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."
arXiv:2601.16333v3 Announce Type: replace-cross Abstract: Foundation models are used for many real-world applications involving language understanding and generation from temporally-ordered multimoda...
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...
arXiv:2609.17923v1 Announce Type: new Abstract: Sports highlight detection aims to identify the most exciting and meaningful moments from long sports videos. While existing methods often emphasize vi...
arXiv:2610.22444v1 Announce Type: new Abstract: Spatio-Temporal Video Grounding (STVG) aims to jointly localize a target in space and time given a natural-language query. Despite continued advances,...
arXiv:2608. 07932v2 Announce Type: replace Abstract: Sports video analysis is crucial for athletic analytics and broadcasting enhancement.
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.
arXiv:2608. 19723v1 Announce Type: cross Abstract: Streaming video understanding requires models to causally update state as video arrives and organize growing history into semantic units that can evolve, persist, and be recalled under bounded computation and memory.
arXiv:2505.01583v2 Announce Type: replace Abstract: Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models (VLM...
arXiv:2608. 19646v1 Announce Type: new Abstract: Visual understanding in sports has emerged as a hot topic in computer vision in recent years.
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...
arXiv:2609.39300v1 Announce Type: new Abstract: Recent advances in computer vision have made broadcast sports videos increasingly useful for event analysis, performance assessment, and player-safety...
SoccerNet‑FoulRet is a new benchmark for retrieving semantically similar soccer foul videos, addressing inconsistencies in refereeing decisions by allowing comparison of a contentious foul with past precedents. The task requires retrieving relevant fouls regardless of camera angle, teams, or appearance, differing from prior video‑to‑video retrieval that focuses on visual similarity. The benchmark, built from the SoccerNet‑MVFoul dataset, evaluates zero‑shot video and vision‑language embeddings and a fine‑tuned baseline on 693 human‑verified queries, revealing that even the best zero‑shot model achieves less than 5% HitRate@10, highlighting the challenge of semantic foul retrieval.