Patents

101 patents: 44 issued, 52 filed, 5 in preparation

1. Rule-based dialog state tracking (Issued 8/2018)

2. Ambient Audio Generation Based on Visual Information (Issued 6/2019)

3. Identification of Reading Order Text Segments with a Probabilistic Language Model (Issued 8/2019)

4. Multiple Turn Conversational Task Assistance (Issued 10/2019)

5. Natural Language Image Editing Annotation Framework (Issued 3/2020)

6. Domain-Specific Speech Recognizers in a Digital Medium Environment (Issued 3/2020)

7. Multi-modal image ranking using neural networks (Issued 5/2020)

8. Automated workflows for identification of reading order from text segments using probabilistic language models (Issued 7/2020)

9. Collecting Multimodal Image Editing Requests (Issued 9/2020)

10. Content Presentation Based on a Multi-Task Neural Network (Issued 10/2020)

11. Generating Modified Digital Images Utilizing a Multimodal Selection Model based on Verbal and Gesture Input (Issued 10/2020)

12. Music Driven Human Dancing Video Synthesis (Issued 11/2020)

13. Generating Dialogue Responses In End-to-End Dialogue Systems Utilizing A context-dependent additive recurrent neural network (Issued 12/2020)

14. Generating Ground Truth Annotations Corresponding To Digital Image Editing Dialogues For Training State Tracking Models (Issued 8/2021)

15. Generating Dialogue Responses Utilizing an Independent Context Dependent additive recurrent neural network (Issued 9/2021)

16. Utilizing a gated self-attention memory network model for predicting a candidate answer match to a query (Issued 9/2021)

17. Answer selection using a compare-aggregate model with language model and condensed similarity information from latent clustering (Issued 9/2021)

18. Abstractive Summarization of Long Documents using Deep Learning (Issued 11/2021)

19. Generating Descriptions of Image Relationships (Issued 12/2021)

20. Utilizing bi-directional recurrent encoders with multi-hop attention for speech emotion recognition (Issued 12/2021)

21. A System for Deep Abstractive Summarization of Long and Structured Documents (Issued 1/2022, AU)

22. Generating contextual tags for digital content (Issued 1/2022)

23. Generating Digital Annotations for Evaluating and Training Automatic Electronic Document Annotation Models (Issued 1/2022)

24. Utilizing a graph neural network to identify supporting text phrases and generate digital query responses (Issued 3/2022)

25. Model-based Semantic Text Searching (Issued 9/2022, AU)

26. Dialog System Training using a Simulated User System (Issued 10/2022)

27. Utilizing A Joint-Learning Self-Distillation Framework For Improving Text Sequential Labeling Machine-Learning Models (Issued 12/2022)

28. Customizable Speech Recognition System (Issued 12/2022)

29. Learning with limited supervision for question-answering with light-weight Markov models (Issued 1/2023)

30. Generating hyper-parameters for machine learning models using modified bayesian optimization based on accuracy and training efficiency (Issued 1/2023)

31. Utilizing logical-form dialogue generation for multi-turn construction of paired natural language queries and query-language representations (Issued 1/2023)

32. An interpretable label-attentive encoder-decoder parser (Issued 1/2023)

33. Model-Based Semantic Text Searching (Issued 1/2023)

34. Performing Global Image Editing Using Editing Operations Determined From Natural Language Requests (Issued 1/2023)

35. Generating Modified Digital Images Utilizing A Dispersed Multimodal Selection Model (Issued 2/2023)

36. Methods and Systems for Determining Characteristics of a Dialog Between a Computer and a User (Issued 3/2023)

37. Training of Neural Network Based Natural Language Processing Models Using Dense Knowledge Distillation (Issued 5/2023)

38. Digital Content Interaction Prediction and Training that Addresses Imbalanced Classes (Issued 6/2023)

39. Reader-retriever approach for question answering (Issued 7/2023)

40. Propagating multi-term contextual tags for digital content (Issued 8/2023)

41. Probabilistic Language Models For Identifying Sequential Reading Order Of Discontinuous Text Segments (Issued 9/2023)

42. Generating and Utilizing Classification and Query-specific models to generate digital responses to queries from client device (Issued 10/2023)

43. Multi-module and multi-task machine learning system based on an ensemble of datasets (Issued 4/2024)

44. Decompositional Learning for Color Attribute Prediction (Issued 4/2024)

45. Automatic discovery of high-performance features for customer lifetime value optimization via low-variance random projection (Filed 11/2014)

46. Abstractive Summarization of Long Documents using Deep Learning (Filed 11/2018, CN)

47. Abstractive Summarization of Long Documents using Deep Learning (Filed 11/2018, DE)

48. Abstractive Summarization of Long Documents using Deep Learning (Filed 11/2018, GB)

49. Artificial Intelligence Techniques For Performing Image Editing Operations Inferred From Natural Language Requests (Filed 8/2020)

50. Scene Graph Modification Based on Natural Language Commands (Filed 11/2020)

51. Model-based Semantic Text Searching (Filed 1/2021, GB)

52. Model-based Semantic Text Searching (Filed 1/2021, CN)

53. Model-based Semantic Text Searching (Filed 2/2021, DE)

54. Semantic Reasoning for Tabular Question Answering (Filed 5/2021)

55. Instantiating Machine-learning Models At On-demand Cloud-based Systems With User-defined Datasets (Filed 5/2021)

56. Topical Vector-Quantized Variational Autoencoders for Extractive Summarization of Video Transcripts (Filed 6/2021)

57. Performing Global Image Editing Using Editing Operations Determined From Natural Language Requests (Filed 6/2021, PROV)

58. Modification of Scene Graphs Based on Natural Language Commands (Filed 9/2021, DE)

59. Modification of Scene Graphs Based on Natural Language Commands (Filed 9/2021, AU)

60. Modification of Scene Graphs Based on Natural Language Commands (Filed 8/2021, CN)

61. Intent Detection (Filed 11/2021) 

62. Image Captioning (Filed 11/2021)

63. Bi-directional  Recurrent Encoders with Multi-hop Attention for Speech Emotion Recognition (Filed 11/2021 US-CON1)

64. Video recommender system by knowledge based multi-modal graph neural networks (Filed 1/2022)

65. System and methods for Keyphrase Extraction (Filed 2/2022)

66. Generating synthetic code-switched data for training language model (Filed 2/2022)

67. Systems and methods for Image Processing using Natural Language (Filed 2/2022) 

68. Method and System for Training Machine Learning Models for Medical Image Classification (Filed 2/2022, VN)

69. System for understanding natural language (Filed 2/2022, VN)

70. Cross-lingual Meta-Transfer Learning Adaptation to Natural Language Understanding (Filed 3/2022)

71. Multimodal Unsupervised Video Temporal Segmentation for Summarization (Filed 5/2022)

72. Multitask Machine-Learning Model Training and Training Data Augmentation (Filed 6/2022)

73. Systems and Methods for Coreference Resolution (Filed 6/2022)

74. Virtual Knowledge Graph Construction for Zero-Shot Domain-Specific Document Retrieval (Filed 6/2022)

75. Long-Tail Color Prediction (Filed 7/2022)

76. Multimodal Intent Discovery System (Filed 7/2022)

77. Radiology Report Editing Method and System (Filed 9/2022)

78. Method and System for Training a Machine Learning Model for Medical Image Classification (Filed 10/2022)

79. Model-based Semantic Text Searching (Filed 12/2022)

80. Methods and Systems for Determining Characteristics of a Dialog between a Computer and a User (Filed 2/2023) 

81. Rendering and anchoring instructional data in augmented reality with context awareness (Filed 3/2023)

82. Perturbation Robust Metric for Multi-Lingual Image Captioning (Filed 3/2023)

83. Segment identification from Long Videos (Filed 4/2023)

84. Modifying Digital Images using Combinations of Direct Interactions with the Digital Images and Context-Informing Speech Input (Filed 5/2023)

85. Multimodal Video Summarization (Filed 6/2023)

86. IMPROVED TRAINING METHODS FOR LANGUAGE MODELS USING DATA GENERATION AND REINFORCEMENT LEARNING (Filed 7/2023)

87. MULTILINGUAL SEMANTIC SEARCH UTILIZING META-DISTILLATION LEARNING (Filed 8/2023)

88. UTILIZING MACHINE LEARNING MODELS TO GENERATE ASPECT-BASED TRANSCRIPT SUMMARIES (Filed 8/2023)

89. Generating 3D Models from a single image (Filed 9/2023)

90. Identifying Speaker Names in Transcripts Utilizing Language Models (Filed 12/2023)

91. Modifying Digital Images using Combinations of Direct Interactions with the Digital Images and Context-Informing Speech Input (Filed 1/2024, CN)

92. Generating Answers to Contextual Queries within a Closed Domain (Filed 2/2024)

93. Modifying Digital Images using Combinations of Direct Interactions with the Digital Images and Context-Informing Speech Input (Filed 3/2024, AU)

94. Modifying Digital Images using Combinations of Direct Interactions with the Digital Images and Context-Informing Speech Input (Filed 3/2024, GB)

95.  Selective Object Level Undo (Filed 3/2024)

96. Generating Synthetic Digital Images Utilizing a Text-To-Image Generation Neural Network with Localized Constraints (Filed 3/2024)

97. Training-free Image Editing with Multi-modal Signals (In preparation)

98. Constrative Multilingual Language and Image Pretraining and Finetuning (In preparation)

99. Photoshop in Words: Text-based Interactive Editing in Photoshop (In preparation)

100. Scaling Up Video Summarization (In preparation)

101. Neural Video Topic Segmentation (In preparation)