TY - GEN
T1 - SoccerNet-Caption
T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
AU - Mkhallati, Hassan
AU - Cioppa, Anthony
AU - Giancola, Silvio
AU - Ghanem, Bernard
AU - Droogenbroeck, Marc Van
N1 - Funding Information:
This paper proposes the novel task of single-anchored dense video captioning focusing on generating textual commentaries anchored with single timestamps. To support this task, we present SoccerNet-Caption, a challenging dataset consisting of 37k timestamped commentaries across 715.9 hours of soccer broadcast videos. We benchmarked a first baseline algorithm on this dataset, highlighting the difficulty of temporally anchoring commentaries yet showing the capacity to generate meaningful commentaries. Acknowledgement. This work was partly supported by KAUST OSR through the VCC funding and the SDAIA-KAUST Center of Excellence in Data Science and Artificial Intelligence. A. Cioppa is funded by the F.R.S.-FNRS.
Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Soccer is more than just a game - it is a passion that transcends borders and unites people worldwide. From the roar of the crowds to the excitement of the commentators, every moment of a soccer match is a thrill. Yet, with so many games happening simultaneously, fans cannot watch them all live. Notifications for main actions can help, but lack the engagement of live commentary, leaving fans feeling disconnected. To fulfill this need, we propose in this paper a novel task of dense video captioning focusing on the generation of textual commentaries anchored with single times-tamps. To support this task, we additionally present a challenging dataset consisting of almost 37k timestamped commentaries across 715.9 hours of soccer broadcast videos. Additionally, we propose a first benchmark and baseline for this task, highlighting the difficulty of temporally anchoring commentaries yet showing the capacity to generate meaningful commentaries. By providing broadcasters with a tool to summarize the content of their video with the same level of engagement as a live game, our method could help satisfy the needs of the numerous fans who follow their team but cannot necessarily watch the live game. We believe our method has the potential to enhance the accessibility and understanding of soccer content for a wider audience, bringing the excitement of the game to more people.
AB - Soccer is more than just a game - it is a passion that transcends borders and unites people worldwide. From the roar of the crowds to the excitement of the commentators, every moment of a soccer match is a thrill. Yet, with so many games happening simultaneously, fans cannot watch them all live. Notifications for main actions can help, but lack the engagement of live commentary, leaving fans feeling disconnected. To fulfill this need, we propose in this paper a novel task of dense video captioning focusing on the generation of textual commentaries anchored with single times-tamps. To support this task, we additionally present a challenging dataset consisting of almost 37k timestamped commentaries across 715.9 hours of soccer broadcast videos. Additionally, we propose a first benchmark and baseline for this task, highlighting the difficulty of temporally anchoring commentaries yet showing the capacity to generate meaningful commentaries. By providing broadcasters with a tool to summarize the content of their video with the same level of engagement as a live game, our method could help satisfy the needs of the numerous fans who follow their team but cannot necessarily watch the live game. We believe our method has the potential to enhance the accessibility and understanding of soccer content for a wider audience, bringing the excitement of the game to more people.
UR - http://www.scopus.com/inward/record.url?scp=85166293862&partnerID=8YFLogxK
U2 - 10.1109/CVPRW59228.2023.00536
DO - 10.1109/CVPRW59228.2023.00536
M3 - Conference contribution
AN - SCOPUS:85166293862
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 5074
EP - 5085
BT - Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
PB - IEEE Computer Society
Y2 - 18 June 2023 through 22 June 2023
ER -