SOTAVerified

Retrieval

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.

Papers

Showing 14511500 of 14297 papers

TitleStatusHype
LaMP: When Large Language Models Meet PersonalizationCode1
Rethinking Benchmarks for Cross-modal Image-text RetrievalCode1
FindVehicle and VehicleFinder: A NER dataset for natural language-based vehicle retrieval and a keyword-based cross-modal vehicle retrieval systemCode1
Image-text Retrieval via Preserving Main Semantics of VisionCode1
Hyperbolic Image-Text RepresentationsCode1
SViTT: Temporal Learning of Sparse Video-Text TransformersCode1
PTC-Net: Point-Wise Transformer with Sparse Convolution Network for Place RecognitionCode1
Robust Cross-Modal Knowledge Distillation for Unconstrained VideosCode1
Tempo vs. Pitch: understanding self-supervised tempo estimationCode1
Noisy Correspondence Learning with Meta Similarity CorrectionCode1
Rethinking Dense Retrieval's Few-Shot AbilityCode1
Are Local Features All You Need for Cross-Domain Visual Place Recognition?Code1
Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent TransportationCode1
WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web CorpusCode1
Learning to Tokenize for Generative RetrievalCode1
T2Ranking: A large-scale Chinese Benchmark for Passage RankingCode1
Generative Recommendation: Towards Next-generation Recommender ParadigmCode1
Self-Supervised Video Similarity LearningCode1
PWESuite: Phonetic Word Embeddings and Tasks They FacilitateCode1
Efficient OCR for Building a Diverse Digital HistoryCode1
Form-NLU: Dataset for the Form Natural Language UnderstandingCode1
Rethinking the Role of Token Retrieval in Multi-Vector RetrievalCode1
HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic FusionCode1
The Archive Query Log: Mining Millions of Search Result Pages of Hundreds of Search Engines from 25 Years of Web ArchivesCode1
SPAN: Learning Similarity between Scene Graphs and Images with TransformersCode1
Enhancing Deformable Local Features by Jointly Learning to Detect and Describe KeypointsCode1
Multimodal Image-Text Matching Improves Retrieval-based Chest X-Ray Report GenerationCode1
WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion ModelsCode1
Hierarchical Video-Moment Retrieval and Step-CaptioningCode1
Bi-directional Training for Composed Image Retrieval via Text Prompt LearningCode1
Zero-Shot Composed Image Retrieval with Textual InversionCode1
Neural Graph Reasoning: Complex Logical Query Answering Meets Graph DatabasesCode1
Equivariant Similarity for Vision-Language Foundation ModelsCode1
Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation LearningCode1
Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable StyleCode1
PanoVPR: Towards Unified Perspective-to-Equirectangular Visual Place Recognition via Sliding Windows across the Panoramic ViewCode1
CCL: Continual Contrastive Learning for LiDAR Place RecognitionCode1
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation ModelsCode1
Top-Down Visual Attention from Analysis by SynthesisCode1
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defenseCode1
Modular Retrieval for Generalization and InterpretationCode1
A Unified Framework for Learned Sparse RetrievalCode1
CompoDiff: Versatile Composed Image Retrieval With Latent DiffusionCode1
Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment PathsCode1
IRGen: Generative Modeling for Image RetrievalCode1
DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelCode1
Data Roaming and Quality Assessment for Composed Image RetrievalCode1
VVS: Video-to-Video Retrieval with Irrelevant Frame SuppressionCode1
Data-Free Sketch-Based Image RetrievalCode1
MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReIDCode1
Show:102550
← PrevPage 30 of 286Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1BM25SQueries per second183.53Unverified
2ElasticsearchQueries per second21.8Unverified
3BM25-PTQueries per second6.49Unverified
4Rank-BM25Queries per second1.18Unverified
#ModelMetricClaimedVerifiedStatus
1BM25SQueries per second20.88Unverified
2ElasticsearchQueries per second7.11Unverified
3Rank-BM25Queries per second0.04Unverified
#ModelMetricClaimedVerifiedStatus
1BM25SQueries per second41.85Unverified
2ElasticsearchQueries per second12.16Unverified
3Rank-BM25Queries per second0.1Unverified
#ModelMetricClaimedVerifiedStatus
1FLMRRecall@589.32Unverified
2RA-VQARecall@582.84Unverified
#ModelMetricClaimedVerifiedStatus
1PreFLMRRecall@562.1Unverified
#ModelMetricClaimedVerifiedStatus
1CLIP-KIStext-to-video Mean Rank30Unverified
#ModelMetricClaimedVerifiedStatus
1CLIP4OutfitRecall@57.59Unverified
#ModelMetricClaimedVerifiedStatus
1MetaGen Blended RAGAccuracy (Top-1)82.1Unverified
#ModelMetricClaimedVerifiedStatus
1MetaGen Blended RAGAccuracy (Top-1)82.1Unverified
#ModelMetricClaimedVerifiedStatus
1COLTCOMP@84.55Unverified
#ModelMetricClaimedVerifiedStatus
1hello0L1,121,222Unverified