Pith. sign in

Soccernet-tracking: Multiple object tracking dataset and benchmark in soccer videos

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Domain Adaptation of VLM for Soccer Video Understanding

cs.CV · 2025-05-20 · conditional · novelty 6.0

A three-stage curriculum (concept alignment, instruction tuning, downstream fine-tuning) adapted LLaVA-NeXT-Video to soccer, raising action classification accuracy from 11.8% to 63.5% and the VQA relative score from about 60 to 83.

citing papers explorer

Showing 1 of 1 citing paper.

  • Domain Adaptation of VLM for Soccer Video Understanding cs.CV · 2025-05-20 · conditional · none · ref 5

    A three-stage curriculum (concept alignment, instruction tuning, downstream fine-tuning) adapted LLaVA-NeXT-Video to soccer, raising action classification accuracy from 11.8% to 63.5% and the VQA relative score from about 60 to 83.