BigRedT / info-ground
Learning phrase grounding from captioned images through InfoNCE bound on mutual information
☆72Updated 4 years ago
Alternatives and similar repositories for info-ground:
Users that are interested in info-ground are comparing it to the libraries listed below
- Improving One-stage Visual Grounding by Recursive Sub-query Construction, ECCV 2020☆84Updated 3 years ago
- ☆62Updated 3 years ago
- Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding☆33Updated 5 years ago
- This is an implementation of "Grounding of Textual Phrases in Images by Reconstruction" in PyTorch☆17Updated 4 years ago
- This repository contains the main baselines introduced in WSSTG (ACL 2019).☆55Updated 7 months ago
- Implementation for MAF: Multimodal Alignment Framework☆44Updated 4 years ago
- Code for Greedy Gradient Ensemble for Visual Question Answering （ICCV 2021, Oral）☆26Updated 2 years ago
- Human-like Controllable Image Captioning with Verb-specific Semantic Roles.☆36Updated 2 years ago
- ☆25Updated 3 years ago
- AAAI2020-The official implementation of "Learning Cross-modal Context Graph for Visual Grounding"☆57Updated 3 years ago
- Accepted by CVPR 2020.☆24Updated 7 months ago
- Codebase for CVPR 2020 paper "Spatio-Temporal Graph for Video Captioning with Knowledge Distillation"☆23Updated 4 years ago
- PyTorch code for: Learning to Generate Grounded Visual Captions without Localization Supervision☆44Updated 4 years ago
- Starter Code for VALUE benchmark☆80Updated 2 years ago
- Official codebase for "Ref-NMS: Breaking Proposal Bottlenecks in Two-Stage Referring Expression Grounding"☆21Updated 4 years ago
- Some papers about *diverse* image (a few videos) captioning☆26Updated last year
- Weakly Supervised Video Moment Retrieval from Text Queries☆42Updated 4 years ago
- The official PyTorch code for "Relation-aware Instance Refinement for Weakly Supervised Visual Grounding" accepted by CVPR2021☆26Updated 3 years ago
- Unpaired Image Captioning☆35Updated 3 years ago
- Data Release for VALUE Benchmark☆31Updated 3 years ago
- Compact Trilinear Interaction for Visual Question Answering (ICCV 2019)☆38Updated 2 years ago
- This repository provides the dataset introduced by our WSSTG paper☆12Updated 5 years ago
- Adaptive Offline Quintuplet Loss for Image-Text Matching (AOQ)☆34Updated 4 years ago
- [CVPR20] Video Object Grounding using Semantic Roles in Language Description (https://arxiv.org/abs/2003.10606)☆67Updated 4 years ago
- Code for CVPR 19 Paper "Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing"☆33Updated 5 years ago
- Code release for Learning to Assemble Neural Module Tree Networks for Visual Grounding (ICCV 2019)☆38Updated 5 years ago
- Code for "Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations" （NeurIPS 2019）☆65Updated 4 years ago
- Cross Modal Retrieval with Querybank Normalisation☆55Updated last year
- Counterfactual Samples Synthesizing for Robust VQA☆77Updated 2 years ago
- A pytorch implemetation of data augmentation method for visual question answering☆21Updated last year