Scene-LLM

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· 2024-03-18
54.2
best: 60.1 (LLaVA-3D)
Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning arXiv:2403.11401
Visual Question Answering (VQA)onScanQA Test w/ objects
BLEU-4· 2024-03-18
12
best: 24.06 (BridgeQA)
Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning arXiv:2403.11401
Visual Question Answering (VQA)onScanQA Test w/ objects
CIDEr· 2024-03-18
80
best: 103.1 (LLaVA-3D)
Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning arXiv:2403.11401
Visual Question Answering (VQA)onScanQA Test w/ objects
Exact Match· 2024-03-18
27.2
best: 31.29 (BridgeQA)
Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning arXiv:2403.11401
Visual Question Answering (VQA)onScanQA Test w/ objects
METEOR· 2024-03-18
16.6
best: 20.8 (LLaVA-3D)
Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning arXiv:2403.11401
Visual Question Answering (VQA)onScanQA Test w/ objects
ROUGE· 2024-03-18
40
best: 49.6 (LLaVA-3D)
Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning arXiv:2403.11401