https://github.com/eladhi/clid
공식 코드CLID: Controlled-Length Image Descriptions with Limited Data
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/elbayadm/seq2seq
공식 코드Token-level and sequence-level loss smoothing for RNN language models
https://github.com/eliottthomas99/data_quest
공식 코드QUEST: Quality-aware Semi-supervised Table Extraction for Business Documents
https://github.com/elisakreiss/concadia
공식 코드Concadia: Towards Image-Based Text Generation with a Purpose
https://github.com/embar111/pgpc
공식 코드Pseudolabel guided pixels contrast for domain adaptive semantic segmentation
https://github.com/embodied-generalist/embodied-generalist
공식 코드https://github.com/epfl-imos/simple-sfod
공식 코드https://github.com/eujhwang/meme-cap
공식 코드https://github.com/explainableml/zeraucap
공식 코드Zero-shot audio captioning with audio-language model guidance and audio context keywords
https://github.com/explainableml/zs-a2t
공식 코드Zero-shot Translation of Attention Patterns in VQA Models to Natural Language
https://github.com/facebookresearch/EGG
공식 코드Cross-Domain Image Captioning with Discriminative Finetuning
https://github.com/facebookresearch/connect-caption-and-trace
공식 코드Connecting What to Say With Where to Look by Modeling Human Attention Traces
https://github.com/facebookresearch/dci
공식 코드A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions
https://github.com/facebookresearch/dpcap
공식 코드Differentially Private Representation Learning via Image Captioning
https://github.com/facebookresearch/metaclip
공식 코드https://github.com/facebookresearch/ov-seg
공식 코드Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP
https://github.com/facebookresearch/sieve
공식 코드Sieve: Multimodal Dataset Pruning Using Image Captioning Models
https://github.com/facebookresearch/suncet
공식 코드https://github.com/facebookresearch/vizseq
공식 코드https://github.com/faiyazkhan11/ban-cap
공식 코드BAN-Cap: A Multi-Purpose English-Bangla Image Descriptions Dataset
https://github.com/fawazsammani/look-and-modify
공식 코드https://github.com/fawazsammani/show-edit-tell
공식 코드https://github.com/feielysia/viecap
공식 코드Transferable Decoding with Visual Entities for Zero-Shot Image Captioning
https://github.com/feizc/future-caption
공식 코드https://github.com/feizc/saic
공식 코드https://github.com/fenglinliu98/MIA
공식 코드Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations
https://github.com/fjchange/MIST_VAD
공식 코드MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection
https://github.com/fnozarian/ReliableStudent
공식 코드Reliable Student: Addressing Noise in Semi-Supervised 3D Object Detection
https://github.com/forjadeforest/icd-lm
공식 코드Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models
https://github.com/forjadeforest/lever-lm
공식 코드Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models
https://github.com/foundation-multimodal-models/capture
공식 코드https://github.com/fqhank/FuSTAL
공식 코드Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization
https://github.com/franklinlingfeng/code-for-salcr
공식 코드Semantic-Aligned Learning with Collaborative Refinement for Unsupervised VI-ReID
https://github.com/franklinlingfeng/code_for_mult
공식 코드https://github.com/fundamentalvision/Uni-Perceiver
공식 코드Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs
https://github.com/furkanbiten/GoodNews
공식 코드Good News, Everyone! Context driven entity-aware captioning for news images
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.