OpenCodePapers

phrase-grounding-on-flickr30k-entities-test

Phrase Grounding
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeR@1R@5R@10ModelNameReleaseDate
GLIPv2: Unifying Localization and Vision-Language Understanding✓ Link87.7GLIPv22022-06-12
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone✓ Link87.496.497.6FIBER-B2022-06-15
Grounded Language-Image Pre-training✓ Link87.196.998.1GLIP2021-12-07
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models✓ Link84.4PEVL2022-05-23
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding✓ Link84.393.995.8MDETR-ENB52021-04-26
Disentangled Motif-aware Graph Learning for Phrase Grounding78.73DIGN2021-04-13
Learning Cross-modal Context Graph for Visual Grounding✓ Link76.74LCMCG2020-02-13
Phrase Grounding by Soft-Label Chain Conditional Random Field✓ Link74.69Soft-Label Chain CRF (SL-CCRF)2019-09-01
Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding✓ Link73.3DDPN (ResNet-101)2018-05-09
VisualBERT: A Simple and Performant Baseline for Vision and Language✓ Link71.3384.9886.51VisualBERT2019-08-09
Bilinear Attention Networks✓ Link69.6984.2286.35BAN (Bottom-Up detector)2018-05-21
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding✓ Link48.69MCB2016-06-06
Grounding of Textual Phrases in Images by Reconstruction✓ Link48.38GroundeR 100.0% annot.2015-11-12
Learning Deep Structure-Preserving Image-Text Embeddings43.8964.4668.66DSPE2015-11-19
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models✓ Link41.7764.5270.77CCA - Fast RCNN2015-05-19
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models✓ Link30.8358.0167.15CCA - VGG192015-05-19
Natural Language Object Retrieval✓ Link27.862.9SCRC2015-11-13
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models✓ Link25.3059.66CCA2015-05-19
Check out how to contribute new results.