SOTAVerified

Image Captioning

Image Captioning is the task of describing the content of an image in words. This task lies at the intersection of computer vision and natural language processing. Most image captioning systems use an encoder-decoder framework, where an input image is encoded into an intermediate representation of the information in the image, and then decoded into a descriptive text sequence. The most popular benchmarks are nocaps and COCO, and models are typically evaluated according to a BLEU or CIDER metric.

( Image credit: Reflective Decoding Network for Image Captioning, ICCV'19)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 1878 papers

TitleStatusHype
RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V TrustworthinessCode11
Chameleon: Mixed-Modal Early-Fusion Foundation ModelsCode7
RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human FeedbackCode6
Versatile Diffusion: Text, Images and Variations All in One Diffusion ModelCode6
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image GenerationCode5
YOLOR-Based Multi-Task LearningCode5
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and BeyondCode5
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationCode5
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language ModelsCode4
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsCode4
GLIPv2: Unifying Localization and Vision-Language UnderstandingCode4
GPT-4V(ision) is a Generalist Web Agent, if GroundedCode4
A Survey on Vision-Language-Action Models for Embodied AICode4
Scaling Up Biomedical Vision-Language Models: Fine-Tuning, Instruction Tuning, and Multi-Modal LearningCode4
LLM2CLIP: Powerful Language Model Unlocks Richer Visual RepresentationCode4
Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal ModelsCode3
Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language ModelsCode3
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation ModelsCode3
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth FusionCode3
View Selection for 3D Captioning via Diffusion RankingCode3
SVIT: Scaling up Visual Instruction TuningCode3
Ludwig: a type-based declarative deep learning toolboxCode3
Emu: Generative Pretraining in MultimodalityCode3
Vision-Language Pre-training: Basics, Recent Advances, and Future TrendsCode3
Falcon: A Remote Sensing Vision-Language Foundation ModelCode3
WikiWeb2M: A Page-Level Multimodal Wikipedia DatasetCode3
Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal UnderstandingCode3
TinyGPT-V: Efficient Multimodal Large Language Model via Small BackbonesCode3
All You May Need for VQA are Image CaptionsCode3
Caption Anything: Interactive Image Description with Diverse Multimodal ControlsCode3
Remote Sensing Temporal Vision-Language Models: A Comprehensive SurveyCode3
Valley2: Exploring Multimodal Models with Scalable Vision-Language DesignCode3
MeaCap: Memory-Augmented Zero-shot Image CaptioningCode2
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual ContextsCode2
LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language ModelsCode2
LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image UnderstandingCode2
LLaMA-VID: An Image is Worth 2 Tokens in Large Language ModelsCode2
Language Models Can See: Plugging Visual Controls in Text GenerationCode2
A Better Variant of Self-Critical Sequence TrainingCode2
BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical TasksCode2
Learning Vision from Models Rivals Learning Vision from DataCode2
OmniCaptioner: One Captioner to Rule Them AllCode2
Benchmarking Retrieval-Augmented Generation in Multi-Modal ContextsCode2
Benchmarking and Improving Detail Image CaptionCode2
GIT: A Generative Image-to-text Transformer for Vision and LanguageCode2
GLaMM: Pixel Grounding Large Multimodal ModelCode2
From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language ModelsCode2
Beyond Text: Frozen Large Language Models in Visual Signal ComprehensionCode2
Keeping Yourself is Important in Downstream Tuning Multimodal Large Language ModelCode2
From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning TasksCode2
Show:102550
← PrevPage 1 of 38Next →
All datasetsVizWiz 2020 test-devCOCO Captionsnocaps in-domainnocaps near-domainnocaps out-of-domainnocaps entireCOCO (Common Objects in Context)VizWiz 2020 testnocaps-XD entirenocaps-val-in-domainnocaps-val-overallnocaps-XD in-domain

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1IBM Research AICIDEr80.67—Unverified
2CASIA_IVACIDEr79.15—Unverified
3feixiangCIDEr77.31—Unverified
4wocaoCIDEr77.21—Unverified
5lamiwab172CIDEr75.93—Unverified
6RUC_AIM3CIDEr73.52—Unverified
7funasCIDEr73.51—Unverified
8SRC-B_VCLabCIDEr73.47—Unverified
9spartaCIDEr73.41—Unverified
10x-vizCIDEr73.26—Unverified
#ModelMetricClaimedVerifiedStatus
1VALORCIDER152.5—Unverified
2VASTCIDER149—Unverified
3Virtex (ResNet-101)CIDER94—Unverified
4KOSMOS-1 (1.6B) (zero-shot)CIDER84.7—Unverified
5BLIP-FuseCapCLIPScore78.5—Unverified
6mPLUGBLEU-446.5—Unverified
7OFABLEU-444.9—Unverified
8GITBLEU-444.1—Unverified
9BLIP-2 ViT-G OPT 2.7B (zero-shot)BLEU-443.7—Unverified
10BLIP-2 ViT-G OPT 6.7B (zero-shot)BLEU-443.5—Unverified
#ModelMetricClaimedVerifiedStatus
1PaLICIDEr149.1—Unverified
2GIT2, Single ModelCIDEr124.18—Unverified
3GIT, Single ModelCIDEr122.4—Unverified
4PaLICIDEr121.09—Unverified
5CoCa - Google BrainCIDEr117.9—Unverified
6Microsoft Cognitive Services teamCIDEr112.82—Unverified
7Single ModelCIDEr108.98—Unverified
8GRIT (zero-shot, no VL pretraining, no CBS)CIDEr105.9—Unverified
9FudanFVLCIDEr104.9—Unverified
10FudanWYZCIDEr104.25—Unverified
#ModelMetricClaimedVerifiedStatus
1GIT2, Single ModelCIDEr125.51—Unverified
2PaLICIDEr124.35—Unverified
3GIT, Single ModelCIDEr123.92—Unverified
4CoCa - Google BrainCIDEr120.73—Unverified
5Microsoft Cognitive Services teamCIDEr115.54—Unverified
6Single ModelCIDEr110.76—Unverified
7FudanFVLCIDEr109.33—Unverified
8FudanWYZCIDEr108.04—Unverified
9IEDA-LABCIDEr100.15—Unverified
10firetheholeCIDEr99.51—Unverified
#ModelMetricClaimedVerifiedStatus
1PaLICIDEr126.67—Unverified
2GIT2, Single ModelCIDEr122.27—Unverified
3GIT, Single ModelCIDEr122.04—Unverified
4CoCa - Google BrainCIDEr121.69—Unverified
5Microsoft Cognitive Services teamCIDEr110.14—Unverified
6Single ModelCIDEr109.49—Unverified
7FudanFVLCIDEr106.55—Unverified
8FudanWYZCIDEr103.75—Unverified
9HumanCIDEr91.62—Unverified
10firetheholeCIDEr88.54—Unverified