Skip to content

Keystroke Partial Action Accuracy

Measures duration-weighted set F1 between recovered and commanded atomic actions. It penalizes both missing and extra actions. For prediction PiP_i, target GiG_i and observed interval duration wiw_i:

F1(Pi,Gi)=2 ∣Pi∩Gi∣∣Pi∣+∣Gi∣(1)\mathrm{F1}(P_i, G_i) = \frac{2\, |P_i \cap G_i|}{|P_i| + |G_i|} \tag{1} partial=∑iwi⋅F1(Pi,Gi)∑iwi(2)\mathrm{partial} = \frac{\sum_i w_i \cdot \mathrm{F1}(P_i, G_i)}{\sum_i w_i} \tag{2}

Two empty sets have F1=1\mathrm{F1} = 1. For one requested action and five predicted actions including that request, F1\mathrm{F1} is 1/31/3, not 11. Higher is better.

Uses the same fixed-rate decoder, native timing and coverage rules as strict accuracy. This official action-control metric measures label agreement; it does not independently measure memory or calibrated motion amplitude. Backend: pose_action.

Audit manifest: docs/assets/metric_examples/longseq_memory_60s_examples_20260909.json.

Input image: memory-dolly_loop-memory_pool_238
Input image
60s memory_loop · same benchmark case · gap 0.9781

memory-dolly_loop-memory_pool_238

Suite: memory_loopScene: stylized / outdoor / suburb
Benchmark prompt target

Move the camera forward through the scene, then back to where it started.

prompt source: memory_loop_prompt

Partial credit still counts overlapping keys. The better 60s example follows the requested direction; the weaker one substitutes a different move.

Model result videos will be available with the ModelScope release. / 模型推理视频将在 ModelScope 方案上线后提供。

Higher metric scoreScore 0.9781 · official

Model result videos will be available with the ModelScope release. / 模型推理视频将在 ModelScope 方案上线后提供。

Lower metric scoreScore 0.0000 · official
Input image: memory-yaw_loop_180-memory_pool_439
Input image
60s memory_loop · same benchmark case · gap 0.9174

memory-yaw_loop_180-memory_pool_439

Suite: memory_loopScene: stylized / outdoor / aquatic_landscape
Benchmark prompt target

Turn the camera to the right, then turn back to the starting view.

prompt source: memory_loop_prompt

Partial credit still counts overlapping keys. The better 60s example follows the requested direction; the weaker one substitutes a different move.

Model result videos will be available with the ModelScope release. / 模型推理视频将在 ModelScope 方案上线后提供。

Higher metric scoreScore 0.9441 · official

Model result videos will be available with the ModelScope release. / 模型推理视频将在 ModelScope 方案上线后提供。

Lower metric scoreScore 0.0267 · official
Input image: memory-yaw_loop_360-memory_pool_132
Input image
60s memory_loop · same benchmark case · gap 0.9161

memory-yaw_loop_360-memory_pool_132

Suite: memory_loopScene: stylized / outdoor / terrestrial_landscape
Benchmark prompt target

Rotate the camera a full turn in place and come back to the starting view.

prompt source: memory_loop_prompt

Partial credit still counts overlapping keys. The better 60s example follows the requested direction; the weaker one substitutes a different move.

Model result videos will be available with the ModelScope release. / 模型推理视频将在 ModelScope 方案上线后提供。

Higher metric scoreScore 0.9283 · official

Model result videos will be available with the ModelScope release. / 模型推理视频将在 ModelScope 方案上线后提供。

Lower metric scoreScore 0.0122 · official
Input image: memory-double_yaw_loop-memory_pool_260
Input image
60s memory_loop · same benchmark case · gap 0.4901

memory-double_yaw_loop-memory_pool_260

Suite: memory_loopScene: stylized / indoor / living_spaces
Benchmark prompt target

Turn away and back to the start twice in a row.

prompt source: memory_loop_prompt

Partial credit still counts overlapping keys. The better 60s example follows the requested direction; the weaker one substitutes a different move.

Model result videos will be available with the ModelScope release. / 模型推理视频将在 ModelScope 方案上线后提供。

Higher metric scoreScore 0.7072 · official

Model result videos will be available with the ModelScope release. / 模型推理视频将在 ModelScope 方案上线后提供。

Lower metric scoreScore 0.2171 · official
Input image: memory-dolly_loop-memory_pool_463
Input image
60s memory_loop · same benchmark case · gap 0.3753

memory-dolly_loop-memory_pool_463

Suite: memory_loopScene: photorealistic / outdoor / terrestrial_landscape
Benchmark prompt target

Move the camera forward through the scene, then back to where it started.

prompt source: memory_loop_prompt

Partial credit still counts overlapping keys. The better 60s example follows the requested direction; the weaker one substitutes a different move.

Model result videos will be available with the ModelScope release. / 模型推理视频将在 ModelScope 方案上线后提供。

Higher metric scoreScore 0.8285 · official

Model result videos will be available with the ModelScope release. / 模型推理视频将在 ModelScope 方案上线后提供。

Lower metric scoreScore 0.4531 · official