Video-Text Retrieval Models
Video Language Graph Matching Network
Introduced by Soldan et al. in VLG-Net: Video-Language Graph Matching Network for Video GroundingVLG-Net leverages recent advantages in Graph Neural Networks (GCNs) and leverages a novel multi-modality graph-based fusion method for the task of natural language video grounding.
Source: VLG-Net: Video-Language Graph Matching Network for Video GroundingPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Moment Retrieval | 2 | 28.57% |
| Natural Language Moment Retrieval | 2 | 28.57% |
| Graph Matching | 1 | 14.29% |
| Temporal Localization | 1 | 14.29% |
| Video Grounding | 1 | 14.29% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
