https://github.com/abanitalebi/simrod
공식 코드SimROD: A Simple Adaptation Method for Robust Object Detection
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/abcAnonymous/EDSL
공식 코드https://github.com/abhayraw1/spi
공식 코드Semi-Supervised Domain Adaptation by Similarity based Pseudo-label Injection
https://github.com/abhi1nandy2/yesbut_dataset
공식 코드https://github.com/aditya12agd5/convcap
공식 코드https://github.com/aengusl/spawrious
공식 코드Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases
https://github.com/afsharshamsi/etage
공식 코드https://github.com/ahmedssabir/belief-revision-score
공식 코드Belief Revision based Caption Re-ranker with Visual Semantic Information
https://github.com/ahmedssabir/genderscore
공식 코드Women Wearing Lipstick: Measuring the Bias Between an Object and Its Related Gender
https://github.com/ahmedssabir/textual-visual-semantic-dataset
공식 코드https://github.com/ai-hpc-research-team/git-mol
공식 코드GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text
https://github.com/ai4colonoscopy/intelliscope
공식 코드https://github.com/aijinrjinr/mlb-seg
공식 코드Consistency-guided Meta-Learning for Bootstrapping Semi-Supervised Medical Image Segmentation
https://github.com/ailab-cvc/vl-gpt
공식 코드VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation
https://github.com/aimagelab/awesome-captioning-evaluation
공식 코드Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives
https://github.com/aimagelab/bridge-score
공식 코드BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues
https://github.com/aimagelab/camel
공식 코드https://github.com/aimagelab/dico
공식 코드Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization
https://github.com/aimagelab/meshed-memory-transformer
공식 코드https://github.com/aimagelab/pacscore
공식 코드Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation
https://github.com/aimagelab/pma-net
공식 코드With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning
https://github.com/aimagelab/show-control-and-tell
공식 코드Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions
https://github.com/air-discover/omni-pq
공식 코드From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds
https://github.com/airmachine/EM-MIL-WeaklyActionDetection
공식 코드Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning
https://github.com/airsplay/VisualRelationships
공식 코드https://github.com/airsplay/vokenization
공식 코드Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision
https://github.com/ajoymondal/Equation-Description-PyTorch
공식 코드https://github.com/akash2907/semi-sup-active-learning
공식 코드https://github.com/akshay107/mimic-and-fool
공식 코드https://github.com/alasdairtran/transform-and-tell
공식 코드https://github.com/alchemyemperor/siavc
공식 코드SIAVC: Semi-Supervised Framework for Industrial Accident Video Classification
https://github.com/alexanderjaus/atlasdataset
공식 코드https://github.com/alexanderswerdlow/unidisc
공식 코드https://github.com/alexrame/rewardedsoups
공식 코드https://github.com/alibaba/AliceMind/tree/main/mPLUG
공식 코드mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections
https://github.com/alinlab/s-clip
공식 코드S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.