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/salesforce/inv-cdip
공식 코드https://github.com/salesforce/lavis
공식 코드https://github.com/sam-rag/sam_rag
공식 코드https://github.com/savinay95n/PatchRefineNet
공식 코드https://github.com/scb-10x/typhoon2-audio
공식 코드Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models
https://github.com/sdc17/crossget
공식 코드CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
https://github.com/sdc17/upop
공식 코드UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
https://github.com/seefreem/meme_text_retrieval_p1
공식 코드Large Vision-Language Models for Knowledge-Grounded Data Annotation of Memes
https://github.com/seermer/RTGen
공식 코드RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection
https://github.com/sensengao/vlptransferattack
공식 코드https://github.com/seonghoon-yu/pseudo-ris
공식 코드Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation
https://github.com/shakeebmurtaza/dips
공식 코드https://github.com/shanghai-digital-brain-laboratory/bdm-db1
공식 코드https://github.com/shashiongithub/sidenet
공식 코드https://github.com/sheffieldnlp/foildataset
공식 코드https://github.com/shengcao-cao/cmt
공식 코드Contrastive Mean Teacher for Domain Adaptive Object Detectors
https://github.com/shengcheng/captions4t2i
공식 코드Precision or Recall? An Analysis of Image Captions for Training Text-to-Image Generation Model
https://github.com/shenkev/Caption-Lifetime-by-Asking-Questions
공식 코드Learning to Caption Images through a Lifetime by Asking Questions
https://github.com/shi-labs/cumo
공식 코드CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
https://github.com/shi-labs/vcoder
공식 코드VCoder: Versatile Vision Encoders for Multimodal Large Language Models
https://github.com/shi-labs/versatile-diffusion
공식 코드Versatile Diffusion: Text, Images and Variations All in One Diffusion Model
https://github.com/shigemichimatsuzaki/ms2pl
공식 코드https://github.com/shijiangming1/mmm
공식 코드Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification
https://github.com/shijie-wu/neural-transducer
공식 코드Hard Non-Monotonic Attention for Character-Level Transduction
https://github.com/shikha-gist/image-captioning
공식 코드Label-Attention Transformer with Geometrically Coherent Objects for Image Captioning
https://github.com/shikras/shikra
공식 코드Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
https://github.com/shishuaihu/prosfda
공식 코드ProSFDA: Prompt Learning based Source-free Domain Adaptation for Medical Image Segmentation
https://github.com/shjo-april/recurseed_and_edgepredictmix
공식 코드https://github.com/shtuplus/iccc_cvpr2024
공식 코드Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning
https://github.com/shuchangye-bib/sgseg
공식 코드https://github.com/shunqim/ctrl-cic
공식 코드https://github.com/shuvenduroy/ssl_fer
공식 코드Analysis of Semi-Supervised Methods for Facial Expression Recognition
https://github.com/shuvenduroy/ssl_fer_ood
공식 코드https://github.com/si0wang/vicrit
공식 코드ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
https://github.com/siddiquemu/sct_mcta
공식 코드Tracking Passengers and Baggage Items using Multiple Overhead Cameras at Security Checkpoints
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.