UWGZQ
/

TRASER

Video-Text-to-Text

video-scene-graph

scene-graph-generation

video-understanding

trajectory-aware

perceiver-resampler

Model card Files Files and versions

UWGZQ commited on 14 days ago

Commit

424132e

·

verified ·

1 Parent(s): cd03841

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ TRASER is the video scene graph generation model introduced in **Synthetic Visua
 ## Model Architecture
-![TRASER Architecture](static/image.png)
 TRASER extends **Qwen2.5-VL-3B-Instruct** with two trainable Perceiver Resampler modules that implement **Trajectory-Aligned Token Arrangement**:

 ## Model Architecture
+![TRASER Architecture](static/model.png)
 TRASER extends **Qwen2.5-VL-3B-Instruct** with two trainable Perceiver Resampler modules that implement **Trajectory-Aligned Token Arrangement**: