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/changji2069/Scope-Project
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/changji2069/literature-review
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/chengding0713/awesome-ppg-af-detection
https://github.com/chengglmotto/AGC-DRR
GraphLearner: Graph Node Clustering with Fully Learnable Augmentation
https://github.com/chenggongliang/arcface
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
https://github.com/chenguolin/DiffSplat
https://github.com/chenhaomingbob/WS3-mindspore
Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud
https://github.com/chenxinpeng/im2p
A Hierarchical Approach for Generating Descriptive Image Paragraphs
https://github.com/chingyaoc/vqg-tensorflow
https://github.com/chirag26495/DAN_VQA
https://github.com/chongweiliu/DUT-USEG
https://github.com/chrisc36/bottom-up-attention-vqa
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/chriswegmann/drone_steering
Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video
https://github.com/chunlei2/show-and-tell
https://github.com/cindyxinyiwang/fairseq
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
https://github.com/cjlovering/Towards-Interpretable-Reinforcement-Learning-Using-Attention-Augmented-Agents-Replication
Towards Interpretable Reinforcement Learning Using Attention Augmented Agents
https://github.com/clip-vil/CLIP-ViL
https://github.com/clip-vil/cider
https://github.com/codecaution/evomoe
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
https://github.com/codehacpj/Image_description
https://github.com/codekansas/keras-language-modeling
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/coldmanck/show-attend-and-tell
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
https://github.com/congvm-it/pyciderevalcap
https://github.com/csalt-research/perturb-predict-paraphrase
https://github.com/cshizhe/asg2cap
Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs
https://github.com/ctr4si/attend2u
Attend to You: Personalized Image Captioning with Context Sequence Memory Networks
https://github.com/cvtower/seesawfacenet_pytorch
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
https://github.com/cyr19/reproducibility
https://github.com/danielajisafe/Image-Captioning-Model
https://github.com/danieldeutsch/bert_score_content_analysis
https://github.com/dannigt/fairseq
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
https://github.com/daqingliu/coco-caption
https://github.com/davidgolub/charizard
Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
https://github.com/davinhill/Convolution_Captioning
https://github.com/dbash/zerowaste
RISE: Randomized Input Sampling for Explanation of Black-box Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.