) refers to the task of automatically mapping an image into a semantic structural scene graph, which requires the correct labeling of detected objects and their relationships  ...  Scene graph has been the focus of research because of its powerful semantic representation and applications to scene understanding.  ...  This paper focuses on reviewing methods for visual relationship detection.  ... 
arXiv:2201.00443v2 fatcat:s4w7sdf6dndzneujly54srh5c4
« Previous Showing results 1 — 15 out of 2,643 results