https://github.com/rajpurkarlab/x-rem
공식 코드Multimodal Image-Text Matching Improves Retrieval-based Chest X-Ray Report Generation
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/ramprs/grad-cam
공식 코드https://github.com/rasoolims/ImageTranslate
공식 코드"Wikily" Supervised Neural Translation Tailored to Cross-Lingual Tasks
https://github.com/reactivetype/simrod
공식 코드SimROD: A Simple Adaptation Method for Robust Object Detection
https://github.com/rebnej/libra
공식 코드https://github.com/rebnej/lick-caption-bias
공식 코드https://github.com/recklessronan/muse
공식 코드https://github.com/rhfeiyang/SPPOT
공식 코드SP$^2$OT: Semantic-Regularized Progressive Partial Optimal Transport for Imbalanced Clustering
https://github.com/rhfeiyang/ppot
공식 코드P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering
https://github.com/ricardooyoung/versatileteacher
공식 코드Versatile Teacher: A Class-aware Teacher-student Framework for Cross-domain Adaptation
https://github.com/richardaecn/cvpr18-caption-eval
공식 코드https://github.com/ritaramo/extra
공식 코드https://github.com/ritaramo/lmcap
공식 코드LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting
https://github.com/ritaramo/smallcap
공식 코드SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation
https://github.com/rizal-rovins/hybrid-image-captioning-model
공식 코드https://github.com/rlhf-v/rlaif-v
공식 코드RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
https://github.com/rlhf-v/rlhf-v
공식 코드https://github.com/rlqja1107/NL-VSGG
공식 코드Weakly Supervised Video Scene Graph Generation via Natural Language Supervision
https://github.com/rmokady/clip_prefix_caption
공식 코드https://github.com/rshaojimmy/seqdeepfake
공식 코드https://github.com/ruiyang-061x/lise
공식 코드Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scene
https://github.com/runminjiang/pw4medseg
공식 코드Enhancing Weakly Supervised 3D Medical Image Segmentation through Probabilistic-aware Learning
https://github.com/ruotianluo/DiscCaptioning
공식 코드Discriminability objective for training descriptive captions
https://github.com/ruotianluo/coco-caption
공식 코드https://github.com/ruotianluo/self-critical.pytorch
공식 코드https://github.com/rvandeghen/ASTOD
공식 코드https://github.com/rwightman/pytorch-image-models
공식 코드MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
https://github.com/s-gupta/visual-concepts
공식 코드https://github.com/saba96/img-cap-metrics-robustness
공식 코드An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics
https://github.com/safouaneelg/SRT2I
공식 코드Class-Conditional self-reward mechanism for improved Text-to-Image models
https://github.com/sahar-nasiri/dist
공식 코드Dual Invariance Self-training for Reliable Semi-supervised Surgical Phase Recognition
https://github.com/sahilkhose/FloodNet
공식 코드Semi-Supervised Classification and Segmentation on High Resolution Aerial Images
https://github.com/sail-sg/ptp
공식 코드Position-guided Text Prompt for Vision-Language Pre-training
https://github.com/sakura-not-sleep/ca_fvd
공식 코드Consistency-aware Fake Videos Detection on Short Video Platforms
https://github.com/salah-zaiem/Pseudo-Label-Selection
공식 코드https://github.com/salanueva/CBM
공식 코드Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question Answering
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.