-
公开(公告)号：US12198397B2
公开(公告)日：2025-01-14
申请号：US17586284
申请日：2022-01-27
Applicant: NEC Laboratories America, Inc.
Inventor： Asim Kadav , Farley Lai , Hans Peter Graf , Yi Huang
Abstract: A computer-implemented method is provided for action localization. The method includes converting one or more video frames into person keypoints and object keypoints. The method further includes embedding position, timestamp, instance, and type information with the person keypoints and object keypoints to obtain keypoint embeddings. The method also includes predicting, by a hierarchical transformer encoder using the keypoint embeddings, human actions and bounding box information of when and where the human actions occur in the one or more video frames.
-
公开(公告)号：US12131489B2
公开(公告)日：2024-10-29
申请号：US17741735
申请日：2022-05-11
Applicant: NEC Laboratories America, Inc.
Inventor： Farley Lai , Asim Kadav , Likitha Lakshminarayanan
CPC classification number: G06T7/292 , G06T7/223 , G06T7/248 , G06V20/52 , G06T2200/24 , G06T2207/10016 , G06T2207/20081 , G06T2207/30196 , G06T2207/30232
Abstract: A surveillance system is provided. The surveillance system is configured for (i) detecting and tracking persons locally for each camera input video stream using the common area anchor boxes and assigning each detected ones of the persons a local track id, (ii) associating a same person in overlapping camera views to a global track id, and collecting associated track boxes as the same person moves in different camera views over time using a priority queue and the local track id and the global track id, (iii) performing track data collection to derive a spatial transformation through matched track box spatial features of a same person over time for scene coverage and (iv) learning a multi-camera tracker given visual features from matched track boxes of distinct people across cameras based on the derived spatial transformation.
-
公开(公告)号：US20230148017A1
公开(公告)日：2023-05-11
申请号：US17960370
申请日：2022-10-05
Applicant: NEC Laboratories America, Inc.
Inventor： Asim Kadav , Farley Lai , Hans Peter Graf , Honglu Zhou
IPC: G06V20/40 , G06V40/10 , G06V10/77 , G06V10/774
CPC classification number: G06V20/41 , G06V10/774 , G06V10/7715 , G06V20/46 , G06V20/49 , G06V40/10
Abstract: A method for compositional reasoning of group activity in videos with keypoint-only modality is presented. The method includes obtaining video frames from a video stream received from a plurality of video image capturing devices, extracting keypoints all of persons detected in the video frames to define keypoint data, tokenizing the keypoint data with time and segment information, clustering groups of keypoint persons in the video frames and passing the clustering groups through multi-scale prediction, and performing a prediction to provide a group activity prediction of a scene in the video frames.
-
公开(公告)号：US11356334B2
公开(公告)日：2022-06-07
申请号：US15980243
申请日：2018-05-15
Applicant: NEC Laboratories America, Inc.
Inventor： Asim Kadav , Erik Kruus
Abstract: A method is provided for sparse communication in a parallel machine learning environment. The method includes determining a fixed communication cost for a sparse graph to be computed. The sparse graph is (i) determined from a communication graph that includes all the machines in a target cluster of the environment, and (ii) represents a communication network for the target cluster having (a) an overall spectral gap greater than or equal to a minimum threshold, and (b) certain information dispersal properties such that an intermediate output from a given node disperses to all other nodes of the sparse graph in lowest number of time steps given other possible node connections. The method further includes computing the sparse graph, based on the communication graph and the fixed communication cost. The method also includes initiating a propagation of the intermediate output in the parallel machine learning environment using a topology of the sparse graph.
-
公开(公告)号：US10474951B2
公开(公告)日：2019-11-12
申请号：US15271589
申请日：2016-09-21
Applicant: NEC Laboratories America, Inc.
Inventor： Renqiang Min , Huahua Wang , Asim Kadav
Abstract: Methods and systems for training a neural network include sampling multiple local sub-networks from a global neural network. The local sub-networks include a subset of neurons from each layer of the global neural network. The plurality of local sub-networks are trained at respective local processing devices to produce trained local parameters. The trained local parameters from each local sub-network are averaged to produce trained global parameters.
-
Patent Agency Ranking
公开(公告)号：US20180060240A1
公开(公告)日：2018-03-01
申请号：US15678889
申请日：2017-08-16
Applicant: NEC Laboratories America, Inc.
Inventor： Asim Kadav , Farley Lai
IPC: G06F12/0875 , G06K9/00 , G06K9/66 , G06N99/00 , G06N3/02
CPC classification number: G06N3/084 , G06F12/0875 , G06F2212/455 , G06K9/00255 , G06K9/00288 , G06K9/00986 , G06K9/66 , G06N3/02 , G06N3/063 , G06N20/00 , G06T1/20 , H04L41/16 , H04L67/2842
Abstract: A face recognition system and method for face recognition are provided. The face recognition system includes a camera for capturing an input image of a face of a person to be recognized. The face recognition system further includes a cache. The face recognition system further includes a set of one or more processors configured to (i) improve a utilization of the cache by the one or more processors during multiple training stages of a neural network configured to perform face recognition, by performing a stage-wise mini-batch process on a set of samples used for the multiple training stages, and (ii) recognize the person by applying the neural network to the input image during a recognition stage. The stage-wise mini-batch process waits for each of the multiple training stages to complete using a system wait primitive to improve the utilization of the cache.
-
公开(公告)号：US20170337467A1
公开(公告)日：2017-11-23
申请号：US15590666
申请日：2017-05-09
Applicant: NEC Laboratories America, Inc.
Inventor： Asim Kadav , Igor Durdanovic , Hans Peter Graf , Hao Li
CPC classification number: G06N3/082 , G06F17/153 , G06F17/17 , G06K9/00771 , G06K9/4628 , G06K9/6228 , G06K9/627 , G06K9/6296 , G06K9/66 , G06K2009/00738 , G06N3/0427 , G06N3/0454 , G06N3/0481 , G06N5/045 , G08B13/00 , G08B29/186 , H03H2222/04
Abstract: Security systems and methods for detecting intrusion events include one or more sensors configured to monitor an environment. A pruned convolutional neural network (CNN) is configured process information from the one or more sensors to classify events in the monitored environment. CNN filters having the smallest summed weights have been pruned from the pruned CNN. An alert module is configured to detect an intrusion event in the monitored environment based on event classifications. A control module is configured to perform a security action based on the detection of an intrusion event.
-
公开(公告)号：US11741712B2
公开(公告)日：2023-08-29
申请号：US17463757
申请日：2021-09-01
Applicant: NEC Laboratories America, Inc.
Inventor： Asim Kadav , Farley Lai , Hans Peter Graf , Alexandru Niculescu-Mizil , Renqiang Min , Honglu Zhou
IPC: G06V20/40 , G06T7/73 , G06T7/246 , G06F18/213 , G06N3/045
CPC classification number: G06V20/41 , G06F18/213 , G06N3/045 , G06T7/246 , G06T7/73 , G06V20/46 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06V2201/07
Abstract: A method for using a multi-hop reasoning framework to perform multi-step compositional long-term reasoning is presented. The method includes extracting feature maps and frame-level representations from a video stream by using a convolutional neural network (CNN), performing object representation learning and detection, linking objects through time via tracking to generate object tracks and image feature tracks, feeding the object tracks and the image feature tracks to a multi-hop transformer that hops over frames in the video stream while concurrently attending to one or more of the objects in the video stream until the multi-hop transformer arrives at a correct answer, and employing video representation learning and recognition from the objects and image context to locate a target object within the video stream.
-
公开(公告)号：US20230086023A1
公开(公告)日：2023-03-23
申请号：US17940599
申请日：2022-09-08
Applicant: NEC Laboratories America, Inc.
Inventor： Farley Lai , Asim Kadav , Cheng-En Wu
IPC: G06V20/40 , G06V10/771
Abstract: A method for model training and deployment includes training, by a processor, a model to learn video representations with a self-supervised contrastive loss by performing progressive training in phases with an incremental number of positive instances from one or more video sequences, resetting the learning rate schedule in each of the phases, and inheriting model weights from a checkpoint from a previous training phase. The method further includes updating the trained model with the self-supervised contrastive loss given multiple positive instances obtained from Cascade K-Nearest Neighbor mining of the one or more video sequences by extracting features in different modalities to compute similarities between the one or more video sequences and selecting a top-k similar instances with features in different modalities. The method also includes fine-tuning the trained model for a downstream task. The method additionally includes deploying the trained model for a target application inference for the downstream task.
-
公开(公告)号：US20220237884A1
公开(公告)日：2022-07-28
申请号：US17586284
申请日：2022-01-27
Applicant: NEC Laboratories America, Inc.
Inventor： Asim Kadav , Farley Lai , Hans Peter Graf , Yi Huang
Abstract: A computer-implemented method is provided for action localization. The method includes converting one or more video frames into person keypoints and object keypoints. The method further includes embedding position, timestamp, instance, and type information with the person keypoints and object keypoints to obtain keypoint embeddings. The method also includes predicting, by a hierarchical transformer encoder using the keypoint embeddings, human actions and bounding box information of when and where the human actions occur in the one or more video frames.
-
-
-
-
-
-
-
-
-
Search Results
58
records
(took 0.04 seconds)
