Filters








332 Hits in 4.8 sec

Automatic Curation of Golf Highlights Using Multimodal Excitement Features

Michele Merler, Dhiraj Joshi, Quoc-Bao Nguyen, Stephen Hammer, John Kent, John R. Smith, Rogerio S. Feris
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We propose a novel approach for auto-curating sports highlights, and use it to create a real-world system for the editorial aid of golf highlight reels.  ...  The production of sports highlight packages summarizing a game's most exciting moments is an essential task for broadcast media. Yet, it requires labor-intensive video editing.  ...  More specifically, we measure the excitement level of video segments based on the following multimodal markers: Figure 1. The H5 system dashboard for auto-curation of sports highlights.  ... 
doi:10.1109/cvprw.2017.14 dblp:conf/cvpr/MerlerJNHKSF17 fatcat:eukurxongbgexh66emhuu2hy64

Automatic Curation of Golf Highlights using Multimodal Excitement Features [article]

Michele Merler and Dhiraj Joshi and Quoc-Bao Nguyen and Stephen Hammer and John Kent and John R. Smith and Rogerio S. Feris
2017 arXiv   pre-print
We propose a novel approach for auto-curating sports highlights, and use it to create a real-world system for the editorial aid of golf highlight reels.  ...  The production of sports highlight packages summarizing a game's most exciting moments is an essential task for broadcast media. Yet, it requires labor-intensive video editing.  ...  More specifically, we measure the excitement level of video segments based on the following multimodal markers: Figure 1. The H5 system dashboard for auto-curation of sports highlights.  ... 
arXiv:1707.07075v1 fatcat:ssfgn4oafzg2nj6sg7ldol556u

The Excitement of Sports: Automatic Highlights Using Audio/Visual Cues

Michele Merler, Dhiraj Joshi, Khoi-Nguyen C. Mac, Quoc-Bao Nguyen, Stephen Hammer, John Kent, Jinjun Xiong, Minh N. Do, John R. Smith, Rogério Schmidt Feris
2018 Computer Vision and Pattern Recognition  
We propose a novel approach for auto-curating sports highlights, and demonstrate it to create a first of a kind, real-world system for the editorial aid of golf and tennis highlight reels.  ...  The production of sports highlight packages summarizing a game's most exciting moments is an essential task for broadcast media. Yet, it requires labor-intensive video editing.  ...  Conclusion We presented a novel approach for automatically extracting highlights from sports videos based on multimodal sport-independent excitement measures, for which models were learned with reduced  ... 
dblp:conf/cvpr/MerlerJMNHKXDSF18 fatcat:5wpqsk23mbamrlma3bma77ereu

Automatic Summarization of Cricket Highlights using Audio Processing

Ritwik Baranwal
2021 International journal of modern trends in science and technology  
The problem of automatic excitement detection in cricket videos is considered and applied for highlight generation.  ...  Our experiments using actual cricket videos show that these features are well correlated with human assessment of excitability.  ...  For example, emotional "hot-spots" within sports videos are very likely to be "exciting" and this information can be used to guide the process of automatically generating highlights.  ... 
doi:10.46501/ijmtst070111 fatcat:wwigsfyi4bat3nuifeaurnutsy

Creative Applications of Human Behavior Understanding [chapter]

Albert Ali Salah, Hayley Hung, Oya Aran, Hatice Gunes
2013 Lecture Notes in Computer Science  
Since arts, creativity, entertainment and edutainment all contribute to significant social and societal benefits, it is vital to tackle the problem of measuring and evaluating the success of automatic  ...  This paper discusses scientific and technological factors that make this a challenging topic to address, provides a brief survey of related work in this area, and identifies active topics of research.  ...  In one of the earliest papers on automatic detection of excitement in videos, Hanjalic used overall motion activity (measured at video frame transitions), the rhythm (via the changes in shot lengths along  ... 
doi:10.1007/978-3-319-02714-2_1 fatcat:byw43vsce5ep3o3es6khru5u3q

Hierarchical Multimodal Transformer to Summarize Videos [article]

Bin Zhao, Maoguo Gong, Xuelong Li
2021 arXiv   pre-print
To integrate the two kinds of information, they are encoded in a two-stream scheme, and a multimodal fusion mechanism is developed based on the hierarchical transformer.  ...  In this paper, the proposed method is denoted as Hierarchical Multimodal Transformer (HMT).  ...  Similar to the video summarization task, an automatic curation method of sports highlights is conducted by combining multimodal excitement features [40] .  ... 
arXiv:2109.10559v1 fatcat:7sh724e3pjhpvdyw2znbaer3mm

Object-level Trajectories based Fine-Grained Action Recognition in Visual IoT Applications

Jian Xiong, Liguo Lu, Hengbing Wang, Jie Yang, Guan Gui
2019 IEEE Access  
The emerging computer vision and deep learning technologies are being applied to the intelligent analysis of sports training videos.  ...  The experimental results show that the proposed method can achieve an accuracy of 93.24%. INDEX TERMS Event classification, object detection network, sports video analysis, LSTM.  ...  Multimodal excitement features were utilized for automatic curation of golf highlights by Merler et al. [31] .  ... 
doi:10.1109/access.2019.2931471 fatcat:kjknufpy6fen5hpmfalfu3m57u

MultiViz: An Analysis Benchmark for Visualizing and Understanding Multimodal Models [article]

Paul Pu Liang, Yiwei Lyu, Gunjan Chhablani, Nihal Jain, Zihao Deng, Xingbo Wang, Louis-Philippe Morency, Ruslan Salakhutdinov
2022 arXiv   pre-print
interactions are represented in decision-level features, and (4) multimodal prediction: how decision-level features are composed to make a prediction.  ...  How can we visualize the internal modeling of multimodal interactions in these models?  ...  of Health, Facebook, Carnegie Mellon University's Center for Machine Learning and Health, or Office of Naval Research, and no official endorsement should be inferred.  ... 
arXiv:2207.00056v1 fatcat:vxg2lcvm6jgghldw74b7onwjje

Affective Computing for Large-scale Heterogeneous Multimedia Data

Sicheng Zhao, Shangfei Wang, Mohammad Soleymani, Dhiraj Joshi, Qiang Ji
2019 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
We then summarize and compare the representative methods on AC of different multimedia types, i.e., images, music, videos, and multimodal data, with the focus on both handcrafted features-based methods  ...  The wide popularity of digital photography and social networks has generated a rapidly growing volume of multimedia data (i.e., image, music, and video), resulting in a great demand for managing, retrieving  ...  This is an important application in entertainment and sports industries (e.g. movie trailers, sports highlights).  ... 
doi:10.1145/3363560 fatcat:m56udtjlxrauvmj6d5z2r2zdeu

SC2EGSet: StarCraft II Esport Replay and Game-state Dataset [article]

Andrzej Białecki, Natalia Jakubowska, Paweł Dobrowolski, Piotr Białecki, Leszek Krupiński, Andrzej Szczap, Robert Białecki, Jan Gajewski
2022 arXiv   pre-print
As a relatively new form of sport, esports offers unparalleled data availability.  ...  Despite the vast amounts of data that are generated by game engines, it can be challenging to extract them and verify their integrity for the purposes of practical and scientific use.  ...  Moreover, we extend our thanks to the StarCraft II esports community for sharing their experiences, playing together, and discussing key aspects of the gameplay in various esports.  ... 
arXiv:2207.03428v1 fatcat:7awzkdfkincqlg7uagpk32fcni

Human Movement Datasets: An Interdisciplinary Scoping Review

Temitayo Olugbade, Marta Bieńkiewicz, Giulia Barbareschi, Vincenzo D'Amato, Luca Oneto, Antonio Camurri, Catherine Holloway, Mårten Björkman, Peter Keller, Martin Clayton, Amanda C de C Williams, Nicolas Gold (+3 others)
2022 ACM Computing Surveys  
We provide an analysis of the datasets and further review them under the themes of human diversity, ecological validity, and data recorded.  ...  Movement dataset reviews exist but are limited in coverage, both in terms of size and research discipline.  ...  As such, our framework aims to highlight the opportunity provided by a multimodal approach to movement modelling.  ... 
doi:10.1145/3534970 fatcat:g6rvjlesxzgn5c3uajbuewcatq

Automatic Identification and Classification of Bragging in Social Media [article]

Mali Jin, Daniel Preoţiuc-Pietro, A. Seza Doğruöz, Nikolaos Aletras
2022 arXiv   pre-print
Bragging is a speech act employed with the goal of constructing a favorable self-image through positive statements about oneself.  ...  To facilitate this, we introduce a new publicly available data set of tweets annotated for bragging and their types.  ...  Ethics Statement Our work has received approval from the Ethics Committee of the Department of Computer Science at the University of Sheffield (No 037572) and complies with Twitter's data policy for research  ... 
arXiv:2203.05840v1 fatcat:psagaeb4qzczdi6jvascesfgcy

Harnessing A.I. for Augmenting Creativity

John R. Smith, Dhiraj Joshi, Benoit Huet, Winston Hsu, Jozef Cota
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
We introduce an intelligent system designed to understand and encode patterns and types of emotions in horror movies that are useful in trailers.  ...  The system was applied on a full-length feature film, "Morgan" released in 2016 where the system identified 10 moments as best candidates for a trailer.  ...  ACKNOWLEDGMENTS The authors would like to thank 20 t h Century Fox for this great collaboration that lead to creation of the world's first joint human and machine made trailer for a full length feature  ... 
doi:10.1145/3123266.3127906 dblp:conf/mm/SmithJHHC17 fatcat:k6of2csqa5b6thftrojr5enkgu

MERLOT: Multimodal Neural Script Knowledge Models [article]

Rowan Zellers, Ximing Lu, Jack Hessel, Youngjae Yu, Jae Sung Park, Jize Cao, Ali Farhadi, Yejin Choi
2021 arXiv   pre-print
On Visual Commonsense Reasoning, MERLOT answers questions correctly with 80.6% accuracy, outperforming state-of-the-art models of similar size by over 3%, even those that make heavy use of auxiliary supervised  ...  Ablation analyses demonstrate the complementary importance of: 1) training on videos versus static images; 2) scaling the magnitude and diversity of the pretraining video corpus; and 3) using diverse objectives  ...  learning of multimodal representations. 1 Though recent work has proposed using grid-based features, on tasks like Visual Commonsense Reasoning, these approaches have so far underperformed  ... 
arXiv:2106.02636v3 fatcat:mrj2t3yuanbdzhsujshtky4enq

Alone With Goffman: Impression Management and the TV Series

Simon Beames, Søren Andkjær, Aage Radmann
2021 Frontiers in Communication  
The show features 10 contestants who are vying to outlast each other while living off the land.  ...  the end of each of the six series that were watched.  ...  features three key themes.  ... 
doi:10.3389/fcomm.2021.676555 fatcat:lwrbddajtng3fiiohugmxrmxqa
« Previous Showing results 1 — 15 out of 332 results