SOTAVerified

Phrase Grounding

Given an image and a corresponding caption, the Phrase Grounding task aims to ground each entity mentioned by a noun phrase in the caption to a region in the image.

Source: Phrase Grounding by Soft-Label Chain Conditional Random Field

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 88 papers

TitleStatusHype
Anatomy-Grounded Weakly Supervised Prompt Tuning for Chest X-ray Latent Diffusion Models—0
Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic StructuresCode0
A Comparison of Object Detection and Phrase Grounding Models in Chest X-ray Abnormality Localization using Eye-tracking Data—0
Progressive Local Alignment for Medical Multimodal Pre-training—0
Anatomical grounding pre-training for medical phrase groundingCode0
VICCA: Visual Interpretation and Comprehension of Chest X-ray Anomalies in Generated Report Without Human FeedbackCode0
Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding—0
Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension—0
Towards Visual Grounding: A SurveyCode3
ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation—0
Show:102550
← PrevPage 1 of 9Next →
All datasetsFlickr30k Entities TestFlickr30kFlickr30k Entities DevReferItVisual Genome

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GBS Ensemble + 12-in-1Pointing Game Accuracy85.9—Unverified
2GbS Ensemble MS-COCOPointing Game Accuracy75.6—Unverified
3COCO_ELMo_PNASNetPointing Game Accuracy69.19—Unverified