https://github.com/anokiai/contextiq-paper
공식 코드ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual Advertising
Papers with Code 아카이브
Retrieval
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 11
- 보존된 평가 기록
- 19
A methodology that involves selecting relevant data or examples from a large dataset to support tasks like prediction, learning, or inference. It enhances models by providing context or additional information, often used in systems like retrieval-augmented generation or in-context learning.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/anosorae/irra
공식 코드Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval
https://github.com/answerdotai/modernbert
공식 코드https://github.com/answerdotai/rerankers
공식 코드rerankers: A Lightweight Python Library to Unify Ranking Methods
https://github.com/ant-uni-bremen/sinfony
공식 코드https://github.com/antheamonod/Dilation_invariant_bottleneck
공식 코드Topological Information Retrieval with Dilation-Invariant Bottleneck Comparative Measures
https://github.com/anthonywchen/AmbER-Sets
공식 코드Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP
https://github.com/antnlp/nope_head_scale
공식 코드Length Generalization of Causal Transformers without Position Encoding
https://github.com/antoine77340/MIL-NCE_HowTo100M
공식 코드End-to-End Learning of Visual Representations from Uncurated Instructional Videos
https://github.com/antoine77340/Mixture-of-Embedding-Experts
공식 코드Learning a Text-Video Embedding from Incomplete and Heterogeneous Data
https://github.com/anusfoil/symrep
공식 코드Symbolic Music Representations for Classification Tasks: A Systematic Evaluation
https://github.com/anyloc/revisit-anything
공식 코드Revisit Anything: Visual Place Recognition via Image Segment Retrieval
https://github.com/anyone546/OCoR
공식 코드https://github.com/apapoudakis/bookworm
공식 코드https://github.com/aparna-b/fairrankingrelevance
공식 코드https://github.com/apple/axlearn/blob/main/axlearn/vision/imagenet_adversarial_text/
공식 코드Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness
https://github.com/apple/ml-fct
공식 코드Forward Compatible Training for Large-Scale Embedding Retrieval Systems
https://github.com/apple/ml-qrecc
공식 코드Open-Domain Question Answering Goes Conversational via Question Rewriting
https://github.com/apple/ml-superposition-prompting
공식 코드Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation
https://github.com/apple/ml-tic-clip
공식 코드https://github.com/apple/ml-veclip
공식 코드VeCLIP: Improving CLIP Training via Visual-enriched Captions
https://github.com/apple/ml-vfm-kt
공식 코드https://github.com/applicaai/contract-discovery
공식 코드Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines
https://github.com/applied-ai-research-lab/orchestrator-agent-trust
공식 코드https://github.com/applied-machine-learning-lab/g3
공식 코드https://github.com/applied-machine-learning-lab/mill
공식 코드MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion
https://github.com/approach0/math-dense-retrievers
공식 코드Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval
https://github.com/araij/gup
공식 코드https://github.com/arailly/pivnet
공식 코드https://github.com/aranciokov/fsmmda_videoretrieval
공식 코드A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval
https://github.com/aranciokov/ranp
공식 코드Learning video retrieval models with relevance-aware online mining
https://github.com/aranciokov/relevancemargin-icmr22
공식 코드Relevance-based Margin for Contrastively-trained Video Retrieval Models
https://github.com/arash-shahmansoori/r2cbr3h-sr
공식 코드https://github.com/arazd/miread
공식 코드MIReAD: Simple Method for Learning High-quality Representations from Scientific Documents
https://github.com/archon159/RAFT
공식 코드https://github.com/areejokaili/topic_labelling
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.