https://github.com/hoar012/rap-mllm
공식 코드RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models
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/hsiehjackson/mr.right
공식 코드Mr. Right: Multimodal Retrieval on Representation of ImaGe witH Text
https://github.com/huanglizi/lvit
공식 코드LViT: Language meets Vision Transformer in Medical Image Segmentation
https://github.com/huanzhang12/ImageCaptioningAttack
공식 코드https://github.com/hugomalard/aneyeforanear
공식 코드https://github.com/hugoschmutz/defixmatch
공식 코드Don't fear the unlabelled: safe semi-supervised learning via simple debiasing
https://github.com/huiimin5/comwin
공식 코드Compete to Win: Enhancing Pseudo Labels for Barely-supervised Medical Image Segmentation
https://github.com/hujiecpp/pais
공식 코드Pseudo-label Alignment for Semi-supervised Instance Segmentation
https://github.com/hust-jy/dds3d
공식 코드DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection
https://github.com/husthuaan/AAT
공식 코드Adaptively Aligned Image Captioning via Adaptive Attention Time
https://github.com/husthuaan/AoANet
공식 코드https://github.com/hwang1996/SGN
공식 코드Structure-Aware Generation Network for Recipe Generation from Images
https://github.com/hwanheelee1993/UMIC
공식 코드UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning
https://github.com/hyeonwoocho7/cng-sfda
공식 코드CNG-SFDA:Clean-and-Noisy Region Guided Online-Offline Source-Free Domain Adaptation
https://github.com/hyounghk/VideoQADenseCapFrameGate-ACL2020
공식 코드Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA
https://github.com/i-gao/adavision
공식 코드https://github.com/ids-cv/coling_iparaphrasing
공식 코드iParaphrasing: Extracting Visually Grounded Paraphrases via an Image
https://github.com/idstcv/coke
공식 코드Unsupervised Visual Representation Learning by Online Constrained K-Means
https://github.com/infly-ai/inf-mllm
공식 코드https://github.com/inhwanbae/lmtrajectory
공식 코드Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction
https://github.com/ipmi-nwu/helpnet
공식 코드https://github.com/ischenawei/dmnil
공식 코드Without Paired Labeled Data: An End-to-End Self-Supervised Paradigm for UAV-View Geo-Localization
https://github.com/ispc-lab/bmd
공식 코드https://github.com/isunLt/IUPC
공식 코드Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning
https://github.com/j-min/VL-T5
공식 코드https://github.com/j-min/clip-caption-reward
공식 코드https://github.com/j-min/dalleval
공식 코드DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models
https://github.com/jacobswan1/ViTCAP
공식 코드Injecting Semantic Concepts into End-to-End Image Captioning
https://github.com/jamycheung/trans4pass
공식 코드https://github.com/janghyuncho/decola
공식 코드https://github.com/jay-codeman/sage
공식 코드https://github.com/jbdel/WMT18_MNMT
공식 코드https://github.com/jchenghu/captioning_eos
공식 코드A request for clarity over the End of Sequence token in the Self-Critical Sequence Training
https://github.com/jchenghu/expansionnet_v2
공식 코드Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning
https://github.com/jchenghu/sacreeos
공식 코드A request for clarity over the End of Sequence token in the Self-Critical Sequence Training
https://github.com/jcjohnson/densecap
공식 코드DenseCap: Fully Convolutional Localization Networks for Dense Captioning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.