Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Model Card for Multimodal Risk Behavior Detection Model
|
| 2 |
|
| 3 |
## Model Overview
|
|
@@ -58,4 +62,4 @@ After training for 5 epochs, the model's performance on the test set was as foll
|
|
| 58 |
### Limitations
|
| 59 |
- Data Balance: If the dataset is imbalanced (more non-risky videos than risky ones), the model may struggle with precision.
|
| 60 |
- Contextual Understanding: The model relies heavily on textual captions. If a caption does not explicitly describe risky behavior, the model may underperform.
|
| 61 |
-
- Limited Frame Sampling: Only 10 frames per video are processed, which may miss important content, especially for longer videos.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- Souha-BH/DetectingRiskyHealthBehaviorsInTikTokVideos
|
| 4 |
+
---
|
| 5 |
# Model Card for Multimodal Risk Behavior Detection Model
|
| 6 |
|
| 7 |
## Model Overview
|
|
|
|
| 62 |
### Limitations
|
| 63 |
- Data Balance: If the dataset is imbalanced (more non-risky videos than risky ones), the model may struggle with precision.
|
| 64 |
- Contextual Understanding: The model relies heavily on textual captions. If a caption does not explicitly describe risky behavior, the model may underperform.
|
| 65 |
+
- Limited Frame Sampling: Only 10 frames per video are processed, which may miss important content, especially for longer videos.
|