SOTAVerified

Text Retrieval

Text Retrieval is the task of finding the most text result (such as an answer, paragraph, or passage) given a query (which could be a question, keywords, or any relevant text)

Papers

Showing 1120 of 671 papers

TitleStatusHype
Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts0
Attacking Attention of Foundation Models Disrupts Downstream TasksCode0
ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase GenerationCode0
One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object TrajectoryCode2
MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval0
Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation0
EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models0
Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval0
Breaking Language Barriers or Reinforcing Bias? A Study of Gender and Racial Disparities in Multilingual Contrastive Vision Language Models0
LoVR: A Benchmark for Long Video Retrieval in Multimodal ContextsCode1
Show:102550
← PrevPage 2 of 68Next →

No leaderboard results yet.