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/angienikki/openwusu
LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
https://github.com/anirbrhm/ImageCaptioning
https://github.com/anita76/linecapdataset
LineCap: Line Charts for Data Visualization Captioning Models
https://github.com/anitakumarijena/Image_Captioning
https://github.com/arjung128/image-paragraph-captioning
https://github.com/arodriguezca/uncertainty-ts-forecasting
https://github.com/arunadurai/Eye-For-Blind
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/atharv6/Image-Captioning
https://github.com/atun-MEI/AI-Course-Final
https://github.com/audio-captioning/caption-evaluation-tools
Improved Image Captioning via Policy Gradient optimization of SPIDEr
https://github.com/avitej-iyer/CapDec-Recreation
Text-Only Training for Image Captioning using Noise-Injected CLIP
https://github.com/b2renger/Runway-experiment-img2txt2img2txt
Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
https://github.com/baai-dcai/bunny
https://github.com/baaivision/eva
https://github.com/batra-mlp-lab/visdial-challenge-starter-pytorch
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/benpeloquin7/sapir_image_captioning
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/beresandras/semisupervised-classification-keras
https://github.com/bespontaneous/proteus-pytorch
Learning Vision from Models Rivals Learning Vision from Data
https://github.com/betterzh/sevlm-code
https://github.com/betterzh/sevlm-for-visual-art-comprehension
https://github.com/bharathbhimshetty/Image-Captioning-using-Show-Attend-and-Tell-paper
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/bloomberg/mixce-acl2023
How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
https://github.com/bmy4415/DMLAB-intern
https://github.com/borisdayma/clip-jax
https://github.com/brandon3964/multimodal-task-vector
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
https://github.com/brandontrabucco/cider
https://github.com/brandontrabucco/im2txt_express
Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
https://github.com/brandontrabucco/im2txt_match
Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
https://github.com/brandontrabucco/up_down_cell
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/brandontrabucco/up_down_rnn_cell
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/bytetriper/lm4lv
https://github.com/bzylich/persona-chatbot
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
https://github.com/caoquanjie/ConditionalLearnToPayAttention
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/cardwing/codes-for-pvkd
Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation
https://github.com/cattidea/VinVL-Paddle
VinVL: Revisiting Visual Representations in Vision-Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.