# Action Recognition on CMU 2235 sequences (4-fold cross val) Source: [Action Recognition on CMU 2235 sequences (4-fold cross val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:27:16.366Z Evaluation of video action recognition performance using the CMU 2235 sequences dataset under a 4-fold cross-validation protocol. 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 | Action Recognition | | Dataset (including any stated split) | CMU 2235 sequences (4-fold cross val) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Clips + CNN + MTLN | 88.3 | Not recorded | 68fa63ce1e209131cea00bf2 | | Clips + CNN + Concatenation | 85.76 | Not recorded | 68fa63ce1e209131cea00bf2 | | Clips + CNN + Pooling | 85.56 | Not recorded | 68fa63ce1e209131cea00bf2 | | Frames + CNN | 85.36 | Not recorded | 68fa63ce1e209131cea00bf2 | | Deep LSTM + Co-occurrence | 81.04 | Not recorded | 68fa63ce1e209131cea00bf2 | | Deep LSTM | 79.53 | Not recorded | 68fa63ce1e209131cea00bf2 | | Hierarchical RNN | 75.02 | Not recorded | 68fa63ce1e209131cea00bf2 | | Coordinates + FTP | 73.61 | Not recorded | 68fa63ce1e209131cea00bf2 | ### Clips + CNN + MTLN Accuracy: 88.3. Result ID: 698c027af729bc7f68e7b11d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input":"Clips","architecture":"MTLN"}. This record does not assert independent reproduction. ### Clips + CNN + Concatenation Accuracy: 85.76. Result ID: 698c027af729bc7f68e7b11b. [Reporting paper]() Recorded evaluation configuration: {"input":"Clips","aggregation":"Concatenation"}. This record does not assert independent reproduction. ### Clips + CNN + Pooling Accuracy: 85.56. Result ID: 698c027af729bc7f68e7b11c. [Reporting paper]() Recorded evaluation configuration: {"input":"Clips","aggregation":"Pooling"}. This record does not assert independent reproduction. ### Frames + CNN Accuracy: 85.36. Result ID: 698c027af729bc7f68e7b11a. [Reporting paper]() Recorded evaluation configuration: {"input":"Individual Frames"}. This record does not assert independent reproduction. ### Deep LSTM + Co-occurrence Accuracy: 81.04. Result ID: 698c027af729bc7f68e7b118. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Deep LSTM Accuracy: 79.53. Result ID: 698c027af729bc7f68e7b117. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Hierarchical RNN Accuracy: 75.02. Result ID: 698c027af729bc7f68e7b116. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Coordinates + FTP Accuracy: 73.61. Result ID: 698c027af729bc7f68e7b119. [Reporting paper]() Recorded evaluation configuration: {"input":"Coordinates","feature":"FTP"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.