The paper introduces a zero‑shot multimodal framework for spotting soccer events in full‑length broadcasts without task‑specific training. It segments matches into overlapping clips, represents them with a compact visual storyboard and aligned commentary, and processes these jointly with a general‑purpose multimodal model. On three annotated matches, the best setup achieves 72.0% F1@5s, surpassing SoccerNet‑trained baselines, and the storyboard reduces inference cost by 72%.
"whyItMatters":"The approach enables efficient, high‑accuracy event detection and highlight generation in soccer broadcasts without relying on large annotated datasets or soccer‑specific training, as demonstrated by its superior performance and reduced inference cost."
By Sadia Kamal, Mahmudul Hasan, Tony Braskich
MultiVENT‑Raw is a new multilingual benchmark comprising nearly 120,000 raw videos—continuous footage from cell phones, hand‑held cameras, or CCTV—totaling over 5,300 hours. The dataset includes 130 events and 222 event‑centric queries, along with human‑annotated relevance judgments and extracted key facts for relevant videos. It supports two tasks: retrieving videos relevant to a query event and generating a coherent report summarizing event‑related videos for a target user, with baseline models showing these tasks remain challenging.
By Reno Kriz, David Etter, Alexander Martin, Cameron Carpenter, Debashish Chakraborty, Hannah Recknor, Reihaneh Iranmanesh, Matthew Maciejewski, Kenton Murray, Eugene Yang, Benjamin Van Durme, Aaron Steven White, Andrew Yates, William Walden
arXiv:2609.28049v1 Announce Type: cross
Abstract: Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as ev...
By Sai Varun Kodathala, Prashanth Pollishetty, Jaylen Cargill
arXiv:2608.09200v3 Announce Type: replace
Abstract: Live basketball commentary generation requires determining when an event is sufficiently observable and describing it before subsequent events unfo...
By Lifang Wu, Yuyang Wu, Yangdong Gao, Fengyu Liu, Ya Jing, Liang Wang
arXiv:2607. 21267v1 Announce Type: new Abstract: Comprehensive basketball video understanding requires resolving not only what event occurs, but also who is responsible and when the key evidence appears.
By Yu Zhang, Jiayuan Rao, Haoning Wu, Weidi Xie
Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as evidence a model is robust enough for deployment. Ama...