Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Scan2Cap

Scan2Cap

Reported on 9 benchmarks across 2 tasks · 1 paper · 9 SOTA

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

Natural Language Processing9 results

Visual Question Answering (VQA)onSQA3D
Exact Match· 2020-12-03
41
best: 60.1 (LLaVA-3D)
SOTA
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans arXiv:2012.02206
Image CaptioningonScanRefer Dataset
BLEU-4· 2020-12-03
34.25
best: 45.56 (3D CoCa)
SOTA
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans arXiv:2012.02206
Image CaptioningonScanRefer Dataset
CIDEr· 2020-12-03
53.73
best: 85.42 (3D CoCa)
SOTA
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans arXiv:2012.02206
Image CaptioningonScanRefer Dataset
METEOR· 2020-12-03
26.14
best: 30.95 (3D CoCa)
SOTA
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans arXiv:2012.02206
Image CaptioningonScanRefer Dataset
ROUGE-L· 2020-12-03
54.95
best: 61.98 (3D CoCa)
SOTA
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans arXiv:2012.02206
Image CaptioningonNr3D
BLEU-4· 2020-12-03
17.24
best: 29.29 (3D CoCa)
SOTA
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans arXiv:2012.02206
Image CaptioningonNr3D
CIDEr· 2020-12-03
27.47
best: 52.84 (3D CoCa)
SOTA
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans arXiv:2012.02206
Image CaptioningonNr3D
METEOR· 2020-12-03
21.8
best: 25.6 (BiCA)
SOTA
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans arXiv:2012.02206
Image CaptioningonNr3D
ROUGE-L· 2020-12-03
49.06
best: 56.43 (3D CoCa)
SOTA
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans arXiv:2012.02206