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/lizhuohong/segland
https://github.com/llijiang/GuidedContrast
Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation
https://github.com/longjj/Caffe-SGDR
https://github.com/lovit/KoBERTScore
https://github.com/lovit/ko-BERTScore
https://github.com/lseventeen/phtrans
Combining Self-Training and Hybrid Architecture for Semi-supervised Abdominal Organ Segmentation
https://github.com/lucidrains/CoCa-pytorch
CoCa: Contrastive Captioners are Image-Text Foundation Models
https://github.com/lucidrains/bit-diffusion
Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
https://github.com/lucidrains/chroma-pytorch
Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
https://github.com/lucidrains/imagen-pytorch
Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
https://github.com/lucylow/En_francais_si_vous_plait-
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
https://github.com/ludwig-ai/ludwig
https://github.com/lukemelas/image-paragraph-captioning
https://github.com/luo-z13/pointobb
PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection
https://github.com/luomancs/alternative_answer_set
https://github.com/luoweizhou/coco-caption
https://github.com/lupantech/MathVista
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
https://github.com/luulinh90s/Contcap
ContCap: A scalable framework for continual image captioning
https://github.com/lvapeab/coco-caption
https://github.com/lvyufeng/image_captioning_mindspore
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/lx709/reobench
VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
https://github.com/lzw-lzw/awesome-remote-sensing-vision-language-models
Vision-Language Models in Remote Sensing: Current Progress and Future Trends
https://github.com/mamhoud/CapstoneProject
A Critical Review of Recurrent Neural Networks for Sequence Learning
https://github.com/marccanby/bidi_decoding
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
https://github.com/marioskatsak/mapert
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/martin-gorner/tensorflow-rnn-shakespeare
https://github.com/martincss/first-captioning
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/mashaan14/SENTRY-toy
SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation
https://github.com/matakshay/Neural_Image_Caption_Generator
https://github.com/mattdeitke/cvpr-buzz
VirTex: Learning Visual Representations from Textual Annotations
https://github.com/maxy0524/image_captioning
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/maz0318/nlpSummerCamp2019
https://github.com/mazm13/Image-to-Tree.pytorch
https://github.com/mchong6/Semantic_Adversarial_Cadv
https://github.com/meiqiguo/iccv2021-atypicalitydetection
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.