Multimodal Video-to-Video Linking: Turning to the Crowd for Insight and Evaluation

被引:0
|
作者
Eskevich, Maria [1 ]
Larson, Martha [1 ,2 ]
Aly, Robin [3 ]
Sabetghadam, Serwah [4 ]
Jones, Gareth J. F. [5 ]
Ordelman, Roeland [3 ]
Huet, Benoit [6 ]
机构
[1] Radboud Univ Nijmegen, CLS, Nijmegen, Netherlands
[2] Delft Univ Technol, Delft, Netherlands
[3] Univ Twente, Enschede, Netherlands
[4] TU Vienna, Vienna, Austria
[5] Dublin City Univ, Sch Comp, ADAPT Ctr, Dublin, Ireland
[6] EURECOM, Sophia Antipolis, France
来源
基金
爱尔兰科学基金会;
关键词
Crowdsourcing; Video-to-video linking; Link evaluation; Verbal-visual information;
D O I
10.1007/978-3-319-51814-524
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Video-to-video linking systems allow users to explore and exploit the content of a large-scale multimedia collection interactively and without the need to formulate specific queries. We present a short introduction to video-to-video linking (also called 'video hyperlinking'), and describe the latest edition of the Video Hyperlinking (LNK) task at TRECVid 2016. The emphasis of the LNK task in 2016 is on multi-modality as used by videomakers to communicate their intended message. Crowdsourcing makes three critical contributions to the LNK task. First, it allows us to verify the multimodal nature of the anchors (queries) used in the task. Second, it enables us to evaluate the performance of video-to-video linking systems at large scale. Third, it gives us insights into how people understand the relevance relationship between two linked video segments. These insights are valuable since the relationship between video segments can manifest itself at different levels of abstraction.
引用
收藏
页码:280 / 292
页数:13
相关论文
共 50 条
  • [1] An Evaluation of Video-to-Video Face Verification
    Poh, Norman
    Chan, Chi Ho
    Kittler, Josef
    Marcel, Sebastien
    Mc Cool, Christopher
    Argones Rua, Enrique
    Alba Castro, Jose Luis
    Villegas, Mauricio
    Paredes, Roberto
    Struc, Vitomir
    Pavesic, Nikola
    Salah, Albert Ali
    Fang, Hui
    Costen, Nicholas
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2010, 5 (04) : 781 - 801
  • [2] Video-to-Video Synthesis
    Wang, Ting-Chun
    Liu, Ming-Yu
    Zhu, Jun-Yan
    Liu, Guilin
    Tao, Andrew
    Kautz, Jan
    Catanzaro, Bryan
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [3] Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning
    Liu, Kangning
    Gu, Shuhang
    Romero, Andres
    Timofte, Radu
    2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021), 2021, : 1029 - 1039
  • [4] Few-shot Video-to-Video Synthesis
    Wang, Ting-Chun
    Liu, Ming-Yu
    Tao, Andrew
    Liu, Guilin
    Kautz, Jan
    Catanzaro, Bryan
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [5] Video-to-Video Translation with Global Temporal Consistency
    Wei, Xingxing
    Zhu, Jun
    Feng, Sitong
    Su, Hang
    PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18), 2018, : 18 - 25
  • [6] Manifold Learning for Video-to-Video Face Recognition
    Hadid, Abdenour
    Pietikainen, Matti
    BIOMETRIC ID MANAGEMENT AND MULTIMODAL COMMUNICATION, PROCEEDINGS, 2009, 5707 : 9 - 16
  • [7] FaceOff: A Video-to-Video Face Swapping System
    Agarwal, Aditya
    Sen, Bipasha
    Mukhopadhyay, Rudrabha
    Namboodiri, Vinay
    Jawahar, C. V.
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 3484 - 3493
  • [8] Mocycle-GAN: Unpaired Video-to-Video Translation
    Chen, Yang
    Pan, Yingwei
    Yao, Ting
    Tian, Xinmei
    Mei, Tao
    PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19), 2019, : 647 - 655
  • [9] Generative Adversarial Networks for Video-to-Video Domain Adaptation
    Chen, Jiawei
    Li, Yuexiang
    Ma, Kai
    Zheng, Yefeng
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 3462 - 3469
  • [10] Deep video-to-video transformations for accessibility with an application to photosensitivity
    Barbu, Andrei
    Banda, Dalitso
    Katz, Boris
    PATTERN RECOGNITION LETTERS, 2020, 137 : 99 - 107