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/allenai/close
공식 코드I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision
https://github.com/allenai/molmo
공식 코드Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
https://github.com/allenai/x-lxmert
공식 코드X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
https://github.com/alpc91/transda
공식 코드Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation
https://github.com/alpha-innovator/omnicaptioner
공식 코드https://github.com/alteia-ai/icss
공식 코드Weakly-supervised continual learning for class-incremental segmentation
https://github.com/aman-4-real/see-or-guess
공식 코드https://github.com/amanmohanty/idl-nncompress
공식 코드Efficient CNN-LSTM based Image Captioning using Neural Network Compression
https://github.com/amitakamath/vl_text_encoders_are_bottlenecks
공식 코드Text encoders bottleneck compositionality in contrastive vision-language models
https://github.com/amzn/confident-sinkhorn-allocation
공식 코드https://github.com/amzn/pretraining-or-self-training
공식 코드https://github.com/anasemad11/c2fpl
공식 코드A Coarse-to-Fine Pseudo-Labeling (C2FPL) Framework for Unsupervised Video Anomaly Detection
https://github.com/anastasiakrith/llm-for-vwsd
공식 코드Language Models as Knowledge Bases for Visual Word Sense Disambiguation
https://github.com/andreacorsini1/selflabelingjobshop
공식 코드https://github.com/andst/text_guided_cl
공식 코드https://github.com/andy412510/tcmm
공식 코드https://github.com/annabeth-h/styled-and-diverse-image-captioning
공식 코드Diverse and Styled Image Captioning Using SVD-Based Mixture of Recurrent Experts
https://github.com/anok3111/loco
공식 코드Low-Contrast-Enhanced Contrastive Learning for Semi-Supervised Endoscopic Image Segmentation
https://github.com/anord-wang/kgptfs
공식 코드Knockoff-Guided Feature Selection via A Single Pre-trained Reinforced Agent
https://github.com/apple/ml-mobileclip
공식 코드MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
https://github.com/apple1986/samatch
공식 코드A SAM-guided and Match-based Semi-Supervised Segmentation Framework for Medical Imaging
https://github.com/artanic30/maccap
공식 코드Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training
https://github.com/asad1996172/Obfuscation-Detection
공식 코드https://github.com/ashwinkalyan/dbs
공식 코드Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
https://github.com/assafbk/mocha_code
공식 코드https://github.com/awslabs/sockeye
공식 코드Image Captioning as Neural Machine Translation Task in SOCKEYE
https://github.com/axi404/pmt
공식 코드https://github.com/baai-dcai/visual-instruction-tuning
공식 코드https://github.com/baaivision/emu
공식 코드https://github.com/barrett-python/sfc
공식 코드SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation
https://github.com/bastienvanderplaetse/gan-image-captioning
공식 코드https://github.com/baxiyi/dut-useg
공식 코드https://github.com/bbuing9/DARP
공식 코드Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
https://github.com/bdvllrs/bimgw
공식 코드Semi-supervised Multimodal Representation Learning through a Global Workspace
https://github.com/bearcatt/LaBERT
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.