3D-VisTA

Reported on 6 benchmarks across 1 task · 1 paper · 1 SOTA

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· 2023-08-08
48.5
best: 60.1 (LLaVA-3D)
SOTA
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment arXiv:2308.04352
Visual Question Answering (VQA)onScanQA Test w/ objects
BLEU-4· 2023-08-08
10.4
best: 24.06 (BridgeQA)
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment arXiv:2308.04352
Visual Question Answering (VQA)onScanQA Test w/ objects
CIDEr· 2023-08-08
69.6
best: 103.1 (LLaVA-3D)
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment arXiv:2308.04352
Visual Question Answering (VQA)onScanQA Test w/ objects
Exact Match· 2023-08-08
22.4
best: 31.29 (BridgeQA)
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment arXiv:2308.04352
Visual Question Answering (VQA)onScanQA Test w/ objects
METEOR· 2023-08-08
13.9
best: 20.8 (LLaVA-3D)
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment arXiv:2308.04352
Visual Question Answering (VQA)onScanQA Test w/ objects
ROUGE· 2023-08-08
35.7
best: 49.6 (LLaVA-3D)
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment arXiv:2308.04352