# HOI Semantic Similarity Alignment on HICO-DET (User Study Average) Source: [HOI Semantic Similarity Alignment on HICO-DET (User Study Average)]() Collection index: [llms.txt]() Data updated: 2026-04-03T07:44:15.742Z Evaluation of model performance on aligning HOI semantic similarity based on aggregated human judgment scores derived from HICO-DET labels. 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 | HOI Semantic Similarity Alignment | | Dataset (including any stated split) | HOI similarity human judgment HICO-DET labels (user study average) | | Metric | Agreement Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Agreement Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Agreement Score | Result date | Report paper | | --- | --- | --- | --- | | SHOE | 85.73 | Not recorded | 69cf49780636e5bf4afcd98e | | SHOE | 84.29 | Not recorded | 69cf49780636e5bf4afcd98e | | SHOE | 84.01 | Not recorded | 69cf49780636e5bf4afcd98e | | DeepSeek-V3-0324 | 83.34 | Not recorded | 69cf49780636e5bf4afcd98e | | Llama-4-Mav-17B | 82.1 | Not recorded | 69cf49780636e5bf4afcd98e | | Qwen3-32B | 82.03 | Not recorded | 69cf49780636e5bf4afcd98e | | Yi-1.5-34B-Chat | 81.55 | Not recorded | 69cf49780636e5bf4afcd98e | | Gemini-2.5-Pro | 77.52 | Not recorded | 69cf49780636e5bf4afcd98e | | CLIP-ViT-B | 59.11 | Not recorded | 69cf49780636e5bf4afcd98e | | CLIP-ViT-B | 58.15 | Not recorded | 69cf49780636e5bf4afcd98e | | BGE | 57.41 | Not recorded | 69cf49780636e5bf4afcd98e | | WordNet | 57.09 | Not recorded | 69cf49780636e5bf4afcd98e | | BGE | 56.37 | Not recorded | 69cf49780636e5bf4afcd98e | | WordNet | 55.69 | Not recorded | 69cf49780636e5bf4afcd98e | | SBERT | 54.09 | Not recorded | 69cf49780636e5bf4afcd98e | | SBERT | 52.86 | Not recorded | 69cf49780636e5bf4afcd98e | | WordNet | 52.47 | Not recorded | 69cf49780636e5bf4afcd98e | | direct-match | 38.9 | Not recorded | 69cf49780636e5bf4afcd98e | ### SHOE Agreement Score: 85.73. Result ID: 69cf6f7e47f34ce924b8fda7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Similarity metric variant":"Standard"}. This record does not assert independent reproduction. ### SHOE Agreement Score: 84.29. Result ID: 69cf6f7e47f34ce924b8fda8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Similarity metric variant":"Geometric Mean"}. This record does not assert independent reproduction. ### SHOE Agreement Score: 84.01. Result ID: 69cf6f7e47f34ce924b8fda9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Similarity metric variant":"Minimum"}. This record does not assert independent reproduction. ### DeepSeek-V3-0324 Agreement Score: 83.34. Result ID: 69cf6f7e47f34ce924b8fdaa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Llama-4-Mav-17B Agreement Score: 82.1. Result ID: 69cf6f7e47f34ce924b8fdac. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-32B Agreement Score: 82.03. Result ID: 69cf6f7e47f34ce924b8fdab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Yi-1.5-34B-Chat Agreement Score: 81.55. Result ID: 69cf6f7e47f34ce924b8fdad. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-2.5-Pro Agreement Score: 77.52. Result ID: 69cf6f7e47f34ce924b8fdae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CLIP-ViT-B Agreement Score: 59.11. Result ID: 69cf6f7e47f34ce924b8fdb2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input representation":"gloss"}. This record does not assert independent reproduction. ### CLIP-ViT-B Agreement Score: 58.15. Result ID: 69cf6f7e47f34ce924b8fdb3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input representation":"pair"}. This record does not assert independent reproduction. ### BGE Agreement Score: 57.41. Result ID: 69cf6f7e47f34ce924b8fdb4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input representation":"gloss"}. This record does not assert independent reproduction. ### WordNet Agreement Score: 57.09. Result ID: 69cf6f7e47f34ce924b8fdaf. [Reporting paper]() Recorded evaluation configuration: {"Similarity metric variant":"WUP"}. This record does not assert independent reproduction. ### BGE Agreement Score: 56.37. Result ID: 69cf6f7e47f34ce924b8fdb5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input representation":"pair"}. This record does not assert independent reproduction. ### WordNet Agreement Score: 55.69. Result ID: 69cf6f7e47f34ce924b8fdb0. [Reporting paper]() Recorded evaluation configuration: {"Similarity metric variant":"LCH"}. This record does not assert independent reproduction. ### SBERT Agreement Score: 54.09. Result ID: 69cf6f7e47f34ce924b8fdb6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input representation":"gloss"}. This record does not assert independent reproduction. ### SBERT Agreement Score: 52.86. Result ID: 69cf6f7e47f34ce924b8fdb7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input representation":"pair"}. This record does not assert independent reproduction. ### WordNet Agreement Score: 52.47. Result ID: 69cf6f7e47f34ce924b8fdb1. [Reporting paper]() Recorded evaluation configuration: {"Similarity metric variant":"Path"}. This record does not assert independent reproduction. ### direct-match Agreement Score: 38.9. Result ID: 69cf6f7e47f34ce924b8fdb8. [Reporting paper]() Recorded evaluation configuration: {"Task Context":"mAP"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.