公开(公告)号：US12033342B2

公开(公告)日：2024-07-09

申请号：US17203645

申请日：2021-03-16

申请人： Huan Liu ,  Zhixiang Chi ,  Yuanhao Yu ,  Yang Wang ,  Jin Tang

发明人： Huan Liu ,  Zhixiang Chi ,  Yuanhao Yu ,  Yang Wang ,  Jin Tang

IPC分类号： G06N3/0455 ,  G06F18/214 ,  G06N3/08 ,  G06T7/50 ,  G06T7/579 ,  G06V10/44

CPC分类号： G06T7/579 ,  G06F18/214 ,  G06N3/08 ,  G06V10/44 ,  G06T2207/10028 ,  G06T2207/20081

摘要： Systems, methods and computer-readable medium for predicting a depth for a video frame are disclosed. An example method may include steps of: receiving a plurality of training data, each comprising a set of consecutive video frames and a depth representation of a subsequent video frame to the consecutive video frames; receiving a pre-trained neural network model fθ having a plurality of weights θ; while the pre-trained neural network model fθ has not converged: computing a plurality of second weights θi′, based on each set of consecutive video frames, and updating the plurality of weights θ, based on the plurality of training data and the plurality of second weights θi′; receiving a plurality of new consecutive video frames with consecutive timestamps; and predicting a depth representation of video frame immediately subsequent to the new consecutive video frames based on the updated plurality of weights θ.

公开(公告)号：US20220156891A1

公开(公告)日：2022-05-19

申请号：US17098605

申请日：2020-11-16

申请人： Zhixiang Chi ,  Yang Wang ,  Yuanhao Yu ,  Jin Tang

发明人： Zhixiang Chi ,  Yang Wang ,  Yuanhao Yu ,  Jin Tang

IPC分类号： G06T5/00 ,  G06N3/08

摘要： Methods and systems for image deblurring are described. The weights of a deblurring network are first trained by meta-training the deblurring network on both a primary deblurring task and an auxiliary reconstruction task. Application-time training of the deblurring network is then performed, using an application-time blurry input image, to obtain values of application-time trained weights. Application-time training includes performing the auxiliary reconstruction task on the application-time blurry input image, and updating the weights of the deblurring network based on an auxiliary loss computed from the auxiliary reconstruction task. A deblurred output image is generated from the application-time blurry input image, using the application-time trained weights in the deblurring network.

公开(公告)号：US11741579B2

公开(公告)日：2023-08-29

申请号：US17098605

申请日：2020-11-16

申请人： Zhixiang Chi ,  Yang Wang ,  Yuanhao Yu ,  Jin Tang

发明人： Zhixiang Chi ,  Yang Wang ,  Yuanhao Yu ,  Jin Tang

IPC分类号： G06T5/00 ,  G06N3/08

CPC分类号： G06T5/003 ,  G06N3/08 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20201

摘要： Methods and systems for image deblurring are described. The weights of a deblurring network are first trained by meta-training the deblurring network on both a primary deblurring task and an auxiliary reconstruction task. Application-time training of the deblurring network is then performed, using an application-time blurry input image, to obtain values of application-time trained weights. Application-time training includes performing the auxiliary reconstruction task on the application-time blurry input image, and updating the weights of the deblurring network based on an auxiliary loss computed from the auxiliary reconstruction task. A deblurred output image is generated from the application-time blurry input image, using the application-time trained weights in the deblurring network.

公开(公告)号：US11729395B2

公开(公告)日：2023-08-15

申请号：US17535840

申请日：2021-11-26

申请人： Sheral Sweta Kumar ,  Amartya Mukherjee ,  Seel Nimeshkumar Patel ,  Rui Xiang Chai ,  Wentao Liu ,  Yuanhao Yu ,  Yang Wang ,  Jin Tang

发明人： Sheral Sweta Kumar ,  Amartya Mukherjee ,  Seel Nimeshkumar Patel ,  Rui Xiang Chai ,  Wentao Liu ,  Yuanhao Yu ,  Yang Wang ,  Jin Tang

IPC分类号： H04N19/44 ,  H04N19/513 ,  H04N19/146 ,  H04N19/137 ,  H04N19/176 ,  H04N19/186 ,  H04N19/85

CPC分类号： H04N19/146 ,  H04N19/137 ,  H04N19/176 ,  H04N19/186 ,  H04N19/85

摘要： Devices and methods for extracting motion vector data during decoding compressed of video data are described. At a video decoder, an encoded video data for a frame of video from an input buffer is obtained. The encoded video data is decoded to obtain decoded image data for a decoded frame, where the decoding includes extracting corresponding motion vector data for the decoded frame. The decoded image data is stored in a temporary storage indexed with a given index, and the corresponding motion vector data is stored in a same or different temporary storage indexed with the given index. An output buffer indexed with the given index is filled with the decoded image data and the corresponding motion vector data stored in the respective temporary storage indexed with the given index.

公开(公告)号：US12062252B2

公开(公告)日：2024-08-13

申请号：US17538516

申请日：2021-11-30

申请人： Irina Kezele ,  Mostafa Shahabinejad ,  Seyed shahabeddin Nabavi ,  Wentao Liu ,  Yuanhao Yu ,  Rui Xiang Chai ,  Jin Tang ,  Yang Wang

发明人： Irina Kezele ,  Mostafa Shahabinejad ,  Seyed shahabeddin Nabavi ,  Wentao Liu ,  Yuanhao Yu ,  Rui Xiang Chai ,  Jin Tang ,  Yang Wang

IPC分类号： G06V40/20 ,  G06N5/04 ,  G06V10/62 ,  G06V10/778 ,  G06V10/94 ,  G06V30/19

CPC分类号： G06V40/20 ,  G06N5/04 ,  G06V10/62 ,  G06V10/778 ,  G06V10/94 ,  G06V30/1912 ,  G06V30/19127

摘要： Methods, devices and computer-readable media for processing a compressed video to perform an inference task are disclosed. Processing the compressed video may include selecting a subset of frame encodings of the compressed video, or zero or more modalities (RGB, motion vectors, residuals) of a frame encoding, for further processing to perform the inference task. Pre-existing motion vector and/or residual information in frame encodings of the compressed video are leveraged to adaptively and efficiently perform the inference task. In some embodiments, the inference task is an action recognition task, such as a human action recognition task.

公开(公告)号：US11778223B2

公开(公告)日：2023-10-03

申请号：US17406845

申请日：2021-08-19

申请人： Wentao Liu ,  Yuanhao Yu ,  Yang Wang ,  Juwei Lu ,  Xiaolin Wu ,  Jin Tang

发明人： Wentao Liu ,  Yuanhao Yu ,  Yang Wang ,  Juwei Lu ,  Xiaolin Wu ,  Jin Tang

IPC分类号： H04N19/59 ,  H04N19/51 ,  H04N19/184 ,  H04N19/136

CPC分类号： H04N19/51 ,  H04N19/136 ,  H04N19/184

摘要： A method, device and computer-readable medium for generating a super-resolution version of a compressed video stream. By leveraging the motion information and residual information in compressed video streams, described examples are able to skip the time-consuming motion-estimation step for most frames and make the most use of the SR results of key frames. A key frame SR module generates SR versions of I-frames and other key frames of a compressed video stream using techniques similar to existing multi-frame approaches to VSR. A non-key frame SR module generates SR version of the non-key inter frames between these key frames by making use of motion information and residual information used to encode the inter frames in the compressed video stream.

公开(公告)号：US09705502B2

公开(公告)日：2017-07-11

申请号：US14565395

申请日：2014-12-09

申请人： Yang Wang ,  Jie Jin ,  Jianzhou Wu

发明人： Yang Wang ,  Jie Jin ,  Jianzhou Wu

IPC分类号： H01H35/00 ,  H01H83/00 ,  H02H3/00 ,  H01H47/00 ,  H03K19/0175 ,  H03K5/125

CPC分类号： H03K19/017509 ,  H02J7/0036 ,  H02J9/061 ,  H02J50/10 ,  H02J2007/0062 ,  H03K5/125

摘要： An electrical system can selectively power a load via a USB connection or via another power source, such as a wireless power transfer path. An integrated switch controller determines whether to power the load via the USB connection or the other power sources and controls two external transistors via a single I/O pin connection to implement that determination. The switch controller determines the greater of two voltages: a voltage associated with the USB connection and a voltage associated with the other power source. The switch controller also determines whether there is a valid USB connection. The switch controller circuitry that controls the two external transistors is powered at the greater voltage to ensure that the external transistors are appropriately and securely turned on or off.

公开(公告)号：US20160126727A1

公开(公告)日：2016-05-05

申请号：US14677921

申请日：2015-04-02

申请人： ZHENGXIANG WANG ,  Yang Wang

发明人： ZHENGXIANG WANG ,  Yang Wang

IPC分类号： H02H9/04

CPC分类号： H02H9/046 ,  H01L23/60 ,  H01L27/0259 ,  H01L27/0266 ,  H02H9/041

摘要： A voltage supply for providing a clamped voltage to a circuit element to be protected against electrical overstress (EOS) has a reference voltage module and a voltage clamp module. The reference voltage module has a first field-effect transistor (FET) whose source and drain are connected in series between a programmable reference current source and a first resistor across a power supply. The gate of the first FET is connected to its drain to provide a reference voltage defined by the reference current flowing in the first resistor. The voltage clamp module has a second FET whose gate receives the reference voltage and whose source is connected to provide to the protected circuit element the clamped voltage whose variation is limited by the reference voltage.

摘要翻译： 用于向要被保护以防止电过压（EOS）的电路元件提供钳位电压的电压源具有参考电压模块和电压钳模块。 参考电压模块具有第一场效应晶体管（FET），其源极和漏极串联在可编程参考电流源和跨电源的第一电阻之间。 第一FET的栅极连接到其漏极，以提供由在第一电阻器中流动的参考电流限定的参考电压。 电压钳模块具有第二FET，其栅极接收参考电压，并且其源极连接以向受保护的电路元件提供变化受参考电压限制的钳位电压。

公开(公告)号：US20150107660A1

公开(公告)日：2015-04-23

申请号：US14129428

申请日：2012-06-27

申请人： Krzysztof J. Kempa ,  Zhifeng Ren ,  Yang Wang

发明人： Krzysztof J. Kempa ,  Zhifeng Ren ,  Yang Wang

IPC分类号： H01L31/0216 ,  H01L31/18 ,  H01L31/0224

CPC分类号： H01L31/02168 ,  H01L31/022425 ,  H01L31/022466 ,  H01L31/02366 ,  H01L31/1804 ,  H01L31/1884 ,  Y02E10/50

摘要： Super-transparent electrodes for photovoltaic applications are disclosed. In some embodiments, a photovoltaic cell (1) includes an absorber material (16) capable of absorbing solar energy and converting the absorbed energy into electrical current; a window electrode (10) disposed on a light-entry surface of the absorber material (16), the window electrode (10) comprising an anti-reflective coating (ARC) layer (12) and a metallic layer (13), and a rear electrode (18) disposed on a surface of the absorber material (16) in opposing relation to the window electrode (10), wherein the rear electrode (18) in combination with the window electrode (10) are configured to collect electrical current generated in the absorber material (16).

摘要翻译： 公开了用于光伏应用的超透明电极。 在一些实施例中，光伏电池（1）包括能吸收太阳能并将吸收的能量转换成电流的吸收材料（16） 设置在吸收体材料（16）的光入射面上的窗口电极（10），所述窗口电极（10）包括抗反射涂层（ARC）层（12）和金属层（13），以及 所述后电极（18）与所述窗电极（10）相对设置在所述吸收体材料（16）的表面上，其中与所述窗电极（10）组合的所述后电极（18）被构造成收集产生的电流 在吸收材料（16）中。

公开(公告)号：US20150106415A1

公开(公告)日：2015-04-16

申请号：US14461445

申请日：2014-08-18

申请人： Wangsheng Mei ,  Yang Wang ,  Jianzhou Wu ,  Yan Xiao

发明人： Wangsheng Mei ,  Yang Wang ,  Jianzhou Wu ,  Yan Xiao

IPC分类号： G06F7/58 ,  H03K3/03

CPC分类号： G06F7/588 ,  H03K3/0315 ,  H03K3/84

摘要： A true random number generator (RNG) has one or more oscillators and an output register for storing a random number output. Each of the oscillators is activated, successively, in a free-running oscillation phase, and a capture phase during which the oscillator is quiescent. The output register latches during the capture phase of each oscillator an end state of that oscillator at or close to the end of its oscillation phase. The random number output is derived from the latched end states.

摘要翻译： 真正的随机数生成器（RNG）具有一个或多个振荡器和用于存储随机数输出的输出寄存器。 每个振荡器依次被激活，处于自由运行的振荡阶段以及振荡器静止期间的捕获阶段。 输出寄存器在每个振荡器的捕获阶段锁存该振荡器的结束状态或接近其振荡阶段的结束。 随机数输出是从锁存结束状态得出的。