Adobe, Inc.

Saayan Mitra

Viswanathan Swaminathan

Somdeb Sarkhel

Ryan A Rossi

Ritwik Sinha

Xiang Chen

Akshay Malhotra

Shivakumar Vaithyanathan

Anup Bandigadi Rao

Tung Mai

Haoliang Wang

Thomas Greger

Han Guo

Alok Kothari

Jiatong Xie

Antonio Cuevas

Kelly Quinn Nicholes

Nathan Ng

Teng Xu

William Brandon George

Eunyee Koh

Gang Wu

Handong Zhao

Trevor Paulsen

Tong Yu

Niranjan Shivanand Kumbi

Kshitiz Garg

Dwight O Rodgers

Sheng Li

David Arbour

Ali Aminian

Uttaran Bhattacharya

Trisha Mittal

Jason Boyer

Victor Soares Bursztyn

Sreekanth Reddy

Kenneth George Russell

Lakshmi Shivalingaiah

Shuo Yang

Manas Garg

Swapneel Mehta

Xueyu Mao

Yifu Zheng

Alan Lai

Alexandru Ionut Hodorogea

Saurabh Tripathy

Qi Lou

Julio Alvarez Martinez, Jr

A method, apparatus, non-transitory computer readable medium, and system for document retrieval include obtaining a query and a document. A prompt generator generates a prompt for a reasoning model based on the query and the document. The reasoning model generates a reasoning result based on the prompt. In some cases, the reasoning result indicates that the document answers the query. A machine learning model provides the document in response to the query based on the reasoning result.

In-context and semantic-aware ensemble model for document retrieval

In some embodiments, techniques for identifying email events generated by bot activity are provided. For example, a process may involve applying bot detection patterns to identify bot activity among email response events.

Bot activity detection for email tracking

Systems and methods for dynamic user profile management are provided. One aspect of the systems and methods includes receiving, by a lookup component, a request for a user profile; computing, by a profile component, a time-to-live (TTL) refresh value for the user profile based on a lookup history of the user profile; updating, by the profile component, a TTL value of the user profile based on the request and the TTL refresh value; storing, by the profile component, the user profile and the updated TTL value in the edge database; and removing, by the edge database, the user profile from the edge database based on the updated TTL value.

Dynamic user profile management

Various disclosed embodiments are directed to using one or more algorithms or models to select a suitable or optimal variation, among multiple variations, of a given content item based on feedback. Such feedback guides the algorithm or model to arrive at suitable variation result such that the variation result is produced as the output for consumption by users. Further, various embodiments resolve tedious manual user input requirements and reduce computing resource consumption, among other things, as described in more detail below.

Media content enhancement based on user feedback of multiple variations

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating automatic suggestions to effectively modify the organization of an ingested data collection without destruction of the underlying raw data. In particular, in one or more embodiments, the disclosed systems utilize multiple machine learning models in sequence to determine likelihoods that the organizational structure of an ingested data collection should be modified in various ways. In response to generating these likelihoods, the disclosed systems generate corresponding automatic suggestions to modify the organization of the ingested data collection. In response to a detected selection of one or more of the automatic suggestions, the disclosed systems read data out of the ingested data collection in accordance with the selected automatic suggestions to effectively modify the organization of the ingested data collection.

Generating and executing automatic suggestions to modify data of ingested data collections without additional data ingestion

Techniques are disclosed for real-time bidding (e.g., for dynamic online content placement) using an optimized final bid. The final bid is determined based on a predicted clearing price and an initial bid. The initial bid represents a value to a prospective content provider, and may be computed based on campaign information. The predicted clearing price is a predicted amount paid, and may be predicted using a model trained using historical winning bids data. The clearing price may be predicted using a quantile regression model, where the quantile can be selected to control bid aggressiveness. In some cases, the quantile is determined based on pacing in an overall campaign. Once the initial bid and the predicted clearing price are calculated, the final bid is computed based on the initial bid and the predicted clearing price.

Artificial intelligence techniques for bid optimization used for generating dynamic online content

Systems and methods for dynamic user profile projection are provided. One or more aspects of the systems and methods includes computing, by a prediction component, a predicted number of lookups for a future time period based on a lookup history of a user profile using a lookup prediction model; comparing, by the prediction component, the predicted number of lookups to a lookup threshold; and transmitting, by a projection component, the user profile to an edge server based on the comparison.

Dynamic user profile projection

Techniques for recommending hashtags, including trending hashtags, are disclosed. An example method includes accessing a graph. The graph includes video nodes representing videos, historical hashtag nodes representing historical hashtags, and edges indicating associations among the video nodes and the historical hashtag nodes. A trending hashtag is identified. An edge is added to the graph between a historical hashtag node representing a historical hashtag and a trending hashtag node representing the trending hashtag, based on a semantic similarity between the historical hashtag and the trending hashtag. A new video node representing a new video is added to the video nodes of the graph. A graph neural network (GNN) is applied to the graph, and the GNN predicts a new edge between the trending hashtag node and the new video node. The trending hashtag is recommended for the new video based on prediction of the new edge.

Open-domain trending hashtag recommendations

Embodiments of the present disclosure provide systems, methods, and computer storage media for optimizing computing resources generally associated with cloud-based media services. Instead of decoding digital assets on-premises to stream to a remote client device, an encoded asset can be streamed to the remote client device. A codebook employable for decoding the encoded asset can be embedded into the stream transmitted to the remote client device, so that the remote client device can extract the embedded codebook, and employ the extracted codebook to decode the encoded asset locally. In this way, not only are processing resources associated with on-premises decoding eliminated, but on-premises storage of codebooks can be significantly reduced, while expensive bandwidth is freed up by virtue of transmitting a smaller quantity of data from the cloud to the remote client device.

Embedding codebooks for resource optimization

Residual vectors are compressed in a lossless compression scheme suitable for cloud DVR video content applications. Thus, a cloud DVR service provider can take many copies of the same file stored in the cloud and save storage space by compressing those copies while still maintaining their status as distinct copies, one per user. Vector quantization is used for compressing already-compressed video streams (e.g., MPEG streams). As vector quantization is a lossy compression scheme, the residual vector has to be stored to regenerate the original video stream at the decoding (playback) node. Entropy coding schemes like Arithmetic or Huffman coding can be used to compress the residual vectors. Additional strategies can be implemented to further optimize this residual compression. In some embodiments, the techniques operate to provide a 25-50% improvement in compression. Storage space is thus more efficiently used and video transmission may be faster in some cases.

Residual entropy compression for cloud-based video applications

Embodiments of the present disclosure provide systems, methods, and computer storage media for mitigating latencies associated with the encoding of digital assets. Instead of waiting for codebook generation to complete in order to encode a digital asset for storage, embodiments described herein describe a shifting codebook generation and employment technique that significantly mitigates any latencies typically associated with encoding schemes. As a digital asset is received, a single codebook is trained based on each portion of the digital asset, or in some instances along with each portion of other digital assets being received. The single codebook is employed to encode subsequent portion(s) of the digital asset as it is received. The process continues until an end of the digital asset is reached or another command to terminate the encoding process is received. To encode an initial portion of the digital asset, a bootstrap codebook can be employed.

Latency mitigation for encoding data

This disclosure relates to methods, non-transitory computer readable media, and systems that can initially train a machine-learning-logo classifier using synthetic training images and incrementally apply the machine-learning-logo classifier to identify logo images to replace the synthetic training images as training data. By incrementally applying the machine-learning-logo classifier to determine one or both of logo scores and positions for logos within candidate logo images, the disclosed systems can select logo images and corresponding annotations indicating positions for ground-truth logos. In some embodiments, the disclosed systems can further augment the iterative training of a machine-learning-logo classifier to include user curation and removal of incorrectly detected logos from candidate images, thereby avoiding the risk of model drift across training iterations.

Selecting logo images using machine-learning-logo classifiers

Techniques are disclosed for training of factorization machines (FMs) using a streaming mode alternating least squares (ALS) optimization. A methodology implementing the techniques according to an embodiment includes receiving a datapoint that includes a feature vector and an associated target value. The feature vector includes user identification, subject matter identification, and a context. The target value identifies an opinion of the user relative to the subject matter. The method further includes applying an FM to the feature vector to generate an estimate of the target value, and updating parameters of the FM for training of the FM. The parameter update is based on application of a streaming mode ALS optimization to: the datapoint; the estimate of the target value; and to an updated summation of intermediate calculated terms generated by application of the streaming mode ALS optimization to previously received datapoints associated with prior parameter updates of the FM.

Online training and update of factorization machines using alternating least squares optimization

Growing community of inventors

San Jose, CA, United States of America

Saayan Mitra