AI Paper Atlas

Research map / Benchmarks / COCO Caption

COCO Caption leaderboard

18 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on COCO Caption. Best CIDEr: 143.1 (CrossGET, ICML 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.

COCO Caption · CIDEr

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

#CIDEr ↑MethodPaperTopic
1143.1CrossGET
BLIP2-OPT6.7B
CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
ICML 2024 · Table: Accelerate BLIP2-OPT6.7
Cross-modal learning
2140.3VIVL
ViT-g/14 + OPT 2.7B
Towards Better Vision-Inspired Vision-Language Models
CVPR 2024 · Table 2
Cross-modal learning
3136.2OURO-7B
Qwen2-VL-7B-Instruct
OURO: A Self-Bootstrapped Framework for Enhancing Multimodal Scene Understanding
ICCV 2025 · Table 4
Multimodal LLMs
4135.66Hyper-ICL
Idefics2-8B-base
Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning
ICML 2026 · Table 1
Human and embodied modeling
5133.2ADEM-VL
LLaMA-13B
ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning
IJCV 2025 · Table 2
Multimodal LLMs
6132.87MimIC
Idefics2-8b-base
Mimic In-Context Learning for Multimodal Tasks
CVPR 2025 · Table 1
Attention and transformers
7131.6UFO-InternVL2.5-8B multi-task
InternVL2.5-8B
UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface
NeurIPS 2025 · Table 1
Multimodal LLMs
8128.9UPop 2x
BLIP
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
ICML 2023 · Table 5
Cross-modal learning
9128.7Tag2Text-Swin (4M)
Swin-Base
Tag2Text: Guiding Vision-Language Model via Image Tagging
ICLR 2024 · Captioning results table
CLIP and zero-shot
10124UpDown (Our)
ResNeXt-IG-3.5B
Engaging Image Captioning via Personality
CVPR 2019 · COCO generative model results
Human and embodied modeling
8 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.