VoteNet+MCAN

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)onScanQA Test w/ objects
BLEU-1· 2021-12-20
29.46
best: 39.73 (NaviLLM)
ScanQA: 3D Question Answering for Spatial Scene Understanding arXiv:2112.10482
Visual Question Answering (VQA)onScanQA Test w/ objects
BLEU-4· 2021-12-20
6.08
best: 24.06 (BridgeQA)
ScanQA: 3D Question Answering for Spatial Scene Understanding arXiv:2112.10482
Visual Question Answering (VQA)onScanQA Test w/ objects
CIDEr· 2021-12-20
58.23
best: 103.1 (LLaVA-3D)
ScanQA: 3D Question Answering for Spatial Scene Understanding arXiv:2112.10482
Visual Question Answering (VQA)onScanQA Test w/ objects
Exact Match· 2021-12-20
19.71
best: 31.29 (BridgeQA)
ScanQA: 3D Question Answering for Spatial Scene Understanding arXiv:2112.10482
Visual Question Answering (VQA)onScanQA Test w/ objects
METEOR· 2021-12-20
12.07
best: 20.8 (LLaVA-3D)
ScanQA: 3D Question Answering for Spatial Scene Understanding arXiv:2112.10482
Visual Question Answering (VQA)onScanQA Test w/ objects
ROUGE· 2021-12-20
30.97
best: 49.6 (LLaVA-3D)
ScanQA: 3D Question Answering for Spatial Scene Understanding arXiv:2112.10482