LLaVA-NeXT-Video

Reported on 6 benchmarks across 1 task · 1 paper

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

Natural Language Processing6 results

Visual Question Answering (VQA)onSQA3D
Exact Match· 2024-08-06
34.2
best: 60.1 (LLaVA-3D)
LLaVA-OneVision: Easy Visual Task Transfer arXiv:2408.03326
Visual Question Answering (VQA)onScanQA Test w/ objects
BLEU-4· 2024-08-06
9.8
best: 24.06 (BridgeQA)
LLaVA-OneVision: Easy Visual Task Transfer arXiv:2408.03326
Visual Question Answering (VQA)onScanQA Test w/ objects
CIDEr· 2024-08-06
46.2
best: 103.1 (LLaVA-3D)
LLaVA-OneVision: Easy Visual Task Transfer arXiv:2408.03326
Visual Question Answering (VQA)onScanQA Test w/ objects
Exact Match· 2024-08-06
18.7
best: 31.29 (BridgeQA)
LLaVA-OneVision: Easy Visual Task Transfer arXiv:2408.03326
Visual Question Answering (VQA)onScanQA Test w/ objects
METEOR· 2024-08-06
9.1
best: 20.8 (LLaVA-3D)
LLaVA-OneVision: Easy Visual Task Transfer arXiv:2408.03326
Visual Question Answering (VQA)onScanQA Test w/ objects
ROUGE· 2024-08-06
27.8
best: 49.6 (LLaVA-3D)
LLaVA-OneVision: Easy Visual Task Transfer arXiv:2408.03326