The Brand Safety classes are mapped to the GARM Brand Safety & Suitability Framework (Global Alliance for Responsible Media), which was defined as part of a cross-industry initiative established by the World Federation of Advertisers to address the challenge of harmful content on digital media platforms and its monetization via advertising. Hive has committed to building out additional class support in our Visual Content Moderation Suite to power this framework. These GARM classes are defined in Hive's Visual Content Moderation suite through the presence of visual cues pertinent to the GARM framework's classes. The classes below refer to the image-based API; support for text and audio are available separately.
Note on Brand Suitability API: Brand Suitability ratings are available by request for each of these Brand Safety classes. Brand Suitability classifies the risk level in four tiers: low, medium, high, and floor. Floor risk is defined as content not suitable for any advertiser, whereas High and Medium risk is suitable for only certain advertisers depending on type of risk and risk tolerance.
|IAB Unique ID||Class Name||Examples of Visual Cues|
|Rm3SiT||Rm3SiT-adult_and_explicit_sexual_content-hive_garm_iab||genitalia, sexual activity, nudity, buttocks, sex toys|
|avbNf2||avbNf2-arms_and_ammunition-hive_garm_iab||guns, knives, and guns-in-use|
|I4GWl6||I4GWl6-death_injury_or_military_conflict-hive_garm_iab||gore, blood, hanging, military conflict|
|HxqYV1||HxqYV1-hate_speech_and_acts_of_aggression-hive_garm_iab||kkk imagery, nazi imagery|
|pg0WhF||pg0WhF-illegal_drugs_tobacco_ecigarettes_vaping_alcohol-hive_garm_iab||pilled or powdered drugs; tobacco, marijuana, or vaping paraphernalia|
|8FD8nI||8FD8nI-terrorism-hive_garm_iab||ISIS symbol imagery|
|Not Applicable*||9010-suggestive_sexual_content-hive||nude or suggestive content (swimwear, underwear, shirtless-ness)|
*The Suggestive Sexual Content class is a custom Hive class included to supplement the Brand Safety & Suitability. It is not included in the IAB taxonomy and GARM frameworks.
For each frame delivered, the API will return a response for each class. Each class will have a value from 0 to 1, indicating the confidence level of the classification.
Updated about 1 year ago