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/chenxi52/upa
공식 코드Uncertainty-Aware Pseudo-Label Filtering for Source-Free Unsupervised Domain Adaptation
https://github.com/chenxinpeng/ARNet
공식 코드Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present
https://github.com/chihyaoma/cyclical-visual-captioning
공식 코드Learning to Generate Grounded Visual Captions without Localization Supervision
https://github.com/christmasfan/ssl_denoising_segmentation
공식 코드Pseudo-Label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation
https://github.com/chu0802/sla
공식 코드Semi-Supervised Domain Adaptation with Source Label Adaptation
https://github.com/chumsy0725/fbc-sa
공식 코드https://github.com/chunhuizng/mllm-video-captioner
공식 코드https://github.com/ciampluca/diffusion_semi_supervised_biomedical_image_segmentation
공식 코드Semi-Supervised Biomedical Image Segmentation via Diffusion Models and Teacher-Student Co-Training
https://github.com/ciodar/cultural-heritage-diffaug
공식 코드Diffusion Based Augmentation for Captioning and Retrieval in Cultural Heritage
https://github.com/claudaff/automatic-map-storytelling
공식 코드An Efficient System for Automatic Map Storytelling -- A Case Study on Historical Maps
https://github.com/clovaai/CutMix-PyTorch
공식 코드CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
https://github.com/codegallery24/cpcl
공식 코드https://github.com/computational-cell-analytics/probabilistic-domain-adaptation
공식 코드Probabilistic Domain Adaptation for Biomedical Image Segmentation
https://github.com/computationalmedia/semstyle
공식 코드SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text
https://github.com/computer-vision-in-the-wild/cvinw_readings
공식 코드Vision-Language Pre-training: Basics, Recent Advances, and Future Trends
https://github.com/contentandmaterialportrait/mae-gebd
공식 코드Masked Autoencoders for Generic Event Boundary Detection CVPR'2022 Kinetics-GEBD Challenge
https://github.com/crockwell/cap3d
공식 코드https://github.com/csimo005/summit
공식 코드SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets
https://github.com/cskyl/sam_wsss
공식 코드Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation
https://github.com/ctu-vras/t-concord3d
공식 코드Teachers in concordance for pseudo-labeling of 3D sequential data
https://github.com/cuhk-aim-group/diffrect
공식 코드DiffRect: Latent Diffusion Label Rectification for Semi-supervised Medical Image Segmentation
https://github.com/curryyuan/x-trans2cap
공식 코드X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning
https://github.com/cvlab-stonybrook/Weighting-Pseudo-Labels
공식 코드https://github.com/cvlab-stonybrook/beyond-pixels
공식 코드https://github.com/czm369/mixpl
공식 코드https://github.com/d10andy/sad
공식 코드https://github.com/damo-nlp-sg/contproto
공식 코드https://github.com/dandoge/palm
공식 코드https://github.com/danielabd/apollo-cap
공식 코드Apollo: Zero-shot MultiModal Reasoning with Multiple Experts
https://github.com/danikiyasseh/SoCal
공식 코드SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac Signals
https://github.com/danikiyasseh/SoQal
공식 코드SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac Signals
https://github.com/danoneata/strim
공식 코드https://github.com/daqingliu/CAVP
공식 코드Context-Aware Visual Policy Network for Sequence-Level Image Captioning
https://github.com/dataminr-ai/joganic
공식 코드https://github.com/datamllab/Mitigating_Gender_Bias_In_Captioning_System
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.