-
公开(公告)号：US11348336B2
公开(公告)日：2022-05-31
申请号：US15931075
申请日：2020-05-13
发明人： Quanfu Fan , Richard Chen , Sijia Liu , Hildegard Kuehne
摘要： Systems and methods for performing video understanding and analysis. Sets of feature maps for high resolution images and low resolution images in a time sequence of images are combined into combined sets of feature maps each having N feature maps. A time sequence of temporally aggregated sets of feature maps is created for each combined set of feature maps by: selecting a selected combined set of feature maps corresponding to an image at time “t” in the time sequence of images; applying, by channel-wise multiplication, a feature map weighting vector to a number of combined sets of feature maps that are temporally adjacent to the selected combined set of feature maps; and summing elements of the number of combined set of feature maps into a temporally aggregated set of feature maps. The time sequence of temporally aggregated sets of feature maps is processed to perform video understanding processing.
-
公开(公告)号：US11257222B2
公开(公告)日：2022-02-22
申请号：US16292847
申请日：2019-03-05
发明人： Chuang Gan , Yang Zhang , Sijia Liu , Dakuo Wang
摘要： Embodiments of the present invention are directed to a computer-implemented method for action localization. A non-limiting example of the computer-implemented method includes receiving, by a processor, a video and segmenting, by the processor, the video into a set of video segments. The computer-implemented method classifies, by the processor, each video segment into a class and calculates, by the processor, importance scores for each video segment of a class within the set of video segments. The computer-implemented method determines, by the processor, a winning video segment of the class within the set of video segments based on the importance scores for each video segment within the class, stores, by the processor, the winning video segment from the set of video segments, and removes the winning video segment from the set of video segments.
-
23.发明授权公开(公告)号：US11227215B2
公开(公告)日：2022-01-18
申请号：US16296897
申请日：2019-03-08
发明人： Sijia Liu , Quanfu Fan , Chuang Gan , Dakuo Wang
摘要： Mechanisms are provided for generating an adversarial perturbation attack sensitivity (APAS) visualization. The mechanisms receive a natural input dataset and a corresponding adversarial attack input dataset, where the adversarial attack input dataset comprises perturbations intended to cause a misclassification by a computer model. The mechanisms determine a sensitivity measure of the computer model to the perturbations in the adversarial attack input dataset based on a processing of the natural input dataset and corresponding adversarial attack input dataset by the computer model. The mechanisms generate a classification activation map (CAM) for the computer model based on results of the processing and a sensitivity overlay based on the sensitivity measure. The sensitivity overlay graphically represents different classifications of perturbation sensitivities. The mechanisms apply the sensitivity overlay to the CAM to generate and output a graphical visualization output of the computer model sensitivity to perturbations of adversarial attacks.
-
公开(公告)号：US20210035599A1
公开(公告)日：2021-02-04
申请号：US16526990
申请日：2019-07-30
发明人： Yang Zhang , Chuang Gan , Sijia Liu , Dakuo Wang
IPC分类号： G10L25/57 , G10L25/30 , H04N21/845 , H04N21/81 , G06N3/04
摘要： A computing device receives a video feed. The video feed is divided into a sequence of video segments. For each video segment, visual features of the video segment are extracted. A predicted spectrogram is generated based on the extracted visual features. A synthetic audio waveform is generated from the predicted spectrogram. All synthetic audio waveforms of the video feed are concatenated to generate a synthetic soundtrack that is synchronized with the video feed.
-
公开(公告)号：US20200279155A1
公开(公告)日：2020-09-03
申请号：US16288975
申请日：2019-02-28
发明人： Sijia Liu , Pin-Yu Chen , Chuang Gan , Lisa Amini
摘要： A black box optimization method, system, and computer program product include implementing an average gradient estimator using a forward difference of function values at multiple random directions, performing variance reduction via gradient blending with an output of the average gradient estimator using a control variate, and performing binary quantization of a result of the variance reduction.
-
26.发明申请公开(公告)号：US20200242252A1
公开(公告)日：2020-07-30
申请号：US16256267
申请日：2019-01-24
发明人： Pin-Yu Chen , Sijia Liu , Akhilan Boopathy , Tsui-Wei Weng , Luca Daniel
摘要： A certification method, system, and computer program product include certifying an adversarial robustness of a convolutional neural network by deriving an analytic solution for a neural network output using an efficient upper bound and an efficient lower bound on an activation function and applying the analytic solution in computing a certified robustness.
-
公开(公告)号：US20200242250A1
公开(公告)日：2020-07-30
申请号：US16256107
申请日：2019-01-24
发明人： Pin-Yu Chen , Sijia Liu , Lingfei Wu , Chia-Yu Chen
摘要： An adversarial robustness testing method, system, and computer program product include testing a robustness of a black-box system under different access settings via an accelerator.
-
公开(公告)号：US20240045974A1
公开(公告)日：2024-02-08
申请号：US18382107
申请日：2023-10-20
发明人： Pin-Yu Chen , Sijia Liu , Lingfei Wu , Chia-Yu Chen
IPC分类号： G06F21/57 , G06N3/04 , G06N3/08 , G06V10/764 , G06V10/82
CPC分类号： G06F21/577 , G06N3/04 , G06N3/08 , G06V10/764 , G06V10/82 , G06F2221/034
摘要： An adversarial robustness testing method, system, and computer program product include testing, via an accelerator, a robustness of a black-box system under different access settings, where the testing includes tearing down the robustness testing to a subtask of a predetermined size.
-
公开(公告)号：US11763084B2
公开(公告)日：2023-09-19
申请号：US16989882
申请日：2020-08-10
发明人： Dakuo Wang , Arunima Chaudhary , Chuang Gan , Mo Yu , Qian Pan , Sijia Liu , Daniel Karl I. Weidele , Abel Valente
IPC分类号： G06F40/289 , G06N20/00 , G06N5/04
CPC分类号： G06F40/289 , G06N5/04 , G06N20/00
摘要： A method comprises receiving a new data set; identifying at least one prior data set of a plurality of prior data sets that matches the new data set; generating a natural language data science problem statement for the new data set based on information associated with the at least prior one data set that matches the new data set; outputting the generated natural language data science problem statement for user verification; and in response to receiving user input verifying the natural language generated data science problem statement, generating one or more AutoAI configuration settings for the new data set based on one or more AutoAI configuration settings associated with the at least one prior data set that matches the new data set.
-
公开(公告)号：US20230004754A1
公开(公告)日：2023-01-05
申请号：US17363043
申请日：2021-06-30
发明人： Quanfu Fan , Sijia Liu , GAOYUAN ZHANG , Kaidi Xu
摘要： Adversarial patches can be inserted into sample pictures by an adversarial image generator to realistically depict adversarial images. The adversarial image generator can be utilized to train an adversarial patch generator by inserting generated patches into sample pictures, and submitting the resulting adversarial images to object detection models. This way, the adversarial patch generator can be trained to generate patches capable of defeating object detection models.
-
-
-
-
-
-
-
-
-
搜索结果
37 条记录 (耗时 0.028 秒)
