SOTAVerified

Referring Expression

Referring expressions places a bounding box around the instance corresponding to the provided description and image.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 61–70 of 364 papers

TitleStatusHype
IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word EmphasisCode1
MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression ComprehensionCode1
3D-GRES: Generalized 3D Referring Expression SegmentationCode1
March in Chat: Interactive Prompting for Remote Embodied Referring ExpressionCode1
MDETR -- Modulated Detection for End-to-End Multi-Modal UnderstandingCode1
Layout-aware Dreamer for Embodied Referring Expression GroundingCode1
Learning to Evaluate Performance of Multi-modal Semantic LocalizationCode1
Large-Scale Adversarial Training for Vision-and-Language Representation LearningCode1
LAVT: Language-Aware Vision Transformer for Referring Image SegmentationCode1
LLMs as Bridges: Reformulating Grounded Multimodal Named Entity RecognitionCode1
Show:102550
← PrevPage 7 of 37Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RandomAcc@0.5m14.6—Unverified