Papers with Code 아카이브
Image-text matching
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 8
Image-Text Matching is a subtask within Cross-Modal Retrieval (CMR) that involves establishing associations between images and corresponding textual descriptions. The goal is to retrieve an image given a textual query or, conversely, retrieve a textual description given an image query. This task is challenging due to the heterogeneity gap between image and text data representations. Image-text matching is used in applications such as content-based image search, visual question answering, and multimodal summarization.
Assessing Brittleness of Image-Text Retrieval Benchmarks from Vision-Language Models Perspective
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/kuanghuei/SCAN
공식 코드https://github.com/kywen1119/DSRAN
공식 코드Learning Dual Semantic Relations with Graph Attention for Image-Text Matching
https://github.com/leolee99/pau
공식 코드Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval
https://github.com/letitiabanana/pnp-ovss
공식 코드Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models
https://github.com/linzhiqiu/visual_gpt_score
공식 코드Revisiting the Role of Language Priors in Vision-Language Models
https://github.com/littleredxh/vse-gradient
공식 코드Dissecting Deep Metric Learning Losses for Image-Text Retrieval
https://github.com/liuyyy111/d2s-vse
공식 코드https://github.com/llabres/library-dataset
공식 코드https://github.com/luminosityx/fne
공식 코드Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination
https://github.com/lwaekfjlk/mmoe
공식 코드MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts
https://github.com/m2man/LGSGM
공식 코드A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval
https://github.com/mcgill-nlp/diffusion-itm
공식 코드https://github.com/mesnico/TERN
공식 코드Transformer Reasoning Network for Image-Text Matching and Retrieval
https://github.com/mesnico/aladin
공식 코드ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval
https://github.com/microsoft/Oscar
공식 코드Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
https://github.com/mitjanikolaus/multimodal-predicate-noun-dependencies
공식 코드Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?
https://github.com/myfoodchoice/malm_mask_augmentation_based_local_matching-_for-_food_recipe_retrieval
공식 코드MALM: Mask Augmentation based Local Matching for Food-Recipe Retrieval
https://github.com/naver-ai/eccv-caption
공식 코드https://github.com/naver-ai/pcmepp
공식 코드https://github.com/paranioar/rcar
공식 코드https://github.com/pengfeiliheu/m2i2
공식 코드Self-supervised vision-language pretraining for Medical visual question answering
https://github.com/pseulki/rococo
공식 코드RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models
https://github.com/pter61/aligncmss
공식 코드Align before Search: Aligning Ads Image to Text for Accurate Cross-Modal Sponsored Search
https://github.com/pzzhang/VinVL
공식 코드VinVL: Revisiting Visual Representations in Vision-Language Models
https://github.com/qinyang79/crcl
공식 코드Cross-modal Active Complementary Learning with Self-refining Correspondence
https://github.com/qxzha/ReCon
공식 코드https://github.com/rajpurkarlab/x-rem
공식 코드Multimodal Image-Text Matching Improves Retrieval-based Chest X-Ray Report Generation
https://github.com/raoyongming/denseclip
공식 코드DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting
https://github.com/salesforce/lavis
공식 코드Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
https://github.com/shijxcs/candle
공식 코드Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model
https://github.com/soon91jae/uvwsd
공식 코드https://github.com/sunanhe/mkt
공식 코드Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer
https://github.com/sunnychencool/AOQ
공식 코드https://github.com/threesr/unifine
공식 코드UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding
https://github.com/top34051/colorswap
공식 코드ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.