Papers with Code 아카이브
Image Captioning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 8
- 평가표
- 34
- 보존된 평가 기록
- 419
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)
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
Frame-Level Real-Time Assessment of Stroke Rehabilitation Exercises from Video-Level Labeled Data: Task-Specific vs. Foundation Models
Attention-based transformer models for image captioning across languages: An in-depth survey and evaluation
L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning
Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation
Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training Models
D2AF: A Dual-Driven Annotation and Filtering Framework for Visual Grounding
Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport
Beam-Guided Knowledge Replay for Knowledge-Rich Image Captioning using Vision-Language Model
CLDTracker: A Comprehensive Language Description for Visual Tracking
Puzzled by Puzzles: When Vision-Language Models Can't Take a Hint
CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation
Collaborative Learning for Unsupervised Multimodal Remote Sensing Image Registration: Integrating Self-Supervision and MIM-Guided Diffusion-Based Image Translation
RefAV: Towards Planning-Centric Scenario Mining
Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Score
Certainty and Uncertainty Guided Active Domain Adaptation
Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)
SATORI-R1: Incentivizing Multimodal Reasoning with Spatial Grounding and Verifiable Rewards
TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP
Scaling Up Biomedical Vision-Language Models: Fine-Tuning, Instruction Tuning, and Multi-Modal Learning
Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
Redemption Score: An Evaluation Framework to Rank Image Captions While Redeeming Image Semantics and Language Pragmatics
A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning
ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning
SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval
NOVA: A Benchmark for Anomaly Localization and Clinical Reasoning in Brain MRI
Aligning Attention Distribution to Information Flow for Hallucination Mitigation in Large Vision-Language Models
RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
MedBLIP: Fine-tuning BLIP for Medical Image Captioning
Sat2Sound: A Unified Framework for Zero-Shot Soundscape Mapping
Mutual Evidential Deep Learning for Medical Image Segmentation
Pseudo-Label Quality Decoupling and Correction for Semi-Supervised Instance Segmentation
TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation
Cross-Image Contrastive Decoding: Precise, Lossless Suppression of Language Priors in Large Vision-Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.