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/kaelsunkiller/vat
공식 코드https://github.com/kaiizhang/mfa
공식 코드Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation
https://github.com/kakaobrain/magvlt
공식 코드https://github.com/kakaobrain/noc
공식 코드Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning
https://github.com/kangreen0210/lime
공식 코드https://github.com/kangreen0210/lime-m
공식 코드https://github.com/karpathy/neuraltalk2
공식 코드https://github.com/katiefraser/pairs
공식 코드https://github.com/kdexd/virtex
공식 코드VirTex: Learning Visual Representations from Textual Annotations
https://github.com/keio-smilab23/JaSPICE
공식 코드JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models
https://github.com/keio-smilab24/Polos
공식 코드Polos: Multimodal Metric Learning from Human Feedback for Image Captioning
https://github.com/keums/icassp2022-vocal-transcription
공식 코드https://github.com/kezheng1204/integer
공식 코드Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration
https://github.com/khadidja-delloul/rgb-d-theatre-scenes-dataset
공식 코드TS-RGBD Dataset: a Novel Dataset for Theatre Scenes Description for People with Visual Impairments
https://github.com/khuangaf/chocolate
공식 코드Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning
https://github.com/kien085/sg2caps
공식 코드https://github.com/kinpzz/udasod-upl
공식 코드https://github.com/kondiz/fraternal-dropout
공식 코드https://github.com/kunzhan/DSSN
공식 코드Improving Semi-Supervised Semantic Segmentation with Dual-Level Siamese Structure Network
https://github.com/kunzhan/MTGCN
공식 코드https://github.com/kwwcv/ssmp
공식 코드Semi-Supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix
https://github.com/kyunnilee/visual_puzzles
공식 코드Puzzled by Puzzles: When Vision-Language Models Can't Take a Hint
https://github.com/l-zhe/vipg
공식 코드https://github.com/l1997i/lim3d
공식 코드Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation
https://github.com/lancopku/Explicit-Sparse-Transformer
공식 코드Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection
https://github.com/lancopku/simNet
공식 코드https://github.com/larocs/pracegover
공식 코드#PraCegoVer: A Large Dataset for Image Captioning in Portuguese
https://github.com/lavender105/rsgpt
공식 코드https://github.com/leehyuck/cdmad
공식 코드CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning
https://github.com/leon1207/3dgctr
공식 코드https://github.com/leonhlj/rskp
공식 코드Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation
https://github.com/less-and-less-bugs/hkemodel
공식 코드Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement
https://github.com/lethesec/plg-mi-attack
공식 코드Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network
https://github.com/letitiabanana/pnp-ovss
공식 코드Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models
https://github.com/levigty/acl
공식 코드Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.