Visual Grounding
178 papers with code • 3 benchmarks • 5 datasets
Visual Grounding (VG) aims to locate the most relevant object or region in an image, based on a natural language query. The query can be a phrase, a sentence, or even a multi-round dialogue. There are three main challenges in VG:
- What is the main focus in a query?
- How to understand an image?
- How to locate an object?
Benchmarks
These leaderboards are used to track progress in Visual Grounding
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Libraries
Use these libraries to find Visual Grounding models and implementations
RefCOCO
DIOR-RSVG
VizWiz Answer Grounding
A Game Of Sorts
SK-VG
Most implemented papers
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
facebookresearch/vilbert-multi-task
•
•
NeurIPS 2019
We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language.
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
akirafukui/vqa-mcb
•
•
EMNLP 2016
Approaches to multimodal pooling include element-wise product or sum, as well as concatenation of the visual and textual representations.
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
In this paper, we propose ViewRefer, a multi-view framework for 3D visual grounding exploring how to grasp the view knowledge from both text and 3D modalities.
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
ofa-sys/ofa
•
•
In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization.
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
In contrast to predominant paradigms of solely relying on sequence-to-sequence generation or encoder-based instance discrimination, mPLUG-2 introduces a multi-module composition network by sharing common universal modules for modality collaboration and disentangling different modality modules to deal with modality entanglement.
Grounding of Textual Phrases in Images by Reconstruction
We propose a novel approach which learns grounding by reconstructing a given phrase using an attention mechanism, which can be either latent or optimized directly.
Revisiting Visual Question Answering Baselines
Cold-Winter/vqs
•
•
Visual question answering (VQA) is an interesting learning setting for evaluating the abilities and shortcomings of current systems for image understanding.
Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat
shekharRavi/Beyond-Task-Success-NAACL2019
•
•
NAACL 2019
We compare our approach to an alternative system which extends the baseline with reinforcement learning.
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
ashkamath/mdetr
•
•
We also investigate the utility of our model as an object detector on a given label set when fine-tuned in a few-shot setting.
Word Discovery in Visually Grounded, Self-Supervised Speech Models
We present a method for visually-grounded spoken term discovery.
