Systems and methods for facilitating searching, labeling, and/or filtering of digital media items

Abstract

In certain embodiments, media item search and machine learning system training may be facilitated. In some embodiments, a first set of media items may be obtained (based on performance of a query) and presented on a user interface. A user selection of a media item of the first set may be obtained, and the query may be updated based on the user-selected media item. A second set of media items may be obtained based on performance of the updated query, and media items of the second set may be assigned to a group based on their similarities with one another. A predicted name for the group may be determined via a machine learning system and presented on the user interface. A user-indicated update to the predicted name for the group may be obtained and provided to the machine learning system to train the machine learning system.

1 - 20 . (canceled) 
     
     
         21 . A computing system, comprising:
 a memory configured to store instructions for displaying a user interface; and   a processor configured to
 display, via the user interface, a first set of media items, the first set of media items identified responsive to a search request; 
 receive, via the user interface, a selection of a selected media item from the first set of media items; 
 display, via the user interface, a second set of media items, the second set of media items responsive to an updated search request based on the selected media item, the second set of media items grouped together based on similarities of the second set to one another; 
 display, via the user interface, a predicted name for the second set of media items, the predicted name determined via a visual-semantic embedding space of a machine learning system based on information associated with the second set of media items; and 
 receive, via the user interface, a user-indicated update to the predicted name, the user-indicated update to the predicted name provided to the machine learning system with the selected media item to cause the machine learning system to be trained based on the user-indicated update and the selected media item. 
   
     
     
         22 . The computing system of  claim 21 , wherein the processor is further configured to, in the display of the first set of media items:
 identify a central media item of the first set of media items where the central media item is in a central representative point in the visual-semantic embedding space associated with the first set of media items; and   display the central media item in a position of priority on the user interface.   
     
     
         23 . The computing system of  claim 22 , wherein the processor is further configured to, in the display of the central media item:
 display the central media item in a center of a display area of the user interface; and   display the other media items in the first set of media items around the central media item.   
     
     
         24 . The computing system of  claim 21 , wherein the updated search request is further based on:
 context information obtained via the machine learning system, the context information associated with the selected media item, wherein at least some of the context information is predicted by the machine learning system.   
     
     
         25 . The computing system of  claim 21 , wherein the first set of media items are mapped to points in the visual-semantic embedding space, wherein the processor is further configured to:
 Assign media items of the first set of media items to a first group based on similarities of the media items of the first set to one another; and   cause the first set of media items to be presented on the user interface such that (i) a central media item of the first group mapped to a most central representative point in the visual-semantic embedding space associated with the first group is presented in a position of priority, the position of priority being proximate to a center of a display portion of the user interface and (ii) other media items of the first group are presented around the central media item.   
     
     
         26 . The computing system of  claim 25 , wherein the processor is further configured to:
 present each of the media items of the first group overlaid over one another in a stack arrangement view; and   receive, via the user interface, a signal to cause the stack arrangement view to be changed such that the central media item of the first group is presented in the position of priority and the other media items of the first group are presented around a periphery of the central media item.   
     
     
         27 . The computing system of  claim 25 , wherein the central media item of the first group is portrayed larger relative to the other media items of the first group. 
     
     
         28 . The computing system of  claim 25 , wherein the second set of media items are mapped to points in the visual-semantic embedding space, and wherein the media items of a second group are presented on the user interface such that (i) a second central media item of the second group mapped to a most central representative point in the visual-semantic embedding space associated with the second group is presented in the position of priority, and (ii) other media items of the second group are presented around the second central media item. 
     
     
         29 . A method, comprising:
 displaying, via a user interface, a first set of media items, the first set of media items identified responsive to a search request;   receiving, via the user interface, a selection of a selected media item from the first set of media items;   displaying, via the user interface, a second set of media items, the second set of media items responsive to an updated search request based on the selected media item, the second set of media items grouped together based on similarities of the second set to one another;   displaying, via the user interface, a predicted name for the second set of media items, the predicted name determined via a visual-semantic embedding space of a machine learning system based on information associated with the second set of media items; and   receiving, via the user interface, a user-indicated update to the predicted name, the user-indicated update to the predicted name provided to the machine learning system with the selected media item to cause the machine learning system to be trained based on the user-indicated update and the selected media item.   
     
     
         30 . The method of  claim 29 , wherein the display of the first set of media items further comprises:
 identifying a central media item of the first set of media items where the central media item is in a central representative point in the visual-semantic embedding space associated with the first set of media items; and   displaying the central media item in a position of priority on the user interface.   
     
     
         31 . The method of  claim 30 , wherein the display of the central media item further comprises:
 displaying the central media item in a center of a display area of the user interface; and   displaying the other media items in the first set of media items around the central media item.   
     
     
         32 . The method of  claim 29 , wherein the updated search request is further based on:
 context information obtained via the machine learning system, the context information associated with the selected media item, wherein at least some of the context information is predicted by the machine learning system.   
     
     
         33 . The method of  claim 29 , wherein the first set of media items are mapped to points in the visual-semantic embedding space, the method further comprising:
 assigning media items of the first set of media items to a first group based on similarities of the media items of the first set to one another; and   causing the first set of media items to be presented on the user interface such that (i) a central media item of the first group mapped to a most central representative point in the visual-semantic embedding space associated with the first group is presented in a position of priority, the position of priority being proximate to a center of a display portion of the user interface and (ii) other media items of the first group are presented around the central media item.   
     
     
         34 . A non-transitory computer-readable medium comprising instructions which when executed by a processor cause a computer to perform a method comprising:
 displaying, via a user interface, a first set of media items, the first set of media items identified responsive to a search request;   receiving, via the user interface, a selection of a selected media item from the first set of media items;   displaying, via the user interface, a second set of media items, the second set of media items responsive to an updated search request based on the selected media item, the second set of media items grouped together based on similarities of the second set to one another;   displaying, via the user interface, a predicted name for the second set of media items, the predicted name determined via a visual-semantic embedding space of a machine learning system based on information associated with the second set of media items; and   receiving, via the user interface, a user-indicated update to the predicted name, the user-indicated update to the predicted name provided to the machine learning system with the selected media item to cause the machine learning system to be trained based on the user-indicated update and the selected media item.