https://github.com/pwc-1/Paper-9/tree/main/6/CAJ/src/models
Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning
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/pwc-1/Paper-9/tree/main/7/PR_Product
PR Product: A Substitute for Inner Product in Neural Networks
https://github.com/pytorch/vision
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
https://github.com/qibinc/KOBE
https://github.com/qingzwang/DiverseImageCaptioning
Towards Diverse and Accurate Image Captions via Reinforcing Determinantal Point Process
https://github.com/qingzwang/DiversityMetrics
https://github.com/quantum-fusion/AI-deeplearning
https://github.com/radpet/fake-news-detector
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/rahulvigneswaran/longtail-buzz
VirTex: Learning Visual Representations from Textual Annotations
https://github.com/rakshithShetty/captionGAN
https://github.com/raymondhs/fairseq-extensible-mbart
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
https://github.com/realmichaelye/NLP-State-of-the-art-Style-Transfer
Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
https://github.com/renmengye/rec-attend-public
https://github.com/renyuanL/ry-Speech-commands
https://github.com/rgarzonj/LSTMs
https://github.com/riron1206/kaggle_MoA
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/rishavbb/Image_Captioning
https://github.com/rishavbb/bottom_up_vqa
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/ronghanghu/natural-language-object-retrieval
https://github.com/ronghanghu/pythia
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/rpryzant/delete_retrieve_generate
Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
https://github.com/ruotianluo/GoogleConceptualCaptioning
https://github.com/ruotianluo/ImageCaptioning.pytorch
https://github.com/ruotianluo/Transformer_Captioning
https://github.com/ruotianluo/neuraltalk2.pytorch
https://github.com/ruxuan666/VQA_program
https://github.com/s-52/ImageCaptions
https://github.com/sahilkhose/floodnet_vqa
Semi-Supervised Classification and Segmentation on High Resolution Aerial Images
https://github.com/salaniz/pycocoevalcap
https://github.com/salanueva/UniVSE
Evaluating Multimodal Representations on Visual Semantic Textual Similarity
https://github.com/salesforce/blip
https://github.com/salesforce/qvr-simpledlm
https://github.com/salesforceairesearch/crmarena
Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning
https://github.com/samim23/NeuralTalkAnimator
https://github.com/sangHa0411/ImageNet
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
https://github.com/sangHa0411/VIT
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.