AI Paper Atlas

Research map / Benchmarks / TextCaps

TextCaps leaderboard

17 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on TextCaps. Best CIDEr: 163.7 (PaLI-X (with OCR pipeline input), CVPR 2024).

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.

TextCaps · CIDEr

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

#CIDEr ↑MethodPaperTopic
1163.7PaLI-X (with OCR pipeline input)On Scaling Up a Multilingual Vision and Language Model
CVPR 2024 · Table 2
Visual question answering
2160.4PaLI-17B
mT5-XXL + ViT-e
PaLI: A Jointly-Scaled Multilingual Language-Image Model
ICLR 2023 · Table 1
Human and embodied modeling
3144.9CogVLM
Vicuna-1.5-7B
CogVLM: Visual Expert for Pretrained Language Models
NeurIPS 2024 · Image Captioning table
Human and embodied modeling
4136PoP (ours)
7-9B MLLM
Proof-of-Perception: Certified Tool-Using Multimodal Reasoning with Compositional Conformal Guarantees
CVPR 2026 · Table 1
Multimodal LLMs
5128.7LLaVA-1.5 + QA-ViT
Vicuna-7B
Question Aware Vision Transformer for Multimodal Reasoning
CVPR 2024 · Table 1
Human and embodied modeling
6125.3HRVDA
LLaMA-2-7B
HRVDA: High-Resolution Visual Document Assistant
CVPR 2024 · Table: Comparison of HRVDA wit
Multimodal LLMs
7124.4LLaVA-NeXT + CAL
LLaVA-NeXT Vicuna-13B
Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
NeurIPS 2024 · Table 2
Cross-modal learning
8123.1mPLUG-Owl-7B + Ours
mPLUG-Owl-7B
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding
NeurIPS 2024 · Performance comparison table
Multimodal LLMs
9115.9mPLUG-Owl with DoCo
mPLUG-Owl
Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models
CVPR 2024 · Table 2
Human and embodied modeling
10105.6ConCap
BLIP
Controllable Image Captioning via Prompting
AAAI 2023 · TextCaps comparison table
Human and embodied modeling
7 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.