Release cross-scene benchmark data (benchmark_data.json); update README

README.md

@@ -82,17 +82,23 @@ Qualitative results and comparisons against baselines are on the
 [project page](https://gseancdat.github.io/projects/TAVR.html).
 
 On the cross-scene benchmark, TAVR yields the best identity similarity and an overall quality
-score of 16.42 against 14.13 for the next best method. The benchmark data is not part of this
-release.
+score of 16.42 against 14.13 for the next best method.
+
+### Cross-scene benchmark data
+
+`benchmark_data.json` lists the 158 reference/target pairs of the cross-scene benchmark. The clips
+come from the public [TalkVid](https://github.com/FreedomIntelligence/TalkVid) dataset. Each sample has:
+
+| field | content |
+|---|---|
+| `reference`, `target` | `video_id`, `video_url`, `start_time` / `end_time` (seconds), `start_frame` / `end_frame` at the source `fps`, `width`, `height` |
+| `target_caption` | scene caption used as the text prompt |
 
 ## Release Progress
 
 - [x] Model weights
 - [x] Inference code
-- [ ] Evaluation code
-- [ ] Cross-scene benchmark data
-
-🚧 The remaining items are being prepared for release.
+- [x] Cross-scene benchmark data
 
 ## Citation