Abstract: Embodiments of a purge ring for use in a process chamber are provided herein. In some embodiments, a purge ring includes: an annular body having an inner portion and an outer portion, wherein the inner portion includes an inner surface of the annular body, the inner surface comprising a first inner sidewall, a second inner sidewall, and a third inner sidewall, wherein the inner portion has an upper inner notch that defines the first inner sidewall and a lower inner notch that defines the second inner sidewall, wherein a third inner sidewall is disposed between the first inner sidewall and the second inner sidewall, and wherein the first inner sidewall and the second inner sidewall are disposed radially outward of the third inner sidewall.

Abstract: A method of forming a semiconductor device structure includes forming a nucleation layer within at least one feature. The method includes exposing the nucleation layer to a nitrogen plasma treatment. The nitrogen plasma treatment preferentially treats the top field and sidewalls while leaving the bottom surface substantially untreated to encourage bottom up metal growth.

Abstract: A method of forming a structure on a substrate includes forming a tungsten nucleation layer within at least one feature. The method includes forming the nucleation layer via a cyclic vapor deposition process. The cyclic vapor deposition process includes forming a portion of the nucleation layer and then exposing the exposing the nucleation layer a chemical vapor transport (CVT) process to remove impurities from the portion of the nucleation layer. The CVT process may be performed at a temperature of 400 degrees Celsius or less and comprises forming a plasma from a processing gas comprising greater than or equal to 90% of hydrogen gas of a total flow of hydrogen gas and oxygen.

Abstract: A method and apparatus for tungsten gap-fill in semiconductor devices are provided. The method includes performing a gradient oxidation process to oxidize exposed portions of a liner layer, wherein the gradient oxidation process preferentially oxidizes an overhang portion of the liner layer, which obstructs or blocks top openings of one or more features formed within a field region of a substrate. The method further includes performing an etchback process to remove or reduce the oxidized overhang portion of the liner layer, exposing the liner layer to a chemical vapor transport (CVT) process to remove metal oxide remaining from the gradient oxidation process and the etchback process, and performing a tungsten gap-fill process to fill or partially fill the one or more features.

Abstract: Embodiments described herein provide techniques for forming an interconnect structure that includes micro features formed therein. Such embodiments can assist with improving interconnect joint reliability when compared to conventional pads that have a flat surface. An interconnect structure may comprise: a metal pad over a substrate (e.g., a semiconductor package, a PCB, an interposer, etc.). Micro features may be formed in an edge of the metal pad or away from the edge of the metal pad. The micro features can assist with: (i) increasing the contact area between solder used to form an interconnect joint and the metal pad; and (ii) improving adherence of solder used to form an interconnect joint to the metal pad. These benefits can improve interconnect joint reliability by, among others, improving the interconnect joint's ability to absorb stress from substrates having differing coefficients of thermal expansion.

Abstract: A method and related system operations includes, determining, for each respective frame of a frame sequence, a respective bounding box that surrounds a respective sub-image of the respective frame, determining a respective string and respective confidence values associated with the respective string based on the respective sub-image, updating the tracklet to comprise the respective bounding box based on the respective string and at least one string generated by the object recognition model for a previous frame, and updating a voting table by adding the respective confidence values to the voting table. The method also includes generating an aggregated string based on the voting table by, for a set of positions of the aggregated string, determining a character associated with a maximum confidence value indicated by the voting table and associating the aggregated string with the tracklet in a data structure.

Abstract: Techniques for rendering a 3D virtual object in an augmented-reality system are described. A system, a method, and a non-transitory memory device for augmented reality rendering of three-dimensional, virtual objects are described. In an example, a number of images of an environment are acquired; relative movement of a camera acquiring the number of images is tracked; camera pose is determined relative to the environment using the number of images and tracked relative movement of the camera; depth and normal surfaces of objects in the environment are estimated using a depth map and a normal map; a surface geometry of the environment is reconstructed using the depth map and the normal map; and the virtual object is rendered using the surface geometry of the environment.

Abstract: A computer vision processor of a camera extracts attributes of persons or vehicles from hyperzooms generated from image frames. The hyperzooms represent traffic patterns. The extracting is performed using a feature extractor of an on-camera convolutional neural network (CNN) including an inverted residual structure. The attributes include at least colors of clothing of the persons or colors of the vehicles. Mobile semantic segmentation models of the CNN are generated using the hyperzooms and the attributes. Attribute analytics are generated by executing the mobile semantic segmentation models while obviating network usage by the camera. The attribute analytics are stored in a key-value database located on a memory card of the camera. A query is received from the server instance specifying one or more of the attributes. The attribute analytics are filtered using the one or more of the attributes to obtain a portion of the traffic patterns.

Abstract: The present invention provides a method and system for acquiring operating parameters of a photographic lens, including: a control circuit and a storage unit that are configured in the photographic lens, where the control circuit acquires an operating parameter of the photographic lens by using a focusing ring position sensor, a zoom ring position sensor, an aperture ring position sensor, an accelerometer and a gyro sensor; and the control circuit is further connected to a camera or an external data reading device by using a communication interface, to output the operating parameter after data encapsulation in real time.

Abstract: Automatic license plate recognition occurs when a light sensor that continually captures video detects motion as a vehicle is driven through a gate. The light sensor detects the vehicle and license plate in the video stream captured by the light sensor. An algorithm associated with the video stream of the light sensor is trained to detect license plates. The light sensor starts executing the recognition algorithm when it detects motion. Recognition of characters in the license plate is based upon an aggregation of several captured video frames in which a license plate is detected.

Abstract: A method and apparatus for a gap-fill in semiconductor devices are provided. The method includes forming a metal seed layer on an exposed surface of the substrate, wherein the substrate has features in the form of trenches or vias formed in a top surface of the substrate, the features having sidewalls and a bottom surface extending between the sidewalls. A gradient oxidation process is performed to oxidize exposed portions of the metal seed layer to form a metal oxide, wherein the gradient oxidation process preferentially oxidizes a field region of the substrate over the bottom surface of the features. An etch back process removes or reduces the oxidized portion of the seed layer. A metal gap-fill process fills or partially fills the features with a gap fill material.

Abstract: A method and related system operations include obtaining a video stream with an image sensor of a camera device, detecting a plurality of target objects by executing a neural network model based on the video stream with a vision processor unit of the camera device. The method also includes generating a plurality of bounding boxes, determining a plurality of character sequences by, for each respective bounding box of the plurality of bounding boxes, performing a set of optical character recognition (OCR) operations to determine a respective character sequence of the plurality of character sequences. The method also includes updating a plurality of tracklets to indicate the plurality of bounding boxes and storing the plurality of tracklets in association with the plurality of character sequences in a memory of the camera device.

Abstract: Embodiments of methods and associated apparatus for filling a feature in a substrate are provided herein. In some embodiments, a method of depositing tungsten in features of a substrate includes: depositing a seed layer consisting essentially of tungsten in the features via a physical vapor deposition (PVD) process; and depositing a bulk layer consisting essentially of tungsten in the features via a chemical vapor deposition (CVD) process to fill the features such that the deposition of the bulk layer is selective to within the features as compared to a field region of the substrate, wherein the CVD process is performed by flowing hydrogen gas (H2) at a first flow rate and a tungsten precursor at a second flow rate, and wherein the first flow rate is less than the second flow rate.

Abstract: Embodiments of the disclosure advantageously provide in situ selectively deposited molybdenum films having reduced resistivity and methods of reducing or eliminating lateral growth of a selectively deposited molybdenum layer. Additional embodiments provide integrated clean and deposition processes which improve the selectivity of in situ selectively deposited molybdenum films on features, such as a via. Further embodiments advantageously provide methods of improving uniformity and selectivity of bottom-up gap fill for vias with improved film properties.

Abstract: Microelectronic packages and methods of fabrication are described. In an embodiment, a redistribution layer spans across multiple components, and includes a region of patterned wiring traces that may mitigate stress in the RDL between the multiple components.

Abstract: Disclosed are a subgraph matching strategy determining method, a subgraph matching method, a counting method, and a device; the matching strategy determining method includes: obtaining a pattern; generating a plurality of restriction sets, for the pattern, each restriction set being capable of eliminating all other automorphisms different from the pattern per se in the automorphisms of the pattern; obtaining a plurality of search order schedules, for the pattern; combining the plurality of restriction sets and the plurality of search order schedules, each combination being referred to as a configuration; using a performance prediction model to predict a computation amount of a subgraph matching algorithm corresponding to each configuration, and determining one or more configurations as a subgraph matching strategy, based on the predicted computation amount.

Abstract: Methods for pre-cleaning substrates having metal and dielectric surfaces are described. The substrate is exposed to a strong reductant to remove contaminants from the metal surface and damage the dielectric surface. The substrate is then exposed to an oxidation process to repair the damage to the dielectric surface and oxidize the metal surface. The substrate is then exposed to a weak reductant to reduce the metal oxide to a pure metal surface without substantially affecting the dielectric surface. Processing tools and computer readable media for practicing the method are also described.

Abstract: Method for selectively oxidizing the dielectric surface of a substrate surface comprising a dielectric surface and a metal surface are discussed. Method for cleaning a substrate surface comprising a dielectric surface and a metal surface are also discussed. The disclosed methods oxidize the dielectric surface and/or clean the substrate surface using a plasma generated from hydrogen gas and oxygen gas. The disclosed method may be performed in a single step without the use of separate competing oxidation and reduction reactions. The disclosed methods may be performed at a constant temperature and/or within a single processing chamber.

Abstract: A computer vision processor of a camera generates hyperzooms for persons or vehicles from image frames captured by the camera. The hyperzooms include a first hyperzoom associated with the persons or vehicles. The computer vision processor tracks traffic patterns of the persons or vehicles while obviating network usage by the camera by predicting positions of the persons or vehicles using a Kalman Filter from the first hyperzoom. The persons or vehicles are detected in the second hyperzoom. The positions of the persons or vehicles are updated based on detecting the persons or vehicles in the second hyperzoom. The first hyperzoom is removed from the camera. Tracks of the persons or vehicles are generated based on the updated positions. The second hyperzoom is removed from the camera. Track metadata is generated from the tracks for storing in a key-value database located on a non-transitory computer-readable storage medium of the camera.