Transformers
VideoBERT
Introduced by Sun et al. in VideoBERT: A Joint Model for Video and Language Representation LearningVideoBERT adapts the powerful BERT model to learn a joint visual-linguistic representation for video. It is used in numerous tasks, including action classification and video captioning.
Source: VideoBERT: A Joint Model for Video and Language Representation Learning
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Language Modelling | 3 | 18.75% |
| Sentence | 1 | 6.25% |
| Image Retrieval | 1 | 6.25% |
| Question Answering | 1 | 6.25% |
| Retrieval | 1 | 6.25% |
| Visual Grounding | 1 | 6.25% |
| Visual Question Answering | 1 | 6.25% |
| Visual Question Answering (VQA) | 1 | 6.25% |
| Action Classification | 1 | 6.25% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
