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/SuperSupermoon/MedViLL
공식 코드https://github.com/SxJyJay/MORE
공식 코드MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes
https://github.com/THU-BPM/MetaSRE
공식 코드Semi-supervised Relation Extraction via Incremental Meta Self-Training
https://github.com/TIXFeniks/neurips2019_intrus
공식 코드https://github.com/TXH-mercury/VALOR
공식 코드VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
https://github.com/TencentYoutuResearch/OpenWorld-DeepFakeAttribution
공식 코드Contrastive Pseudo Learning for Open-World DeepFake Attribution
https://github.com/Tiiiger/bert_score
공식 코드https://github.com/UMass-Foundation-Model/VisualCoT
공식 코드https://github.com/Unbear430/DGCN-for-image-captioning
공식 코드Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning
https://github.com/VASHISHT-RAHUL/ACML_2022_On_the_Interpretability_of_Attention_Networks
공식 코드https://github.com/Vision-CAIR/RelTransformer
공식 코드RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition
https://github.com/Vision-CAIR/VisualGPT
공식 코드VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning
https://github.com/VisualAIKHU/SAMPD
공식 코드Multispectral Pedestrian Detection with Sparsely Annotated Label
https://github.com/WANGXinyiLinda/CMLE
공식 코드Counterfactual Maximum Likelihood Estimation for Training Deep Networks
https://github.com/WYu-Feng/pc-gain
공식 코드PC-GAIN: Pseudo-label Conditional Generative Adversarial Imputation Networks for Incomplete Data
https://github.com/Wangt-CN/VC-R-CNN
공식 코드https://github.com/Westlake-AGI-Lab/Distill-Any-Depth
공식 코드Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator
https://github.com/Westlake-AI/SemiReward
공식 코드SemiReward: A General Reward Model for Semi-supervised Learning
https://github.com/WisconsinAIVision/YoLLaVA
공식 코드https://github.com/WongKinYiu/yolor
공식 코드https://github.com/Wuziyi616/EventCLIP
공식 코드https://github.com/XuanhaoLiu/mixEEG
공식 코드mixEEG: Enhancing EEG Federated Learning for Cross-subject EEG Classification with Tailored mixup
https://github.com/Yaan-Wang/CRLN
공식 코드https://github.com/YaoYao1995/Cross-Labeling-Supervision-for-Semi-Supervised-Learning
공식 코드CLS: Cross Labeling Supervision for Semi-Supervised Learning
https://github.com/Yikai-Wang/ICI-FSL
공식 코드https://github.com/YoucanBaby/VTG-GPT
공식 코드VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT
https://github.com/YuanEZhou/Grounded-Image-Captioning
공식 코드More Grounded Image Captioning by Distilling Image-Text Matching Model
https://github.com/YuanEZhou/satic
공식 코드https://github.com/Yushi-Hu/PromptCap
공식 코드https://github.com/ZJULearning/ALDA
공식 코드https://github.com/ZephyrZhuQi/ssbaseline
공식 코드Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps
https://github.com/aa200647963/sgg-dhl
공식 코드Dual-branch Hybrid Learning Network for Unbiased Scene Graph Generation
https://github.com/aalto-cbir/neuraltalkTheano
공식 코드https://github.com/aashish2000/anchor
공식 코드ANCHOR: LLM-driven News Subject Conditioning for Text-to-Image Synthesis
https://github.com/aashish2000/rona
공식 코드RONA: Pragmatically Diverse Image Captioning with Coherence Relations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.