A surface mountable storage assembly for storing and organizing purses and handbags includes a housing, which defines an interior space. The housing has a top, which is open, and a front, which has an aperture positioned therein. Contents, such as purses and handbags, can be inserted into the housing through the top. A panel is engaged to the housing and extends over the aperture. The panel is substantially transparent so that the contents of the housing are visible therethrough. A fastener engaged to a back of the housing engages a surface to mount the housing thereto.

A key locator with tracking capability. A bent rod-shaped first member has a bent first end portion and a second end portion. A second member is configured for selectively retaining keys. The bent first end portion and second end portion are opposed to each other. The bend rod-shaped first member incorporates a planar bent center region intermediate to the bent first end portion and the second end portion to form the interior of the key locator. The bent first end portion and the second end portion are not urged against each other and are configured to allow the bent center region to hang from an edge. The bent first end portion of the bent rod-shaped first member substantially permanently and flexibly interlocks with the second member. A tracking device is connected to the key locator and is in radio frequency communication with a user's smart phone. In a preferred embodiment the tracking device enables a user of the smart phone to find the key locator if it is lost or misplaced.

An anti-theft pocket insert designed to prevent a pickpocket from stealing items stored within a traditional pocket. The anti-theft pocket insert includes a first fabric member having a front surface and a rear surface. A second fabric member is affixed to the front surface of the first fabric member such that a compartment having an interior volume designed to hold a passport or wallet is formed. An upper side of the second fabric member is not affixed to the first fabric member such that an opening in communication with the interior volume is formed. Further, the first fabric member is greater in length than the second fabric member such that a top edge of the first fabric member overhangs the opening. In this way, a user is able to store items inside the anti-theft pocket insert and place the insert within a pocket to prevent pickpockets from stealing the items.

An activity classifier system and method that classifies human activities using 2D skeleton data. The system includes a skeleton preprocessor that transforms the 2D skeleton data into transformed skeleton data, the transformed skeleton data comprising scaled, relative joint positions and relative joint velocities. The system also includes a gesture classifier comprising a first recurrent neural network that receives the transformed skeleton data, and is trained to identify the most probable of a plurality of gestures. The system also has an action classifier comprising a second recurrent neural network that receives information from the first recurrent neural networks and is trained to identify the most probable of a plurality of actions.

An activity classifier system and method that classifies human activities using 2D skeleton data. The system includes a skeleton preprocessor that transforms the 2D skeleton data into transformed skeleton data, the transformed skeleton data comprising scaled, relative joint positions and relative joint velocities. The system also includes a gesture classifier comprising a first recurrent neural network that receives the transformed skeleton data, and is trained to identify the most probable of a plurality of gestures. The system also has an action classifier comprising a second recurrent neural network that receives information from the first recurrent neural networks and is trained to identify the most probable of a plurality of actions.

A surface mountable storage assembly for storing and organizing purses and handbags includes a housing, which defines an interior space. The housing has a top, which is open, and a front, which has an aperture positioned therein. Contents, such as purses and handbags, can be inserted into the housing through the top. A panel is engaged to the housing and extends over the aperture. The panel is substantially transparent so that the contents of the housing are visible therethrough. A fastener engaged to a back of the housing engages a surface to mount the housing thereto.

A chained purse wallet that provide a convenient way for a person's wallet to have the ability to be clipped to the interior of a purse. The chained purse wallet includes a ring inserted through an aperture disposed above the edge of a fold portion of the bifold and attached to a first end of the attachment chain and a C-clasp or a safety pin fastener disposed on a second end of the attachment chain that are utilized to couple the chained purse wallet to a purse.

An activity classifier system and method that classifies human activities using 2D skeleton data. The system includes a skeleton preprocessor that transforms the 2D skeleton data into transformed skeleton data, the transformed skeleton data comprising scaled, relative joint positions and relative joint velocities. The system also includes a gesture classifier comprising a first recurrent neural network that receives the transformed skeleton data, and is trained to identify the most probable of a plurality of gestures. The system also has an action classifier comprising a second recurrent neural network that receives information from the first recurrent neural networks and is trained to identify the most probable of a plurality of actions.

This disclosure is directed to an activity classifier system, for classifying human activities using 2D skeleton data. The system includes a skeleton preprocessor that transforms the 2D skeleton data into transformed skeleton data, the transformed skeleton data comprising scaled, relative joint positions and relative joint velocities. It also includes a gesture classifier comprising a first recurrent neural network that receives the transformed skeleton data, and is trained to identify the most probable of a plurality of gestures. There is also an action classifier comprising a second recurrent neural network that receives information from the first recurrent neural networks and is trained to identify the most probable of a plurality of actions.

An adaptable handbag system enables a user to customize the capacity of their hand bag by adding or removing bags from a carrying ring. The bags are attached to the ring via a hinge and attachment point to allow the bag to move with respect to the carrying ring. The bags have different shapes and markings to allow for quick identification even in less than optimal viewing conditions.