# Embryo Stage Classification on NYU Mouse Embryo 2 (test) Source: [Embryo Stage Classification on NYU Mouse Embryo 2 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:45:59.684Z Evaluation of the model's ability to classify mouse embryos into specific developmental stages (1 through 8) using the test split of the NYU Mouse Embryo 2 dataset, reporting global and per-stage accuracies. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Embryo Stage Classification | | Dataset (including any stated split) | NYU Mouse Embryo 2 (test) | | Metric | Global Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Global Accuracy](): Higher is better; unit: PERCENT. - [Per-Stage Accuracy](): Higher is better; unit: PERCENT. - [Stage 1 Accuracy](): Higher is better; unit: PERCENT. - [Stage 2 Accuracy](): Higher is better; unit: PERCENT. - [Stage 3 Accuracy](): Higher is better; unit: PERCENT. - [Stage 4 Accuracy](): Higher is better; unit: PERCENT. - [Stage 5 Accuracy](): Higher is better; unit: PERCENT. - [Stage 6 Accuracy](): Higher is better; unit: PERCENT. - [Stage 7 Accuracy](): Higher is better; unit: PERCENT. - [Stage 8 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Global Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Two-Stream Linear-Chain CRF | 0.981 | Not recorded | 68fa6a611e209131cea27e09 | | LSTM | 0.98 | Not recorded | 68fa6a611e209131cea27e09 | | AutoIVF | 0.964 | Not recorded | 68fa6a611e209131cea27e09 | | Early Fusion | 0.919 | Not recorded | 68fa6a611e209131cea27e09 | | ResNet50 | 0.909 | Not recorded | 68fa6a611e209131cea27e09 | ### Two-Stream Linear-Chain CRF Global Accuracy: 0.981. Result ID: 698e30f7ffc3901de09b883b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Spatiotemporal Classification Model"}. This record does not assert independent reproduction. ### LSTM Global Accuracy: 0.98. Result ID: 698e30f7ffc3901de09b883a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Spatiotemporal Classification Model"}. This record does not assert independent reproduction. ### AutoIVF Global Accuracy: 0.964. Result ID: 698e30f7ffc3901de09b8838. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Per-Image Classification Model","Focus Mode":"single focus"}. This record does not assert independent reproduction. ### Early Fusion Global Accuracy: 0.919. Result ID: 698e30f7ffc3901de09b8839. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Spatiotemporal Classification Model","Temporal Context":"five successive frames"}. This record does not assert independent reproduction. ### ResNet50 Global Accuracy: 0.909. Result ID: 698e30f7ffc3901de09b8837. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Per-Image Classification Model","Backbone":"ResNet-50"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.