https://github.com/sdu-l/finecir
공식 코드FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Image Retrieval is a fundamental and long-standing computer vision task that involves finding images similar to a given query from a large database. It is often considered a form of fine-grained, instance-level classification. The task is integral to image recognition alongside classification and cross-modal retrieval. By leveraging visual similarity and other criteria, image retrieval enables users to efficiently discover relevant images, making it a crucial tool in applications such as search and recommendation.
Extending CLIP for Category-to-image Retrieval in E-commerce
<span style="color:grey; opacity: 0.6">( Image credit: DELF )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval
Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment
ICFHR 2020 Competition on Image Retrieval for Historical Handwritten Fragments
AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shift
Some Like It Small: Czech Semantic Embedding Models for Industry Applications
DeVLBert: Learning Deconfounded Visio-Linguistic Representations
Global Features are All You Need for Image Retrieval and Reranking
Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning
Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image
Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching
Shotit: compute-efficient image-to-video search engine for the cloud
HybridHash: Hybrid Convolutional and Self-Attention Deep Hashing for Image Retrieval
Benchmarking Vision-Language Contrastive Methods for Medical Representation Learning
PAPERCLIP: Associating Astronomical Observations and Natural Language with Multi-Modal Models
A non-alternating graph hashing algorithm for large scale image search
Unsupervised Visual Sense Disambiguation for Verbs using Multimodal Embeddings
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
Unsupervised Neural Quantization for Compressed-Domain Similarity Search
Dataset and Case Studies for Visual Near-Duplicates Detection in the Context of Social Media
Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions
CLIPSE -- a minimalistic CLIP-based image search engine for research
Representation Learning via Consistent Assignment of Views over Random Partitions
Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features
It's All About Your Sketch: Democratising Sketch Control in Diffusion Models
Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval
Fairness in Image Search: A Study of Occupational Stereotyping in Image Retrieval and its Debiasing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.