https://github.com/davidhuji/capdec
공식 코드Text-Only Training for Image Captioning using Noise-Injected CLIP
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/davidmchan/caption-by-committee
공식 코드https://github.com/davidnvq/grit
공식 코드GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features
https://github.com/dcdmllm/cheetah
공식 코드Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
https://github.com/ddz16/TSASPC
공식 코드Timestamp-Supervised Action Segmentation from the Perspective of Clustering
https://github.com/deceptrax123/jpeb-gssl
공식 코드Leveraging Joint Predictive Embedding and Bayesian Inference in Graph Self Supervised Learning
https://github.com/declare-lab/lg-vqa
공식 코드https://github.com/declare-lab/sat
공식 코드SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training
https://github.com/deep-spin/TVmax
공식 코드https://github.com/deepglint/unicom
공식 코드Multi-label Cluster Discrimination for Visual Representation Learning
https://github.com/deeplearnxmu/mm-mkp
공식 코드https://github.com/deepmicroscopy/prototype-sampling
공식 코드Leveraging image captions for selective whole slide image annotation
https://github.com/deepmind/semppl
공식 코드SemPPL: Predicting pseudo-labels for better contrastive representations
https://github.com/deepsemantic/image_captioning
공식 코드https://github.com/deeptibhegde/attentiveprototypesfuda
공식 코드Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection
https://github.com/delchiaro/RATT
공식 코드RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning
https://github.com/detecting-cheapfakes/detecting-cheapfakes-code
공식 코드https://github.com/devaansh100/cliptrans
공식 코드CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation
https://github.com/dheeraj7596/lops
공식 코드LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification
https://github.com/dhg-wei/decap
공식 코드DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training
https://github.com/difeigu/radalign
공식 코드RadAlign: Advancing Radiology Report Generation with Vision-Language Concept Alignment
https://github.com/div290/capeen
공식 코드CAPEEN: Image Captioning with Early Exits and Knowledge Distillation
https://github.com/dlyuangod/tinygpt-v
공식 코드TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
https://github.com/dmcv-ecnu/MindSpore_ModelZoo
공식 코드Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud
https://github.com/dmg-illc/didec-seq-gen
공식 코드Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze
https://github.com/dodoxxb/cognitive-resilience
공식 코드https://github.com/dosowiechi/clipartt
공식 코드https://github.com/douglas125/SpeechCmdRecognition
공식 코드https://github.com/dphuongn/FLoRA
공식 코드FLoRA: Enhancing Vision-Language Models with Parameter-Efficient Federated Learning
https://github.com/dvlab-research/llama-vid
공식 코드LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models
https://github.com/dylan-h-wang/skin-sm3
공식 코드Self-Supervised Multi-Modality Learning for Multi-Label Skin Lesion Classification
https://github.com/dymanne123/PLPCL
공식 코드Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery
https://github.com/e-bug/syncap
공식 코드The Role of Syntactic Planning in Compositional Image Captioning
https://github.com/eai-lab/transpl
공식 코드https://github.com/eclique/RISE
공식 코드RISE: Randomized Input Sampling for Explanation of Black-box Models
https://github.com/efrat-safanov/caption-enriched-samples-research
공식 코드Caption Enriched Samples for Improving Hateful Memes Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.