AI Paper Atlas

Research map / Benchmarks / nocaps validation overall

nocaps validation overall leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on nocaps validation overall. Best CIDEr: 120.5 (Ours Base (human-annotated style), IJCV 2023).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

nocaps validation overall · CIDEr

11 papers, each with its best reported number for its own method; higher is better.

#CIDEr ↑MethodPaperTopic
1120.5Ours Base (human-annotated style)
35.7M images
Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets
IJCV 2023 · Table 3
Editing and style transfer
2110.2ConCap
BLIP
Controllable Image Captioning via Prompting
AAAI 2023 · COCO/NoCaps comparison table
Human and embodied modeling
3106PTP-BLIP (4M)
BLIP
Position-Guided Text Prompt for Vision-Language Pre-Training
CVPR 2023 · Image captioning results table
CLIP and zero-shot
4105.1BLIPBLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
ICML 2022 · Table: Image captioning
CLIP and zero-shot
5100.9NOC-REK
BERT-base
NOC-REK: Novel Object Captioning With Retrieved Vocabulary From External Knowledge
CVPR 2022 · Table 3
Open-set and few-shot detection
697.2P2C
BERT-base captioner
Paraphrasing Is All You Need for Novel Object Captioning
NeurIPS 2022 · Table 1
Human and embodied modeling
793.8ViTCAP + CBS
ViT/B
Injecting Semantic Concepts Into End-to-End Image Captioning
CVPR 2022 · Table 3
Human and embodied modeling
892.6PMA-Net
Transformer, CLIP ViT-L/14
With a Little Help from Your Own Past: Prototypical Memory Networks for Image Captioning
ICCV 2023 · nocaps table
Human and embodied modeling
990.8LightCap + CBS
CLIP ResNet-50 + TinyBERT4
Efficient Image Captioning for Edge Devices
AAAI 2023 · nocaps comparison table
Cross-modal learning
1088.3VIVO + SCST + CBSVIVO: Visual Vocabulary Pre-Training for Novel Object Captioning
AAAI 2021 · Table 1
Human and embodied modeling
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.