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 351–400 of 1878 papers

TitleStatusHype
Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense CaptionerCode1
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial TrajectoryCode1
Neural Fashion Image Captioning : Accounting for Data DiversityCode1
NeuSyRE: Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph EnrichmentCode1
EDSL: An Encoder-Decoder Architecture with Symbol-Level Features for Printed Mathematical Expression RecognitionCode1
Egoshots, an ego-vision life-logging dataset and semantic fidelity metric to evaluate diversity in image captioning modelsCode1
Dual-branch Hybrid Learning Network for Unbiased Scene Graph GenerationCode1
On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model PerspectiveCode1
DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only TrainingCode1
Dual-Level Collaborative Transformer for Image CaptioningCode1
Passage Retrieval for Outside-Knowledge Visual Question AnsweringCode1
Paying Attention to Descriptions Generated by Image Captioning ModelsCode1
Enhancing Visual Question Answering through Question-Driven Image Captions as PromptsCode1
Distinctive Image Captioning: Leveraging Ground Truth Captions in CLIP Guided Reinforcement LearningCode1
Disentangled Pre-training for Human-Object Interaction DetectionCode1
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence ModelsCode1
Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree SearchCode1
Position-guided Text Prompt for Vision-Language Pre-trainingCode1
Concadia: Towards Image-Based Text Generation with a PurposeCode1
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsCode1
Progressive Tree-Structured Prototype Network for End-to-End Image CaptioningCode1
Confidence-aware Non-repetitive Multimodal Transformers for TextCapsCode1
Protect, Show, Attend and Tell: Empowering Image Captioning Models with Ownership ProtectionCode1
Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image SegmentationCode1
Discovering Non-monotonic Autoregressive Orderings with Variational InferenceCode1
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text RetrievalCode1
Consensus-Aware Visual-Semantic Embedding for Image-Text MatchingCode1
RadAlign: Advancing Radiology Report Generation with Vision-Language Concept AlignmentCode1
Diverse Image Captioning with Context-Object Split Latent SpacesCode1
Diffusion Bridge: Leveraging Diffusion Model to Reduce the Modality Gap Between Text and Vision for Zero-Shot Image CaptioningCode1
Revisiting Image Captioning Training Paradigm via Direct CLIP-based OptimizationCode1
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewardsCode1
Differentially Private Representation Learning via Image CaptioningCode1
DiffX: Guide Your Layout to Cross-Modal Generative ModelingCode1
COSMic: A Coherence-Aware Generation Metric for Image DescriptionsCode1
Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene GraphsCode1
Detecting Hate Speech in Multi-modal MemesCode1
SciMMIR: Benchmarking Scientific Multi-modal Information RetrievalCode1
See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual ReasoningCode1
Self-critical Sequence Training for Image CaptioningCode1
ConTEXTual Net: A Multimodal Vision-Language Model for Segmentation of PneumothoraxCode1
Discovering Autoregressive Orderings with Variational InferenceCode1
In Defense of Scene Graphs for Image CaptioningCode1
Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart CaptioningCode1
Show, Attend and Tell: Neural Image Caption Generation with Visual AttentionCode1
Show, Deconfound and Tell: Image Captioning With Causal InferenceCode1
Contrastive Vision-Language Alignment Makes Efficient Instruction LearnerCode1
Sieve: Multimodal Dataset Pruning Using Image Captioning ModelsCode1
ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language GenerationCode1
GAIA: A Global, Multi-modal, Multi-scale Vision-Language Dataset for Remote Sensing Image AnalysisCode1
Show:102550
← PrevPage 8 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