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/bigvideoresearch/Enigma
공식 코드Webly Supervised Image Classification with Self-Contained Confidence
https://github.com/bigvideoresearch/SCC
공식 코드Webly Supervised Image Classification with Self-Contained Confidence
https://github.com/bit-da/domain-oriented-transformer
공식 코드Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation
https://github.com/bladedancer957/finer
공식 코드https://github.com/bladedancer957/iner_rdp
공식 코드Task Relation Distillation and Prototypical Pseudo Label for Incremental Named Entity Recognition
https://github.com/bladewaltz1/modecap
공식 코드Learning Distinct and Representative Styles for Image Captioning
https://github.com/blmoistawinde/fense
공식 코드https://github.com/bobleegogogo/building_height
공식 코드https://github.com/boreng0817/ifcap
공식 코드IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning
https://github.com/brandonhanx/fame-vil
공식 코드FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks
https://github.com/bryanyu1997/data-efficient-3d-learner
공식 코드Data Efficient 3D Learner via Knowledge Transferred from 2D Model
https://github.com/bupt-ai-cz/IAST-ECCV2020
공식 코드Instance Adaptive Self-Training for Unsupervised Domain Adaptation
https://github.com/bupt-ai-cz/hhcl-reid
공식 코드Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification
https://github.com/bupt-ai-cz/hiast
공식 코드Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation
https://github.com/bupt-ai-cz/proml
공식 코드Semi-supervised Domain Adaptation via Prototype-based Multi-level Learning
https://github.com/buxiangzhiren/ddcap
공식 코드https://github.com/bytedance/valley
공식 코드Valley2: Exploring Multimodal Models with Scalable Vision-Language Design
https://github.com/c-juhwan/gpt-multilingual-annotator
공식 코드GPTs Are Multilingual Annotators for Sequence Generation Tasks
https://github.com/caicch/OS-WSGIC
공식 코드Top-Down Framework for Weakly-supervised Grounded Image Captioning
https://github.com/cainand/refav
공식 코드https://github.com/camma-public/surg-ftda
공식 코드Text-driven Adaptation of Foundation Models for Few-shot Surgical Workflow Analysis
https://github.com/canbaoburen/CoDT
공식 코드https://github.com/cao-cong/ads-semiseg
공식 코드https://github.com/caraj7/comat
공식 코드CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
https://github.com/carrotsniper/bp-sgcn
공식 코드https://github.com/castorini/unirag
공식 코드UniRAG: Universal Retrieval Augmentation for Large Vision Language Models
https://github.com/cesc-park/attend2u
공식 코드Attend to You: Personalized Image Captioning with Context Sequence Memory Networks
https://github.com/ch3cook-fdu/vote2cap-detr
공식 코드https://github.com/chaneyddtt/UDA-Animal-Pose
공식 코드From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation
https://github.com/chaneyddtt/scarcenet
공식 코드https://github.com/changdaeoh/multimodal-mixup
공식 코드https://github.com/changxinwang/boficap
공식 코드Bounding and Filling: A Fast and Flexible Framework for Image Captioning
https://github.com/chauncey-tow/mrg-clip
공식 코드UniCrossAdapter: Multimodal Adaptation of CLIP for Radiology Report Generation
https://github.com/chen-xin-94/dart
공식 코드https://github.com/chen-yang-liu/awesome-rs-temporal-vlm
공식 코드Remote Sensing Temporal Vision-Language Models: A Comprehensive Survey
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.