Shot2Story

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Video CaptioningonShot2Story20K
BLEU-4· 2023-12-16
10.7
SOTA
Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos arXiv:2312.10300
Video CaptioningonShot2Story20K
CIDEr· 2023-12-16
37.4
best: 63.2 (Shotluck-Holmes (3.1B))
SOTA
Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos arXiv:2312.10300
Video CaptioningonShot2Story20K
METEOR· 2023-12-16
16.2
best: 25.7 (Shotluck-Holmes (3.1B))
SOTA
Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos arXiv:2312.10300
Video CaptioningonShot2Story20K
ROUGE· 2023-12-16
29.6
best: 36.2 (Shotluck-Holmes (3.1B))
SOTA
Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos arXiv:2312.10300