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/microsoft/unilm/tree/master/beit
공식 코드Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks
https://github.com/microsoft/unilm/tree/master/kosmos-2
공식 코드Kosmos-2: Grounding Multimodal Large Language Models to the World
https://github.com/mightyzau/infmllm
공식 코드https://github.com/milkxie/ssmll-cap
공식 코드Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning
https://github.com/milomilo0320/a-semi-automatic-annotation-software-for-scene-graph
공식 코드GeneAnnotator: A Semi-automatic Annotation Tool for Visual Scene Graph
https://github.com/mingukjang/tast
공식 코드Test-Time Adaptation via Self-Training with Nearest Neighbor Information
https://github.com/mitjanikolaus/compositional-image-captioning
공식 코드https://github.com/mjhucla/Google_Refexp_toolbox
공식 코드Generation and Comprehension of Unambiguous Object Descriptions
https://github.com/mjhucla/mRNN-CR
공식 코드Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
https://github.com/ml-jku/semantic-image-text-alignment
공식 코드Linear Alignment of Vision-language Models for Image Captioning
https://github.com/ml-research/ILLUME
공식 코드ILLUME: Rationalizing Vision-Language Models through Human Interactions
https://github.com/mlii0117/COV-CTR
공식 코드Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generation
https://github.com/mlspeech/gradseg
공식 코드Unsupervised Word Segmentation Using Temporal Gradient Pseudo-Labels
https://github.com/monikshah/caption-explanation-hmln
공식 코드Disentangling Fine-Tuning from Pre-Training in Visual Captioning with Hybrid Markov Logic
https://github.com/moranyanuka/KnowAda
공식 코드Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions
https://github.com/moucheng2017/emssl
공식 코드https://github.com/movinghoon/mira
공식 코드Unsupervised Visual Representation Learning via Mutual Information Regularized Assignment
https://github.com/mpsc-umbc/efficient-vision-language-models-a-survey
공식 코드https://github.com/mpsych/boostlet
공식 코드Boostlet.js: Image processing plugins for the web via JavaScript injection
https://github.com/mshaikh2/MMRL
공식 코드https://github.com/mtanti/quantifing-visual-information
공식 코드Quantifying the amount of visual information used by neural caption generators
https://github.com/mtanti/rnn-role
공식 코드What is the Role of Recurrent Neural Networks (RNNs) in an Image Caption Generator?
https://github.com/mu-y/mpl-mdd
공식 코드https://github.com/multimodal-interpretability/nnn
공식 코드Nearest Neighbor Normalization Improves Multimodal Retrieval
https://github.com/multimodalmi/multimodal-membership-inference
공식 코드https://github.com/mxahan/nev-ncd
공식 코드Novel Categories Discovery Via Constraints on Empirical Prediction Statistics
https://github.com/mxbh/spatiotemporal-ssl
공식 코드https://github.com/mzhaoshuai/rlcf
공식 코드Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
https://github.com/naver-ai/cream
공식 코드https://github.com/naver-ai/mid.metric
공식 코드Mutual Information Divergence: A Unified Metric for Multimodal Generative Models
https://github.com/naver-intel-co-lab/gaudi-lavcap
공식 코드LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport
https://github.com/naver/posescript
공식 코드https://github.com/nayeemrizve/trssl
공식 코드https://github.com/nayeemrizve/ups
공식 코드https://github.com/nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.