Patents by Inventor Topojoy BISWAS

Topojoy BISWAS has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20240371162
    Abstract: The disclosed systems and methods provide a novel framework that provides mechanisms for performing cost-effective, accurate and scalable detection and recognition of fine-grained events. The framework functions by training high precision and high recall object/optical character recognition (OCR) models and aligning video frames to text commentaries of the videos (e.g., licensed play-by-play). The disclosed framework operates as a single algorithm that performs multimodal alignments between events/actions within videos and their prescribed text. Thus, the disclosed framework is able to scale to fine-grained action categories across different venues by delving into the key frames and key aspects of a video to identify particular actions performed by particular actors, thereby providing the novelty of fine-granted action detection and recognition.
    Type: Application
    Filed: July 11, 2024
    Publication date: November 7, 2024
    Inventors: Topojoy BISWAS, Avijit SHAH, Deven Santosh SHAH
  • Publication number: 20240296291
    Abstract: The example embodiments are directed toward improvements in document classification. In an embodiment, a method is disclosed comprising generating a set of sentences based on a document; predicting a set of labels for each sentence using a multi-label classifier, the multi-label classifier including a self-attended contextual word embedding backbone layer, a bank of trainable unigram convolutions, a bank of trainable bigram convolutions, and a fully connected layer the multi-label classifier trained using a weakly labeled data set; and labeling the document based on the set of labels. The various embodiments can target multiple use cases such as identifying related entities, trending related entities, creating ephemeral timeline of entities, and others using a single solution. Further, the various embodiments provide a weakly supervised framework to train a model when a labeled golden set does not contain a sufficient number of examples.
    Type: Application
    Filed: May 13, 2024
    Publication date: September 5, 2024
    Inventors: Deven Santosh SHAH, Sukanya MOORTHY, Topojoy BISWAS
  • Patent number: 12056928
    Abstract: The disclosed systems and methods provide a novel framework that provides mechanisms for performing cost-effective, accurate and scalable detection and recognition of fine-grained events. The framework functions by training high precision and high recall object/optical character recognition (OCR) models and aligning video frames to text commentaries of the videos (e.g., licensed play-by-play). The disclosed framework operates as a single algorithm that performs multimodal alignments between events/actions within videos and their prescribed text. Thus, the disclosed framework is able to scale to fine-grained action categories across different venues by delving into the key frames and key aspects of a video to identify particular actions performed by particular actors, thereby providing the novelty of fine-granted action detection and recognition.
    Type: Grant
    Filed: March 24, 2021
    Date of Patent: August 6, 2024
    Assignee: YAHOO ASSETS LLC
    Inventors: Topojoy Biswas, Avijit Shah, Deven Santosh Shah
  • Patent number: 11983502
    Abstract: The example embodiments are directed toward improvements in document classification. In an embodiment, a method is disclosed comprising generating a set of sentences based on a document; predicting a set of labels for each sentence using a multi-label classifier, the multi-label classifier including a self-attended contextual word embedding backbone layer, a bank of trainable unigram convolutions, a bank of trainable bigram convolutions, and a fully connected layer the multi-label classifier trained using a weakly labeled data set; and labeling the document based on the set of labels. The various embodiments can target multiple use cases such as identifying related entities, trending related entities, creating ephemeral timeline of entities, and others using a single solution. Further, the various embodiments provide a weakly supervised framework to train a model when a labeled golden set does not contain a sufficient number of examples.
    Type: Grant
    Filed: November 24, 2021
    Date of Patent: May 14, 2024
    Assignee: YAHOO AD TECH LLC
    Inventors: Deven Santosh Shah, Sukanya Moorthy, Topojoy Biswas
  • Publication number: 20230368531
    Abstract: According to disclosed embodiments, an event detection framework is provided to detect key events or actions on videos. According to some embodiments, a method is provided to detect an event using the event detection framework by retrieving a frame sequence depicting an event, the frame sequence having a plurality of frames; extracting a feature from each frame of the plurality of frames; combining the extracted features to generate an input matrix; applying an event detection model the input matrix to generate an output matrix; and, determining, based on the output matrix, the event depicted by the frame sequence.
    Type: Application
    Filed: May 13, 2022
    Publication date: November 16, 2023
    Inventors: Joao SOARES, Avijit SHAH, Topojoy BISWAS
  • Publication number: 20230206632
    Abstract: The disclosed systems and methods provide a novel framework that enables cost-effective, accurate and scalable detection and recognition of key events in sporting or live events. The framework functions by creating a domain-specific video dataset with frame level annotations (i.e., deep domain datasets) and then training a lightweight camera view classifier to detect camera views for a given video. The disclosed framework uses pre-trained pose estimation and panoptic segmentation models along with geometric rules as labeling functions to define scene types and derive frame level classification training data. According to some embodiments, disclosed frameworks may be used to identify key persons or events, select a thumbnail corresponding to a key person or event, generate personalized highlights to enhance user experience and social media promotions for a team, sport or players, and predict and select the best camera view sequence for automatic highlights generation.
    Type: Application
    Filed: December 23, 2021
    Publication date: June 29, 2023
    Inventors: Deven Santosh SHAH, Avijit SHAH, Topojoy BISWAS, Biren BARODIA
  • Publication number: 20220309279
    Abstract: The disclosed systems and methods provide a novel framework that provides mechanisms for performing cost-effective, accurate and scalable detection and recognition of fine-grained events. The framework functions by training high precision and high recall object/optical character recognition (OCR) models and aligning video frames to text commentaries of the videos (e.g., licensed play-by-play). The disclosed framework operates as a single algorithm that performs multimodal alignments between events/actions within videos and their prescribed text. Thus, the disclosed framework is able to scale to fine-grained action categories across different venues by delving into the key frames and key aspects of a video to identify particular actions performed by particular actors, thereby providing the novelty of fine-granted action detection and recognition.
    Type: Application
    Filed: March 24, 2021
    Publication date: September 29, 2022
    Inventors: Topojoy BISWAS, Avijit SHAH, Deven Santosh SHAH