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

Showing 5188 of 88 papers

TitleStatusHype
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language ModelsCode1
Making the Most of Text Semantics to Improve Biomedical Vision--Language ProcessingCode0
Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs with Language Structures via Dependency RelationshipsCode1
Lite-MDETR: A Lightweight Multi-Modal Detector0
Improving Pre-trained Vision-and-Language Embeddings for Phrase Grounding0
Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling0
Grounding Plural Phrases: Countering Evaluation Biases by Individuation0
MDETR -- Modulated Detection for End-to-End Multi-Modal UnderstandingCode1
Detector-Free Weakly Supervised Grounding by SeparationCode0
Disentangled Motif-aware Graph Learning for Phrase Grounding0
MDETR - Modulated Detection for End-to-End Multi-Modal UnderstandingCode2
Utilizing Every Image Object for Semi-supervised Phrase Grounding0
Learning to ground medical text in a 3D human atlasCode0
MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase GroundingCode1
Propagating Over Phrase Relations for One-Stage Visual Grounding0
Improving Weakly Supervised Visual Grounding by Contrastive Knowledge DistillationCode1
Neural Parameter Allocation SearchCode0
Contrastive Learning for Weakly Supervised Phrase GroundingCode1
Learning Cross-modal Context Graph for Visual GroundingCode1
Phrase Grounding by Soft-Label Chain Conditional Random FieldCode0
Zero-Shot Grounding of Objects from Natural Language QueriesCode0
Language Features Matter: Effective Language Representations for Vision-Language Tasks0
Modularized Textual Grounding for Counterfactual ResilienceCode0
Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment0
Neural Sequential Phrase Grounding (SeqGROUND)0
PIRC Net : Using Proposal Indexing, Relationships and Context for Phrase Grounding0
Multi-level Multimodal Common Semantic Space for Image-Phrase GroundingCode0
Revisiting Image-Language Networks for Open-ended Phrase DetectionCode0
Dynamic Conditional Networks for Few-Shot Learning0
Rethinking Diversified and Discriminative Proposal Generation for Visual GroundingCode0
Knowledge Aided Consistency for Weakly Supervised Phrase Grounding0
Conditional Image-Text Embedding NetworksCode0
Query-guided Regression Network with Context Policy for Phrase Grounding0
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual GroundingCode0
Learning Deep Structure-Preserving Image-Text Embeddings0
Natural Language Object RetrievalCode0
Grounding of Textual Phrases in Images by ReconstructionCode0
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence ModelsCode1
Show:102550
← PrevPage 2 of 2Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GLIPv2R@187.7Unverified
2FIBER-BR@187.4Unverified
3GLIPR@187.1Unverified
4PEVLR@184.4Unverified
5MDETR-ENB5R@184.3Unverified
6DIGNR@178.73Unverified
7LCMCGR@176.74Unverified
8Soft-Label Chain CRF (SL-CCRF)R@174.69Unverified
9DDPN (ResNet-101)R@173.3Unverified
10VisualBERTR@171.33Unverified
#ModelMetricClaimedVerifiedStatus
1GBS Ensemble + 12-in-1Pointing Game Accuracy85.9Unverified
2GbS Ensemble MS-COCOPointing Game Accuracy75.6Unverified
3COCO_ELMo_PNASNetPointing Game Accuracy69.19Unverified
#ModelMetricClaimedVerifiedStatus
1Fiber-BR@187.1Unverified
2PEVLR@184.1Unverified
3VisualBERTR@170.4Unverified
#ModelMetricClaimedVerifiedStatus
1VG_BiLSTM_VGGPointing Game Accuracy62.76Unverified
2GbS Ensemble MS-COCOPointing Game Accuracy58.21Unverified
3MCBAccuracy28.91Unverified
#ModelMetricClaimedVerifiedStatus
1GbS VGPointing Game Accuracy55.91Unverified
2VG_ELMo_PNASNetPointing Game Accuracy55.16Unverified
3GbS Ensemble MS-COCOPointing Game Accuracy54.55Unverified