https://github.com/vcl-iisc/CoNMix
공식 코드CoNMix for Source-free Single and Multi-target Domain Adaptation
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/velor2012/tdo-dif
공식 코드Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion
https://github.com/vgthengane/climb3d
공식 코드CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation
https://github.com/vibashan/tt-sfuda
공식 코드Target and Task specific Source-Free Domain Adaptive Image Segmentation
https://github.com/victorssilva/concreteness
공식 코드Quantifying the visual concreteness of words and topics in multimodal datasets
https://github.com/vimar-gu/Bias-Eliminate-DA-ReID
공식 코드1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification
https://github.com/virajprabhu/SENTRY
공식 코드SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation
https://github.com/vishakhpk/mil-creative-captioning
공식 코드https://github.com/visinf/cos-cvae
공식 코드Diverse Image Captioning with Context-Object Split Latent Spaces
https://github.com/visinf/cups
공식 코드https://github.com/visinf/lnfmm
공식 코드Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings
https://github.com/visinf/style-seqcvae
공식 코드https://github.com/vision-cair/chatcaptioner
공식 코드ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions
https://github.com/vl2g/PatentLMM
공식 코드PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures
https://github.com/voldemortX/DST-CBC
공식 코드https://github.com/wangbo-zhao/WSVSOD
공식 코드https://github.com/wanggrun/SYSU-30k
공식 코드Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark
https://github.com/wangyuchi369/ladic
공식 코드https://github.com/wavinflaghxm/GroupSampling
공식 코드Rethinking Sampling Strategies for Unsupervised Person Re-identification
https://github.com/webis-de/eacl-23
공식 코드https://github.com/weiguangzhao/BFANet
공식 코드BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis
https://github.com/weijun88/SPOL
공식 코드Shallow Feature Matters for Weakly Supervised Object Localization
https://github.com/weixuansun/wsss_sam
공식 코드https://github.com/weiyuk/fluent-cap
공식 코드https://github.com/wenhuchen/ETHZ-Bootstrapped-Captioning
공식 코드https://github.com/wenkehuang/awesome-mllm-tuning
공식 코드Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model
https://github.com/wenlve-zhou/guidance-training
공식 코드Improve Cross-domain Mixed Sampling with Guidance Training for Adaptive Segmentation
https://github.com/wentaotan/sena
공식 코드Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution
https://github.com/westlakeaerialrobotics/m3d
공식 코드Domain Adaptive Detection of MAVs: A Benchmark and Noise Suppression Network
https://github.com/whats2000/WeiMoCIR
공식 코드Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
https://github.com/whileherham/calibratedteacher
공식 코드https://github.com/windweller/Pragmatic-ISIC
공식 코드https://github.com/witdsl/krt-mlcil
공식 코드Knowledge Restore and Transfer for Multi-label Class-Incremental Learning
https://github.com/wltyby/lnq2023_training_code
공식 코드https://github.com/wojzaremba/lstm
공식 코드https://github.com/woldier/siamseg
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.