Abstract: Techniques for building automated workflow sequences associated with a document review platform are provided. A method includes accessing trigger event data from a trigger event database and action data from an action database; presenting a user interface to create a workflow; adding a function block to the workflow by: detecting a selection of an add function block option; presenting a function block including at least one of (i) a user-selectable option to select a trigger event from a list of trigger events populated based on the trigger event data or (ii) a user-selectable option to select an action from a list of actions populated based on the action data; and presenting the function block including at least one of a selected trigger event or a selected action; detecting that the workflow is ready for deployment; translating the workflow into a logic-based representation of the workflow; and deploying the logic-based representation.

Abstract: The present technology can detect potential labeling conflicts made during different labeling tasks when those tasks are checked in to ensure that a map database is free from conflicts that might interrupt publishing of a map. The present technology can determine whether a first labeled version of map portion is based on a most recent version for the map portion that is stored in the map database, and when it is determined that it is not, and there is an intervening version, the present technology can identify differences between the intervening version of the map portion and the first version of the map portion and identify differences between the second version of the map portion and the first version of the map portion. Based on the identified differences, the present technology can determine whether any of those differences are conflicting.

Abstract: Technology disclosed herein may involve a computing system that (i) generates (a) a first feature map based on a first visual input from a first perspective of a scene utilizing at least one first neural network and (b) a second feature map based on a second visual input from a second, different perspective of the scene utilizing at least one second neural network, where the first perspective and the second perspective share a common dimension, (ii) based on the first feature map and a portion of the second feature map corresponding to the common dimension, generates cross-referenced data for the first visual input, (iii) based on the second feature map and a portion of the first feature map corresponding to the common dimension, generates cross-referenced data for the second visual input, and (iv) based on the cross-referenced data, performs object detection on the scene.

Abstract: Technology disclosed herein may involve a computing system that (i) generates (a) a first feature map based on a first visual input from a first perspective of a scene utilizing at least one first neural network and (b) a second feature map based on a second visual input from a second, different perspective of the scene utilizing at least one second neural network, where the first perspective and the second perspective share a common dimension, (ii) based on the first feature map and a portion of the second feature map corresponding to the common dimension, generates cross-referenced data for the first visual input, (iii) based on the second feature map and a portion of the first feature map corresponding to the common dimension, generates cross-referenced data for the second visual input, and (iv) based on the cross-referenced data, performs object detection on the scene.

Abstract: Technology disclosed herein may involve a computing system that (i) generates (a) a first feature map based on a first visual input from a first perspective of a scene utilizing at least one first neural network and (b) a second feature map based on a second visual input from a second, different perspective of the scene utilizing at least one second neural network, where the first perspective and the second perspective share a common dimension, (ii) based on the first feature map and a portion of the second feature map corresponding to the common dimension, generates cross-referenced data for the first visual input, (iii) based on the second feature map and a portion of the first feature map corresponding to the common dimension, generates cross-referenced data for the second visual input, and (iv) based on the cross-referenced data, performs object detection on the scene.

Abstract: Technology disclosed herein may involve a computing system that (i) generates (a) a first feature map based on a first visual input from a first perspective of a scene utilizing at least one first neural network and (b) a second feature map based on a second visual input from a second, different perspective of the scene utilizing at least one second neural network, where the first perspective and the second perspective share a common dimension, (ii) based on the first feature map and a portion of the second feature map corresponding to the common dimension, generates cross-referenced data for the first visual input, (iii) based on the second feature map and a portion of the first feature map corresponding to the common dimension, generates cross-referenced data for the second visual input, and (iv) based on the cross-referenced data, performs object detection on the scene.

Abstract: Various systems, methods and non-transitory computer-readable media are described, which may involve performing operations comprising: receiving, with an object detector, a first image from a first positional angle comprising a first perspective of a scene, receiving, with the object detector, a second image from a second, different positional angle comprising a second perspective of the scene, and performing, with the object detector, object detection on the first image from the first perspective and on the second image from the second perspective by cross-referencing data related to the first image and the second image within the object detector.