ChatScene

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)onScanQA Test w/ objects
BLEU-4· 2023-12-13
14.3
best: 24.06 (BridgeQA)
SOTA
Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers arXiv:2312.08168
Visual Question Answering (VQA)onSQA3D
Exact Match· 2023-12-13
54.6
best: 60.1 (LLaVA-3D)
Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers arXiv:2312.08168
Visual Question Answering (VQA)onScanQA Test w/ objects
CIDEr· 2023-12-13
87.7
best: 103.1 (LLaVA-3D)
Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers arXiv:2312.08168
Visual Question Answering (VQA)onScanQA Test w/ objects
Exact Match· 2023-12-13
21.6
best: 31.29 (BridgeQA)
Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers arXiv:2312.08168
Visual Question Answering (VQA)onScanQA Test w/ objects
METEOR· 2023-12-13
18
best: 20.8 (LLaVA-3D)
Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers arXiv:2312.08168
Visual Question Answering (VQA)onScanQA Test w/ objects
ROUGE· 2023-12-13
41.6
best: 49.6 (LLaVA-3D)
Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers arXiv:2312.08168