https://github.com/lyan62/RobustCap
공식 코드Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning
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/lyan62/data-curation
공식 코드https://github.com/lzrobots/DeepEmbeddingModel_ZSL
공식 코드https://github.com/machengcheng2016/crossteaching-ssod
공식 코드CrossRectify: Leveraging Disagreement for Semi-supervised Object Detection
https://github.com/mad-red/VSR-guided-CIC
공식 코드Human-like Controllable Image Captioning with Verb-specific Semantic Roles
https://github.com/mair-lab/mapl
공식 코드https://github.com/mamadou-keita/vlm-detect
공식 코드Bi-LORA: A Vision-Language Approach for Synthetic Image Detection
https://github.com/mansoor-at/semi-supervised-surgical-tool-detection
공식 코드A semi-supervised Teacher-Student framework for surgical tool detection and localization
https://github.com/maoyj1998/transdic
공식 코드https://github.com/matfrei/clipmasterprints
공식 코드Fooling Contrastive Language-Image Pre-trained Models with CLIPMasterPrints
https://github.com/matinmoezzi/ups_conformal_classification
공식 코드An Uncertainty-Aware Pseudo-Label Selection Framework using Regularized Conformal Prediction
https://github.com/matsuo-shinnosuke/online-pseudo-labeling
공식 코드Learning from Label Proportion with Online Pseudo-Label Decision by Regret Minimization
https://github.com/matthewcym/sflm
공식 코드Revisiting Self-Training for Few-Shot Learning of Language Model
https://github.com/mattochal/enhanced-outlier-logits
공식 코드EOL: Transductive Few-Shot Open-Set Recognition by Enhancing Outlier Logits
https://github.com/mbzuai-oryx/groundingLMM
공식 코드https://github.com/mediatechnologycenter/aestheval
공식 코드Understanding Aesthetics with Language: A Photo Critique Dataset for Aesthetic Assessment
https://github.com/megvii-basedetection/denseteacher
공식 코드Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection
https://github.com/megvii-research/co-mining
공식 코드Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection
https://github.com/megvii-research/fullmatch
공식 코드Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data
https://github.com/meitounao110/uge-st
공식 코드Uncertainty Guided Ensemble Self-Training for Semi-Supervised Global Field Reconstruction
https://github.com/merterm/cosmic
공식 코드COSMic: A Coherence-Aware Generation Metric for Image Descriptions
https://github.com/mesophil/myriadal
공식 코드https://github.com/miaomiaoli2/ruleprompt
공식 코드https://github.com/miccaiif/dgmil
공식 코드DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classification
https://github.com/miccaiif/ins
공식 코드https://github.com/michaelvorndran/inconsistencymasks
공식 코드Inconsistency Masks: Removing the Uncertainty from Input-Pseudo-Label Pairs
https://github.com/michigannlp/mosaic
공식 코드The Power of Many: Multi-Agent Multimodal Models for Cultural Image Captioning
https://github.com/microsoft/GLIP
공식 코드GLIPv2: Unifying Localization and Vision-Language Understanding
https://github.com/microsoft/GenerativeImage2Text
공식 코드GIT: A Generative Image-to-text Transformer for Vision and Language
https://github.com/microsoft/LLM2CLIP
공식 코드LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation
https://github.com/microsoft/Oscar
공식 코드Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
https://github.com/microsoft/PICa
공식 코드An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA
https://github.com/microsoft/ProDA
공식 코드https://github.com/microsoft/SoftTeacher
공식 코드End-to-End Semi-Supervised Object Detection with Soft Teacher
https://github.com/microsoft/UniTAB
공식 코드UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling
https://github.com/microsoft/fiber
공식 코드Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.