Patents by Inventor Yi-Hsuan Tsai
Yi-Hsuan Tsai 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).
-
Patent number: 12131422Abstract: A method for achieving high-fidelity novel view synthesis and 3D reconstruction for large-scale scenes is presented. The method includes obtaining images from a video stream received from a plurality of video image capturing devices, grouping the images into different image clusters representing a large-scale 3D scene, training a neural radiance field (NeRF) and an uncertainty multilayer perceptron (MLP) for each of the image clusters to generate a plurality of NeRFs and a plurality of uncertainty MLPs for the large-scale 3D scene, applying a rendering loss and an entropy loss to the plurality of NeRFs, performing uncertainty-based fusion to the plurality of NeRFs to define a fused NeRF, and jointly fine-tuning the plurality of NeRFs and the plurality of uncertainty MLPs, and during inference, applying the fused NeRF for novel view synthesis of the large-scale 3D scene.Type: GrantFiled: October 11, 2022Date of Patent: October 29, 2024Assignee: NEC CorporationInventors: Bingbing Zhuang, Samuel Schulter, Yi-Hsuan Tsai, Buyu Liu, Nanbo Li
-
Publication number: 20240353366Abstract: The electrochemical biosensor strip includes an electrode layer, a spacer, a reagent layer and a cover layer. The electrode layer is disposed on a substrate, and the electrode layer includes a first electrode, a second electrode and a third electrode. The spacer is disposed on the electrode layer, and the spacer includes a first opening, a second opening and a groove which are not communicated with each other. The groove is recessed inwardly from a side of the spacer. The first and second openings are adjacent to the groove. The first opening, the second opening and the groove respectively correspond to and expose the first electrode, the second electrode and the third electrode. The reagent layer is disposed on the first electrode and the second electrode, and the reagent layer is not disposed on the third electrode exposed from the groove. The cover layer is disposed on the spacer.Type: ApplicationFiled: January 18, 2024Publication date: October 24, 2024Inventors: Tsung-Hsuan TSAI, Yi-An CHOU, Chien-Yu YIN, Bo-Jiun SHEN
-
Patent number: 12118036Abstract: Systems and methods of automatically extracting summaries of video content are described herein. A data processing system can access, from a video database, a first video content element including a first plurality of frame. The data processing system can select an intervallic subset of the first plurality of frames of the first video content element. The data processing system can calculate, for each of a plurality of further subsets comprising a predetermined number of frames from the intervallic subset, a score for the further subset. The data processing system can identify, from the plurality of further subsets, a further subset having a highest score. The data processing system can select a portion of the first video content element comprising the frames of the further subset having the highest score. The data processing system can generate a second video content element comprising the selected portion of the first video content element.Type: GrantFiled: June 18, 2021Date of Patent: October 15, 2024Assignee: GOOGLE LLCInventors: Yi Shen, Xiangrong Chen, Min-hsuan Tsai, Yun Shi, Tianpeng Jin, Zheng Sun, Weilong Yang, Jingbin Wang, Carolyn Au, James Futrell
-
Publication number: 20240331862Abstract: The present invention provides a data analytic scheme for screening biomarkers for differential diagnosis of the status of Parkinson's disease, Parkinson's disease with mild cognitive impairment, Parkinson's disease dementia, Alzheimer's disease, and/or multiple system atrophy, the methodology implementing the same and the results of the screening thereof. Biomedical Oriented Logistic Dantzig Selector (BOLD Selector) was developed to identify candidate microRNAs and extracellular vesicle proteins effective at discerning between any two of the above mentioned disease categories from profiling results. The prediction models are finalized by establishing logistic regression formula for each pair of patient group differentiation.Type: ApplicationFiled: March 29, 2024Publication date: October 3, 2024Inventors: Shau-Ping LIN, Ruey-Meei WU, Frederick Kin Hing Phoa, Ming-Che KUO, Yi-Tzang TSAI, Jing-Wen HUANG, Yan-Han LIN, Hsiang-Hsuan LIN WANG, Chia-Lang HSU, Ya-Fang HSU, Pin-Jui KUNG
-
Patent number: 12080100Abstract: A method for employing facial information in unsupervised person re-identification is presented. The method includes extracting, by a body feature extractor, body features from a first data stream, extracting, by a head feature extractor, head features from a second data stream, outputting a body descriptor vector from the body feature extractor, outputting a head descriptor vector from the head feature extractor, and concatenating the body descriptor vector and the head descriptor vector to enable a model to generate a descriptor vector.Type: GrantFiled: November 5, 2021Date of Patent: September 3, 2024Assignee: NEC CorporationInventors: Yumin Suh, Xiang Yu, Yi-Hsuan Tsai, Masoud Faraki, Manmohan Chandraker
-
Patent number: 12045992Abstract: Methods and systems for training a model include combining data from multiple datasets, the datasets having different respective label spaces. Relationships between labels in the different label spaces are identified. A unified neural network model is trained, using the combined data and the identified relationships to generate a unified model, with a class relational binary cross-entropy loss.Type: GrantFiled: November 5, 2021Date of Patent: July 23, 2024Assignee: NEC CorporationInventors: Yi-Hsuan Tsai, Masoud Faraki, Yumin Suh, Sparsh Garg, Manmohan Chandraker, Dongwan Kim
-
Patent number: 11977602Abstract: A method for training a model for face recognition is provided. The method forward trains a training batch of samples to form a face recognition model w(t), and calculates sample weights for the batch. The method obtains a training batch gradient with respect to model weights thereof and updates, using the gradient, the model w(t) to a face recognition model what(t). The method forwards a validation batch of samples to the face recognition model what(t). The method obtains a validation batch gradient, and updates, using the validation batch gradient and what(t), a sample-level importance weight of samples in the training batch to obtain an updated sample-level importance weight. The method obtains a training batch upgraded gradient based on the updated sample-level importance weight of the training batch samples, and updates, using the upgraded gradient, the model w(t) to a trained model w(t+1) corresponding to a next iteration.Type: GrantFiled: November 8, 2021Date of Patent: May 7, 2024Assignee: NEC CorporationInventors: Xiang Yu, Yi-Hsuan Tsai, Masoud Faraki, Ramin Moslemi, Manmohan Chandraker, Chang Liu
-
Patent number: 11947626Abstract: A method for improving face recognition from unseen domains by learning semantically meaningful representations is presented. The method includes obtaining face images with associated identities from a plurality of datasets, randomly selecting two datasets of the plurality of datasets to train a model, sampling batch face images and their corresponding labels, sampling triplet samples including one anchor face image, a sample face image from a same identity, and a sample face image from a different identity than that of the one anchor face image, performing a forward pass by using the samples of the selected two datasets, finding representations of the face images by using a backbone convolutional neural network (CNN), generating covariances from the representations of the face images and the backbone CNN, the covariances made in different spaces by using positive pairs and negative pairs, and employing the covariances to compute a cross-domain similarity loss function.Type: GrantFiled: November 5, 2021Date of Patent: April 2, 2024Assignee: NEC CorporationInventors: Masoud Faraki, Xiang Yu, Yi-Hsuan Tsai, Yumin Suh, Manmohan Chandraker
-
Publication number: 20240037186Abstract: Video methods and systems include extracting features of a first modality and a second modality from a labeled first training dataset in a first domain and an unlabeled second training dataset in a second domain. A video analysis model is trained using contrastive learning on the extracted features, including optimization of a loss function that includes a cross-domain regularization part and a cross-modality regularization part.Type: ApplicationFiled: October 11, 2023Publication date: February 1, 2024Inventors: Yi-Hsuan Tsai, Xiang Yu, Bingbing Zhuang, Manmohan Chandraker, Donghyun Kim
-
Publication number: 20240037187Abstract: Video methods and systems include extracting features of a first modality and a second modality from a labeled first training dataset in a first domain and an unlabeled second training dataset in a second domain. A video analysis model is trained using contrastive learning on the extracted features, including optimization of a loss function that includes a cross-domain regularization part and a cross-modality regularization part.Type: ApplicationFiled: October 11, 2023Publication date: February 1, 2024Inventors: Yi-Hsuan Tsai, Xiang Yu, Bingbing Zhuang, Manmohan Chandraker, Donghyun Kim
-
Publication number: 20240038683Abstract: A method of manufacturing a semiconductor device is provided. The method includes placing a package substrate on a carrier substrate, forming a frame on the package substrate, and affixing an active side of a semiconductor die on the package substrate. The semiconductor die together with the frame and the package substrate form a cavity between the semiconductor die and the package substrate. At least a portion of the semiconductor die and the package substrate are encapsulated with an encapsulant. The frame is configured to prevent the encapsulant from entering the cavity.Type: ApplicationFiled: July 28, 2022Publication date: February 1, 2024Inventors: Tzu Ya Fang, Yen-Chih Lin, Jian Nian Chen, Moly Lee, Yi Xiu Xie, Vanessa Wyn Jean Tan, Yao Jung Chang, Yi-Hsuan Tsai, Xiu Hong Shen, Kuan Lin Huang
-
Publication number: 20240037188Abstract: Video methods and systems include extracting features of a first modality and a second modality from a labeled first training dataset in a first domain and an unlabeled second training dataset in a second domain. A video analysis model is trained using contrastive learning on the extracted features, including optimization of a loss function that includes a cross-domain regularization part and a cross-modality regularization part.Type: ApplicationFiled: October 11, 2023Publication date: February 1, 2024Inventors: Yi-Hsuan Tsai, Xiang Yu, Bingbing Zhuang, Manmohan Chandraker, Donghyun Kim
-
Publication number: 20230401776Abstract: A face model editing method adapted to a face model editing system having a modeling platform and an editing platform is provided. The modeling platform has a plurality of face feature animation objects and a plurality of object parameters thereof. The face model editing method includes: receiving an object selection instruction by using the editing platform, and accessing the object parameter of the face feature animation object from the modeling platform according to the object selection instruction; receiving an adjusting instruction by using the editing platform, and adjusting the accessed object parameter; transmitting, by the editing platform, the adjusted object parameter to the modeling platform to update the object parameters; and generating, by the modeling platform, a three-dimensional face model by using the updated object parameters in combination with the face feature animation objects, and transmitting the three-dimensional face model to the editing platform for demonstration.Type: ApplicationFiled: December 20, 2022Publication date: December 14, 2023Inventors: Kuan-Ling CHEN, Yi-Hsuan TSAI, Jo-Hsuan HUANG, Chieh-Han CHUANG, Jun-Ting CHEN, Shih-Hua MA
-
Publication number: 20230401775Abstract: A face model building method is provided. The face model building method includes: obtaining a plurality of facial feature animation objects and a plurality of object parameters respectively corresponding to the facial feature animation objects, where the facial feature animation objects include a plurality of two-dimensional facial feature animation objects and at least one three-dimensional facial feature animation object; and integrating the facial feature animation objects according to the object parameters to generate a three-dimensional face model. A face model building system is further provided.Type: ApplicationFiled: December 20, 2022Publication date: December 14, 2023Inventors: Yi-Hsuan TSAI, Kuan-Ling CHEN, Jo-Hsuan HUANG, Jun-Ting CHEN, Shih-Hua MA, Chieh-Han CHUANG
-
Publication number: 20230326146Abstract: An augmented reality implementing method applied to a server, which includes a plurality of augmented reality objects and a plurality of setting records corresponding to the augmented reality objects respectively is provided. Firstly, the server receives an augmented reality request from a mobile device, where the augmented reality request is related to a target device. Then, the server is communicated with the target device to access current information. Then, the server determines the current information corresponds to which one of the setting records, and selects one of the augmented reality objects based on the determined setting record as a virtual object provided to the mobile device.Type: ApplicationFiled: October 4, 2022Publication date: October 12, 2023Inventors: Kuo-Chung CHIU, Hsuan-Wu WEI, Yen-Ting LIU, Shang-Chih LIANG, Shih-Hua MA, Yi-Hsuan TSAI, Jun-Ting CHEN, Kuan-Ling CHEN
-
Patent number: 11710346Abstract: Methods and systems for training a neural network include generate an image of a mask. A copy of an image is generated from an original set of training data. The copy is altered to add the image of a mask to a face detected within the copy. An augmented set of training data is generated that includes the original set of training data and the altered copy. A neural network model is trained to recognize masked faces using the augmented set of training data.Type: GrantFiled: May 26, 2021Date of Patent: July 25, 2023Inventors: Manmohan Chandraker, Ting Wang, Xiang Xu, Francesco Pittaluga, Gaurav Sharma, Yi-Hsuan Tsai, Masoud Faraki, Yuheng Chen, Yue Tian, Ming-Fang Huang, Jian Fang
-
Publication number: 20230179719Abstract: A scanner is provided and includes a load bearing element, a scan assembly, a transparent plate and a casing. The load bearing element includes a support element and a base. The support element is disposed on the base and surrounds the base. The scan assembly is configured to perform a scan operation and is disposed on the base. The transparent plate is disposed on the support element and is configured to bear an object. The casing includes a first casing part and a second casing part. The second casing part includes a bottom plate and at least one cylinder. The at least one cylinder is disposed on the bottom plate. The load bearing element is disposed on the at least one cylinder, and is located between the first casing part and the second casing part. A first buffer space is formed between the base and the bottom plate.Type: ApplicationFiled: December 23, 2021Publication date: June 8, 2023Inventors: Wei-Shen Chen, Yi-Hsuan Tsai
-
Patent number: 11659112Abstract: A scanner is provided and includes a load bearing element, a scan assembly, a transparent plate and a casing. The load bearing element includes a support element and a base. The support element is disposed on the base and surrounds the base. The scan assembly is configured to perform a scan operation and is disposed on the base. The transparent plate is disposed on the support element and is configured to bear an object. The casing includes a first casing part and a second casing part. The second casing part includes a bottom plate and at least one cylinder. The at least one cylinder is disposed on the bottom plate. The load bearing element is disposed on the at least one cylinder, and is located between the first casing part and the second casing part. A first buffer space is formed between the base and the bottom plate.Type: GrantFiled: December 23, 2021Date of Patent: May 23, 2023Assignee: TECO IMAGE SYSTEMS CO., LTD.Inventors: Wei-Shen Chen, Yi-Hsuan Tsai
-
Publication number: 20230154104Abstract: A method for achieving high-fidelity novel view synthesis and 3D reconstruction for large-scale scenes is presented. The method includes obtaining images from a video stream received from a plurality of video image capturing devices, grouping the images into different image clusters representing a large-scale 3D scene, training a neural radiance field (NeRF) and an uncertainty multilayer perceptron (MLP) for each of the image clusters to generate a plurality of NeRFs and a plurality of uncertainty MLPs for the large-scale 3D scene, applying a rendering loss and an entropy loss to the plurality of NeRFs, performing uncertainty-based fusion to the plurality of NeRFs to define a fused NeRF, and jointly fine-tuning the plurality of NeRFs and the plurality of uncertainty MLPs, and during inference, applying the fused NeRF for novel view synthesis of the large-scale 3D scene.Type: ApplicationFiled: October 11, 2022Publication date: May 18, 2023Inventors: Bingbing Zhuang, Samuel Schulter, Yi-Hsuan Tsai, Buyu Liu, Nanbo Li
-
Publication number: 20230153572Abstract: A computer-implemented method for model training is provided. The method includes receiving, by a hardware processor, sets of images, each set corresponding to a respective task. The method further includes training, by the hardware processor, a task-based neural network classifier having a center and a covariance matrix for each of a plurality of classes in a last layer of the task-based neural network classifier and a plurality of convolutional layers preceding the last layer, by using a similarity between an image feature of a last convolutional layer from among the plurality of convolutional layers and the center and the covariance matrix for a given one of the plurality of classes, the similarity minimizing an impact of a data model forgetting problem.Type: ApplicationFiled: October 21, 2022Publication date: May 18, 2023Inventors: Masoud Faraki, Yi-Hsuan Tsai, Xiang Yu, Samuel Schulter, Yumin Suh, Christian Simon