Update README.md

README.md

@@ -6,7 +6,6 @@ tags:
 - inverse-dynamics
 - camera-motion
 - optical-flow
-- counter-strike-2
 model-index:
 - name: RIDM flow model
   results:
@@ -33,9 +32,6 @@ model-index:
   - task:
       type: video-classification
       name: Forward, turn left or turn right
-    dataset:
-      name: Counter-Strike 2, 7,716 frame pairs
-      type: counter-strike-2
     metrics:
     - type: accuracy
       value: 84.5
@@ -43,9 +39,6 @@ model-index:
   - task:
       type: video-classification
       name: Turn direction
-    dataset:
-      name: Counter-Strike 2, 3,716 turn pairs
-      type: counter-strike-2
     metrics:
     - type: accuracy
       value: 84.9
@@ -55,18 +48,18 @@ model-index:
 # Reka Inverse Dynamics Model (RIDM)
 
 Two models predict camera motion (W/A/S/D/Shift, yaw, pitch) from video.
-Both trained on Counter-Strike 2 renders.
+Both trained on game renders.
 
 | | [flow](flow/) | [pixel](pixel/) |
 |---|---|---|
 | Input | Optical flow (RAFT-small) | Raw frames |
 | Parameters | 1,795,337 trained, plus 990,162 in frozen RAFT-small (2,785,499 in total) | 9,836,063 |
 | Output | One prediction per 17-frame window | One prediction per frame |
-| Real-video turn accuracy | 91.5 | 51.1 † |
-| Counter-Strike 2 turn accuracy | 84.9 | 70.9 † |
+| Real-video turn accuracy | 91.5 | 51.1 |
+| Gaming footage turn accuracy | 84.9 | 70.9 |
 | Dependencies | torch, torchvision, av, opencv, safetensors | torch, av, opencv, safetensors |
 
-† The number comes from a write-up and has no run log yet. All scores are in `results.json`.
+All scores are in `results.json`.
 
 ```text
 Reka-Inverse-Dynamics-Model/
@@ -88,8 +81,8 @@ In the failure clip the camera stands still and pans. The model reports the walk
 
 ## Which model to use
 
-Use the flow model for real video. The pixel model gives no clear signal on real footage.
-Its card says so. Use the pixel model for Counter-Strike 2 footage only.
+The flow model has better generalization capabilities to real videos.
+The pixel model might have a high potential for gaming footage especially if trained further.
 
 ## Use
 
@@ -110,7 +103,7 @@ Status: preliminary release. The scores marked † are unconfirmed.
 
 ## Training data
 
-- Source: 4,071 recorded Counter-Strike 2 matches, captured at 1,280 x 720 and 48 frames per second.
+- Source: 4,071 recorded gaming footage plays, captured at 1,280 x 720 and 48 frames per second.
 - Labels: the game engine gives the keys, the mouse movement and the camera angles for every frame. Nobody annotates.
 - Flow model: 7,071,037 frame pairs. Pixel model: about 104,000 gameplay windows.
 - Both models trained on one NVIDIA L4 GPU.
@@ -119,7 +112,7 @@ Status: preliminary release. The scores marked † are unconfirmed.
 
 - The weights and the code in this repository use the Apache License 2.0. See `LICENSE`.
 - RAFT-small weights use the BSD-3 license. They come from torchvision and are not in this repository. See `NOTICE`.
-- The models trained on Counter-Strike 2 gameplay captures. This repository holds no game assets, no gameplay clips and no training data.
+- The models trained on gameplay captures. This repository holds no game assets, no gameplay clips and no training data.
 - The videos in `assets/` and `examples/` are not Apache 2.0. They come from walking tours by POPtravel on Wikimedia Commons, licensed CC BY 3.0, and carry the model overlay or are shortened excerpts.
   Sources: [Bristol](https://commons.wikimedia.org/wiki/File:Walking_in_BRISTOL_-_UK_-_4K_60fps_(UHD).webm),
   [Ingolstadt](https://commons.wikimedia.org/wiki/File:Walking_in_INGOLSTADT_-_Germany_-_4K_60fps_(UHD).webm),