Zero-shot virtual product placement in videos

被引:0
|
作者
Bhargavi, Divya [1 ]
Sindwani, Karan [1 ]
Gholami, Sia [1 ]
机构
[1] Amazon Web Serv, Irvine, CA 92618 USA
关键词
Object Detection; Image Segmentation; Virtual product insertion;
D O I
10.1145/3573381.3597213
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Virtual Product Placement (VPP) is an advertising technique that digitally places branded objects into movie or TV show scenes. Despite being a billion-dollar industry, current ad rendering techniques are time-consuming, costly, and executed manually with the help of visual effects (VFX) artists. In this paper, we present a fully automated and generalized framework for placing 2D ads in any linear TV cooking show captured using a single-view camera with minimal camera movements. The framework detects empty spaces, understands the kitchen scene, handles occlusion, renders ambient lighting, and tracks ads. Our framework without requiring access to full video or production camera configuration reduces the time and cost associated with manual post-production ad rendering techniques, enabling brands to reach consumers seamlessly while preserving the continuity of their viewing experience.
引用
收藏
页码:289 / 297
页数:9
相关论文
共 50 条
  • [1] Zero-shot action recognition in videos: A survey
    Estevam, Valter
    Pedrini, Helio
    Menotti, David
    NEUROCOMPUTING, 2021, 439 : 159 - 175
  • [2] The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos
    Liu, Runtao
    Wu, Zhirong
    Yu, Stella X.
    Lin, Stephen
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021,
  • [3] Zero-Shot Event Detection by Multimodal Distributional Semantic Embedding of Videos
    Elhoseiny, Mohamed
    Liu, Jingen
    Cheng, Hui
    Sawhney, Harpreet
    Elgammal, Ahmed
    THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 3478 - 3486
  • [4] A Unified Approach for Conventional Zero-Shot, Generalized Zero-Shot, and Few-Shot Learning
    Rahman, Shafin
    Khan, Salman
    Porikli, Fatih
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (11) : 5652 - 5667
  • [5] Combining Text and Image Knowledge with GANs for Zero-Shot Action Recognition in Videos
    Huang, Kaiqiang
    Miralles-Pechuan, Luis
    Mckeever, Susan
    PROCEEDINGS OF THE 17TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISAPP), VOL 5, 2022, : 623 - 631
  • [6] Enhancing Zero-Shot Action Recognition in Videos by Combining GANs with Text and Images
    Huang K.
    Miralles-Pechuán L.
    Mckeever S.
    SN Computer Science, 4 (4)
  • [7] Compressing Unknown Images with Product Quantizer for Efficient Zero-Shot Classification
    Li, Jin
    Lan, Xuguang
    Liu, Yang
    Wang, Le
    Zheng, Nanning
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 5458 - 5467
  • [8] VMAN: A Virtual Mainstay Alignment Network for Transductive Zero-Shot Learning
    Xie, Guo-Sen
    Zhang, Xu-Yao
    Yao, Yazhou
    Zhang, Zheng
    Zhao, Fang
    Shao, Ling
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 : 4316 - 4329
  • [9] Zero-Shot Object Counting
    Xu, Jingyi
    Le, Hieu
    Nguyen, Vu
    Ranjan, Viresh
    Samaras, Dimitris
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 15548 - 15557
  • [10] Ordinal Zero-Shot Learning
    Huo, Zengwei
    Geng, Xin
    PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 1916 - 1922