https://github.com/1180300419/imperfect-deweathering
공식 코드Learning Real-World Image De-Weathering with Imperfect Supervision
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/232525/PureT
공식 코드https://github.com/2han9x1a0release/RLCC
공식 코드https://github.com/4dvlab/cl3d
공식 코드CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection
https://github.com/AHandsomePython/MSMedCap
공식 코드Sam-Guided Enhanced Fine-Grained Encoding with Mixed Semantic Learning for Medical Image Captioning
https://github.com/AI-14/micar-vl-moe
공식 코드https://github.com/AIGeeksGroup/3DCoCa
공식 코드https://github.com/AIROTAU/TexLiDAR
공식 코드TexLiDAR: Automated Text Understanding for Panoramic LiDAR Data
https://github.com/Abhishek0697/Detection-of-Hate-Speech-in-Multimodal-Memes
공식 코드https://github.com/AcEbt/CPL
공식 코드https://github.com/AlibabaResearch/efficientteacher
공식 코드Efficient Teacher: Semi-Supervised Object Detection for YOLOv5
https://github.com/AnnikaLindh/Controllable_Region_Pointer_Advancement
공식 코드Language-Driven Region Pointer Advancement for Controllable Image Captioning
https://github.com/AnnikaLindh/Diverse_and_Specific_Image_Captioning
공식 코드https://github.com/BIT-DA/SSAN
공식 코드Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation
https://github.com/BestiVictory/DPC-Captions
공식 코드https://github.com/BruceW91/CVSE
공식 코드Consensus-Aware Visual-Semantic Embedding for Image-Text Matching
https://github.com/CVMI-Lab/ST3D
공식 코드ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
https://github.com/Captain-Hong/UDA-via-joint-adversarial-learning-and-self-learning
공식 코드https://github.com/Chaolei98/FreeZAD
공식 코드Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models
https://github.com/ChengJianH/CDC
공식 코드https://github.com/Claydon-Wang/OFTTA
공식 코드Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition
https://github.com/Cory-M/DCCM
공식 코드https://github.com/CyberAgentAILab/adaptive-mbr
공식 코드Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding
https://github.com/DSBA-Lab/ECO
공식 코드https://github.com/DYEvaLab/EvalMuse
공식 코드https://github.com/DZhaoXd/SND
공식 코드Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation
https://github.com/DesertsP/SLRNet
공식 코드https://github.com/Dong-JinKim/DenseRelationalCaptioning
공식 코드Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning
https://github.com/DongHande/PT_propagation_then_training
공식 코드On the Equivalence of Decoupled Graph Convolution Network and Label Propagation
https://github.com/Earth-Intelligence-Lab/vleo-bench
공식 코드Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data
https://github.com/EnriqueSolarte/360-mlc
공식 코드360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning
https://github.com/EvLab-MIT/LexiContrastiveGrd
공식 코드Visual Grounding Helps Learn Word Meanings in Low-Data Regimes
https://github.com/ExplorerFreda/VSE-C
공식 코드Learning Visually-Grounded Semantics from Contrastive Adversarial Samples
https://github.com/Externalhappy/DPA
공식 코드DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models
https://github.com/FaiyazKhan11/Improved-Bengali-Image-Captioning-via-deep-convolutional-neural-network-based-encoder-decoder-model
공식 코드Improved Bengali Image Captioning via deep convolutional neural network based encoder-decoder model
https://github.com/FlyingRoastDuck/MetaCam_DSCE
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.