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/liangzid/TEMP
공식 코드Healing Unsafe Dialogue Responses with Weak Supervision Signals
https://github.com/libeineu/fairseq_mmt
공식 코드https://github.com/lihr747/cgtgan
공식 코드https://github.com/lijuncen/Sentiment-and-Style-Transfer
공식 코드Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
https://github.com/lingrayy/plpb
공식 코드Robust Source-Free Domain Adaptation for Fundus Image Segmentation
https://github.com/linnanwang/AlphaX-NASBench101
공식 코드AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search
https://github.com/lipang/special
공식 코드SPECIAL: Zero-shot Hyperspectral Image Classification With CLIP
https://github.com/lishenglana/gdstrack
공식 코드Modality-Guided Dynamic Graph Fusion and Temporal Diffusion for Self-Supervised RGB-T Tracking
https://github.com/littlekobe/AREL
공식 코드No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
https://github.com/liulisixin/mli-nerf
공식 코드MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fields
https://github.com/liuzhengzhe/One-Thing-One-Click
공식 코드You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding
https://github.com/lixinustc/samb-transformeruda
공식 코드Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation
https://github.com/lizhaoliu-lec/cg-vlm
공식 코드Contrastive Vision-Language Alignment Makes Efficient Instruction Learner
https://github.com/lizhou-cs/mglmm
공식 코드Instruction-guided Multi-Granularity Segmentation and Captioning with Large Multimodal Model
https://github.com/lizhuohong/paraformer
공식 코드https://github.com/lizzy8587/castdet
공식 코드https://github.com/llavar/llavar-2
공식 코드A High-Quality Text-Rich Image Instruction Tuning Dataset via Hybrid Instruction Generation
https://github.com/lliuz/mixteacher
공식 코드MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection
https://github.com/llm-as-dataset-analyst/SSDLLM
공식 코드LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model
https://github.com/lofrienger/s2me
공식 코드https://github.com/lokhande-vishnu/DeepHermites
공식 코드https://github.com/lseventeen/flare22-twostagephtrans
공식 코드Combining Self-Training and Hybrid Architecture for Semi-supervised Abdominal Organ Segmentation
https://github.com/ltguo19/VSUA-Captioning
공식 코드Aligning Linguistic Words and Visual Semantic Units for Image Captioning
https://github.com/lucasyang567/metaocc
공식 코드https://github.com/lufan31/comprecap
공식 코드https://github.com/luluho1208/diffusion-ss3d
공식 코드Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection
https://github.com/lunarshen/dsicovla
공식 코드https://github.com/luo3300612/image-captioning-DLCT
공식 코드https://github.com/luogen1996/oneteacher
공식 코드Towards End-to-end Semi-supervised Learning for One-stage Object Detection
https://github.com/luohongyin/entst
공식 코드https://github.com/luyvlei/BiSMAPs
공식 코드https://github.com/lx-doctorai1/deltanet
공식 코드DeltaNet:Conditional Medical Report Generation for COVID-19 Diagnosis
https://github.com/lx709/vrsbench
공식 코드VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
https://github.com/lxucs/capretrieval
공식 코드Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings
https://github.com/lxysl/plremix
공식 코드PLReMix: Combating Noisy Labels with Pseudo-Label Relaxed Contrastive Representation Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.