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/deepinsight/insightface
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
https://github.com/detectiveli/PSMA
https://github.com/dgonzalez-ri/neural-visual-storyteller
Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
https://github.com/dhecloud/simple_language_modelling
https://github.com/dianaglzrico/neural-visual-storyteller
Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
https://github.com/diegobonilla98/PixLore
https://github.com/divyanshpuri02/COCO_2018-Stuff-Segmentation-Challenge
https://github.com/djain454/Show-Attend-and-Tell-Neural-Image-Caption-Generation-with-Visual-Attention
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/dmcv-ecnu/MindSpore_ModelZoo/tree/main/WS3_MindSpore
Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud
https://github.com/doc-doc/NExT-OE
https://github.com/dongdong69/MixAugmentation
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
https://github.com/doubledaibo/gancaption_iccv2017
Towards Diverse and Natural Image Descriptions via a Conditional GAN
https://github.com/dreamstorm25/Generating-Natural-Questions-from-an-Image
https://github.com/dtak/local-independence-public
https://github.com/elliottd/GroundedTranslation
https://github.com/elliottd/compareImageDescriptionMeasures
https://github.com/entalent/MemCap
https://github.com/eric-erki/insightface
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
https://github.com/eric-xw/AREL
No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
https://github.com/exgc/r1v-free
https://github.com/facebookresearch/ActivityNet-Entities
Learning to Generate Grounded Visual Captions without Localization Supervision
https://github.com/facebookresearch/DomainBed
Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases
https://github.com/facebookresearch/LaMCTS
Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search
https://github.com/facebookresearch/chameleon
https://github.com/facebookresearch/fairseq
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
https://github.com/facebookresearch/flowmm
Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
https://github.com/facebookresearch/grid-feats-vqa
https://github.com/facebookresearch/meru
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts
https://github.com/facebookresearch/mmf
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/facebookresearch/msn
https://github.com/facebookresearch/multimodal
CoCa: Contrastive Captioners are Image-Text Foundation Models
https://github.com/fairseq/fairseq
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
https://github.com/fanchenyou/deepdiary
https://github.com/farazahmeds/Classification-of-brain-tumor-using-Spatiotemporal-models
ConvNet Architecture Search for Spatiotemporal Feature Learning
https://github.com/fawazsammani/knowing-when-to-look-adaptive-attention
Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.