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)
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/siyi-wind/STiL
공식 코드https://github.com/sjokerlily/awesome-image-captioning
공식 코드https://github.com/slavaheroes/brain-captioning-with-gpt2
공식 코드Decoding fMRI Data into Captions using Prefix Language Modeling
https://github.com/snowdusky/dualpolishlearning
공식 코드Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object Detection
https://github.com/social-ai-studio/pro-cap
공식 코드Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection
https://github.com/solicucu/siod
공식 코드SIOD: Single Instance Annotated Per Category Per Image for Object Detection
https://github.com/somepago/dcr
공식 코드https://github.com/songxiaoshuai/dpl
공식 코드Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery
https://github.com/ssen7/histo_cap_transformers
공식 코드Automatic Report Generation for Histopathology images using pre-trained Vision Transformers and BERT
https://github.com/ssi-research/sfda-rchc
공식 코드Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptation
https://github.com/stefan-maximilian-dietrich/reliable-pls
공식 코드Semi-Supervised Learning guided by the Generalized Bayes Rule under Soft Revision
https://github.com/stogiannidis/srbench
공식 코드Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models
https://github.com/stone5265/3c-reid
공식 코드3C: Confidence-Guided Clustering and Contrastive Learning for Unsupervised Person Re-Identification
https://github.com/strivezs/alps
공식 코드https://github.com/subbareddy248/mllm_instruction_brain
공식 코드Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)
https://github.com/subho406/OmniNet
공식 코드OmniNet: A unified architecture for multi-modal multi-task learning
https://github.com/superagi/veagle
공식 코드https://github.com/swsiwu/composition_and_deformance
공식 코드Composition and Deformance: Measuring Imageability with a Text-to-Image Model
https://github.com/syp2ysy/dce
공식 코드Descriptive Caption Enhancement with Visual Specialists for Multimodal Perception
https://github.com/szbonaldo/fedmlp
공식 코드FedMLP: Federated Multi-Label Medical Image Classification under Task Heterogeneity
https://github.com/taeiin/aaai2025-jovale
공식 코드JoVALE: Detecting Human Actions in Video Using Audiovisual and Language Contexts
https://github.com/taewhankim/vipcap
공식 코드ViPCap: Retrieval Text-Based Visual Prompts for Lightweight Image Captioning
https://github.com/taicaichen/pg-lbo
공식 코드https://github.com/talshaharabany/what-is-where-by-looking
공식 코드What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs
https://github.com/taokz/biomedgpt
공식 코드BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks
https://github.com/technicolor-research/dsve-loc
공식 코드Finding beans in burgers: Deep semantic-visual embedding with localization
https://github.com/tencentarc/gvt
공식 코드What Makes for Good Visual Tokenizers for Large Language Models?
https://github.com/tencentyouturesearch/classification-semicls
공식 코드https://github.com/tensorflow/models
공식 코드https://github.com/tensorflow/tensor2tensor
공식 코드https://github.com/tgGuo15/PriorImageCaption
공식 코드Improving Reinforcement Learning Based Image Captioning with Natural Language Prior
https://github.com/tgisaturday/BITTERS
공식 코드Large-Scale Bidirectional Training for Zero-Shot Image Captioning
https://github.com/tgisaturday/L-Verse
공식 코드https://github.com/tgxs002/wikiscenes
공식 코드Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision
https://github.com/thu-bpm/gradlre
공식 코드Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.