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/park-jungin/vlap
공식 코드Bridging Vision and Language Spaces with Assignment Prediction
https://github.com/pascalschlachter/planalysis
공식 코드Analysis of Pseudo-Labeling for Online Source-Free Universal Domain Adaptation
https://github.com/paulalbert31/pls
공식 코드Is your noise correction noisy? PLS: Robustness to label noise with two stage detection
https://github.com/paulalbert31/sncf
공식 코드Is your noise correction noisy? PLS: Robustness to label noise with two stage detection
https://github.com/paulgavrikov/vlm_shapebias
공식 코드https://github.com/paulsubarna/core-tokenset
공식 코드Core Tokensets for Data-efficient Sequential Training of Transformers
https://github.com/pengshuai-rin/multimath
공식 코드MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models
https://github.com/pengzai/aric
공식 코드https://github.com/peri044/STT
공식 코드https://github.com/peteanderson80/SPICE
공식 코드https://github.com/peteanderson80/bottom-up-attention
공식 코드Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/philm5/mscoco-spo-triples
공식 코드Image Captioning with Clause-Focused Metrics in a Multi-Modal Setting for Marketing
https://github.com/pinakinathc/fscoco
공식 코드FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context
https://github.com/pinterest/atg-research
공식 코드OmniSearchSage: Multi-Task Multi-Entity Embeddings for Pinterest Search
https://github.com/pioneerAlpha/BanglaImageCaptioning
공식 코드Bangla Image Caption Generation through CNN-Transformer based Encoder-Decoder Network
https://github.com/pixel-333/MRCMV
공식 코드Deep Music Retrieval for Fine-Grained Videos by Exploiting Cross-Modal-Encoded Voice-Overs
https://github.com/pluslabnlp/clipscore-bias
공식 코드Gender Biases in Automatic Evaluation Metrics for Image Captioning
https://github.com/pphub-hy/torch-tapnet
공식 코드Deep Learning based Intelligent Coin-tap Test for Defect Recognition
https://github.com/prantikbubun/beyond-pixels
공식 코드https://github.com/prdwb/okvqa-release
공식 코드Passage Retrieval for Outside-Knowledge Visual Question Answering
https://github.com/princeton-pli/vlm_s2h
공식 코드Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
https://github.com/princetonvisualai/DomainBiasMitigation
공식 코드Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
https://github.com/princetonvisualai/SPICE-U
공식 코드https://github.com/princetonvisualai/imagecaptioning-bias
공식 코드Understanding and Evaluating Racial Biases in Image Captioning
https://github.com/puchapu/utep
공식 코드Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling
https://github.com/pzzhang/VinVL
공식 코드VinVL: Revisiting Visual Representations in Vision-Language Models
https://github.com/qdin4048/CPL-OT
공식 코드Conflict-Aware Pseudo Labeling via Optimal Transport for Entity Alignment
https://github.com/qingzwang/GHA-ImageCaptioning
공식 코드https://github.com/qiumuyang/siab
공식 코드https://github.com/qiurui4shu/PIG
공식 코드https://github.com/qwenlm/qwen-vl
공식 코드Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
https://github.com/qy-feng/CRN
공식 코드https://github.com/rabiulcste/vqazero
공식 코드Investigating Prompting Techniques for Zero- and Few-Shot Visual Question Answering
https://github.com/raingo/TGIF-Release
공식 코드TGIF: A New Dataset and Benchmark on Animated GIF Description
https://github.com/rainyugg/blip-adapter
공식 코드BLIP-Adapter: Parameter-Efficient Transfer Learning for Mobile Screenshot Captioning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.