Image-to-Text Retrieval
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 8
- 보존된 평가 기록
- 33
Image-text retrieval is the process of retrieving relevant images based on textual descriptions or finding corresponding textual descriptions for a given image. This task is interdisciplinary, combining techniques from computer vision, and natural language processing. The primary challenge lies in bridging the semantic gap — the difference between how visual data is represented in images and how humans describe that information using language. To address this, many methods focus on learning a shared embedding space where both images and text can be represented in a comparable way, allowing their similarities to be measured and facilitating more accurate retrieval.
Source: Extending CLIP for Category-to-Image Retrieval in E-commerce
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval
Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs
Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset
COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval
IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages
FLAVA: A Foundational Language And Vision Alignment Model
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation
A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval
Learning Relation Alignment for Calibrated Cross-modal Retrieval
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training
Learning Transferable Visual Models From Natural Language Supervision
Hierarchical Gumbel Attention Network for Text-based Person Search
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task
Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training
Exploring Models and Data for Remote Sensing Image Caption Generation
Deep Visual-Semantic Alignments for Generating Image Descriptions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.