https://github.com/yangdsh/VQA-BUTD-demo
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
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/yangletliu/finlora
https://github.com/yangyucheng000/University/tree/main/model-1/pix2struct
Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
https://github.com/yangyucheng000/University/tree/main/model-2/blip_2
https://github.com/yanxinyan1/yxy
https://github.com/yaoli/arctic-capgen-vid
https://github.com/yaolinli/capenrich
VinVL: Revisiting Visual Representations in Vision-Language Models
https://github.com/yashk2810/Image-Captioning
https://github.com/yifanh1/gqa_pytorch
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/yiskw713/RISE
RISE: Randomized Input Sampling for Explanation of Black-box Models
https://github.com/yiwuzhong/sub-gc
Comprehensive Image Captioning via Scene Graph Decomposition
https://github.com/yiyixuxu/denoising-diffusion-flax
Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
https://github.com/ylqi/gl-rg
https://github.com/ys-zong/medfair
Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
https://github.com/yuchuantian/u-dit
Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models
https://github.com/yufengm/Adaptive
Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning
https://github.com/yuhui-zh15/nlg_metrics
https://github.com/yukw777/videoblip
https://github.com/yuleiqin/capro
Webly Supervised Image Classification with Self-Contained Confidence
https://github.com/yuleiqin/fopro
Webly Supervised Image Classification with Self-Contained Confidence
https://github.com/yulong-XJTU/SimVLM
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
https://github.com/yunjey/show-attend-and-tell
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/yurayli/image-caption-pytorch
https://github.com/yurayli/image_caption_pytorch
https://github.com/yuyay/chainer_nic
https://github.com/yxgeee/MMT-plus
Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID
https://github.com/yyliu01/tracoco
Semi-supervised Left Atrium Segmentation with Mutual Consistency Training
https://github.com/zelaki/wsac
Text-Only Training for Image Captioning using Noise-Injected CLIP
https://github.com/zhang0jhon/AttentionOCR
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/zhangzibin/char-rnn-chinese
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
https://github.com/zhaochongan/coseg
Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model
https://github.com/zheangh/dfg
Context-Aware Pseudo-Label Refinement for Source-Free Domain Adaptive Fundus Image Segmentation
https://github.com/zhengxiangshi/powerfulpromptft
https://github.com/zhihaozhang97/ru-ai
Text-Free Image-to-Speech Synthesis Using Learned Segmental Units
https://github.com/zixuwang1996/VQA-reading-list
Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering
https://github.com/zkcys001/awesome-Semi-WeakPersonReID
Weakly supervised discriminative feature learning with state information for person identification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.