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/Dlut-lab-zmn/Image-Captioning-Attack
https://github.com/DonghwanKIM0101/CS492I_CV
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
https://github.com/Draven-Lee/COVID-19-CT-Reports-Generation
Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generation
https://github.com/E-DEEP/PapersReview
https://github.com/Evolving-AI-Lab/ppgn
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
https://github.com/FJSam/SelfCritical_ImageCaptioning
https://github.com/Faceplugin-ltd/FaceRecognition-Android
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
https://github.com/FengSuSky/CCB-VQA
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/FerryHuang/SimVLM
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
https://github.com/FredericGodin/QuasiRNN-DReLU
https://github.com/GJTNB/reading-memo
Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID
https://github.com/Goodideax/lstm-negtive
https://github.com/Goodideax/rnn_neg_efficient
https://github.com/Gowthamkar6/Image-captioning-using-CNN-RNN
https://github.com/Guillem96/zsl-pytorch
https://github.com/HaleyPei/Implement-of-SCA-CNN
SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning
https://github.com/HemanthTejaY/Deep-Learning-Image-Captioning---A-comparitive-study
Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training
https://github.com/HiLab-git/DTC
Semi-supervised Left Atrium Segmentation with Mutual Consistency Training
https://github.com/HughKu/Im2txt
Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
https://github.com/Hyeongkeun/LAVCap
LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport
https://github.com/IBM/Image-Captioning-Attack
https://github.com/IBM/wasserstein-barycenters
https://github.com/INZHAGY/WDA-Net
Weakly-Supervised Cross-Domain Segmentation of Electron Microscopy with Sparse Point Annotation
https://github.com/IPINGCHOU/NTU_MachineLearning
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
https://github.com/IlyaDobrynin/GridMixup
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
https://github.com/InnerPeace-Wu/im2p-tensorflow
A Hierarchical Approach for Generating Descriptive Image Paragraphs
https://github.com/IzabelaKrupinska/PROJBAD
Deep Visual-Semantic Alignments for Generating Image Descriptions
https://github.com/JHKim-snu/GVCCI
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/JHKim-snu/PGA
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/JP-MRPhys/bayesianLSTM
https://github.com/JamesLuoyh/character-level-soft-and-hard-attention
Hard Non-Monotonic Attention for Character-Level Transduction
https://github.com/Japanese-Image-Captioning/ClipCap-for-Japanese
https://github.com/Japanese-Image-Captioning/M2-transformer-for-Japanese
https://github.com/Japanese-Image-Captioning/ORT-for-Japanese
https://github.com/Japanese-Image-Captioning/SAT-for-Japanese
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.