REINFORCED LIST DECODING
    11.
    发明申请
    REINFORCED LIST DECODING 审中-公开
    强化列表解码

    公开(公告)号:WO2018013268A1

    公开(公告)日:2018-01-18

    申请号:PCT/US2017/036911

    申请日:2017-06-10

    Abstract: Certain aspects of the present disclosure relate to techniques and apparatus for increasing decoding performance and/or reducing decoding complexity. A transmitter may divide data of a codeword into two or more sections and then calculate redundancy check information (e.g., a cyclic redundancy check or a parity check) for each section and attach the redundancy check information to the codeword. A decoder of a receiver may decode each section of the codeword and check the decoding against the corresponding redundancy check information. If decoding of a section fails, the decoder may use information regarding section(s) that the decoder successfully decoded in re-attempting to decode the section(s) that failed decoding. In addition, the decoder may use a different technique to decode the section(s) that failed decoding. If the decoder is still unsuccessful in decoding the section(s), then the receiver may request retransmission of the failed section(s) or of the entire codeword.

    Abstract translation: 本公开的某些方面涉及用于提高解码性能和/或降低解码复杂度的技术和装置。 发射机可以将码字的数据分成两个或更多个部分,然后为每个部分计算冗余校验信息(例如,循环冗余校验或奇偶校验),并将冗余校验信息附加到码字。 接收器的解码器可以对码字的每个部分进行解码并且针对相应的冗余校验信息来检查解码。 如果部分的解码失败,则解码器可以使用关于解码器成功解码以重新尝试解码解码失败的部分的部分的信息。 另外,解码器可以使用不同的技术来解码解码失败的部分。 如果解码器仍然不成功解码该部分,则接收器可以请求重传失败部分或整个码字。

    ENHANCED LIST DECODING OF TAIL BITING CONVOLUTIONAL CODES
    12.
    发明申请
    ENHANCED LIST DECODING OF TAIL BITING CONVOLUTIONAL CODES 审中-公开
    增强列表卷积卷积码的列表解码

    公开(公告)号:WO2017196451A1

    公开(公告)日:2017-11-16

    申请号:PCT/US2017/023875

    申请日:2017-03-23

    Abstract: Certain aspects of the present disclosure relate to techniques and apparatus for enhanced decoding, for example, by providing a multi-phase tail biting convolutional code (TBCC) decoding algorithm. An exemplary method generally includes obtaining, via a wireless medium, a codeword encoded with a TBCC encoding scheme, generating metrics for candidate paths through trellis stages of a decoder, propagating information from at least one of the trellis stages to a later trellis stage, while generating the metrics, selecting a set of the candidate paths based on the propagated information, and decoding the encoded codeword by evaluating the selected set of candidate paths based, at least in part, on the generated metrics. Other aspects, embodiments, and features are claimed and described.

    Abstract translation: 本公开的某些方面涉及用于例如通过提供多相咬尾卷积码(TBCC)解码算法来增强解码的技术和装置。 示例性方法一般包括经由无线介质获得用TBCC编码方案编码的码字,通过解码器的网格阶段生成用于候选路径的度量,将信息从至少一个网格阶段传播到后来的网格阶段,而 生成度量,基于传播的信息来选择一组候选路径,以及通过至少部分地基于所生成的度量来评估所选择的候选路径集合来对经编码的码字进行解码。 要求和描述其他方面,实施例和特征。

    DOMAIN ADAPTATION FOR WIRELESS SENSING
    13.
    发明申请

    公开(公告)号:WO2023049601A1

    公开(公告)日:2023-03-30

    申请号:PCT/US2022/075514

    申请日:2022-08-26

    Abstract: Certain aspects of the present disclosure provide techniques for domain adaptation. An input tensor comprising channel state information (CSI) for a wireless signal is determined, where each channel in the input tensor corresponds to a respective degree of freedom (DoF) in the wireless signal. A domain-adapted tensor is generated by processing the input tensor using a domain-adaptation network comprising, for each respective DoF in the wireless signal, a respective convolution path. The domain-adapted tensor is provided to a neural network trained for position estimation.

    ELASTIC BOTTLENECK ARCHITECTURES FOR VARIABLE CONVOLUTION OPERATIONS

    公开(公告)号:WO2022020386A1

    公开(公告)日:2022-01-27

    申请号:PCT/US2021/042424

    申请日:2021-07-20

    Abstract: In one aspect of the present disclosure, a method includes: determining a number of loops for a convolution layer of an elastic bottleneck block; for each loop of the number of loops: loading a loop-specific set of convolution weights; performing a convolution operation using the loop-specific set of convolution-weights; and storing loop-specific convolution results in a local memory; and determining an output of the convolution layer based on a summation of loop-specific convolution results associated with each loop of the number of loops.

    EFFICIENT INFERENCING WITH FAST POINTWISE CONVOLUTION

    公开(公告)号:WO2021055364A1

    公开(公告)日:2021-03-25

    申请号:PCT/US2020/050896

    申请日:2020-09-15

    Abstract: Embodiments described herein relate to a method, comprising: receiving input data at a convolutional neural network (CNN) model; generating a factorized computation network comprising a plurality of connections between a first layer of the CNN model and a second layer of the CNN model, wherein: the factorized computation network comprises N inputs, the factorized computation network comprises M outputs, and the factorized computation network comprises at least one path from every input of the N inputs to every output of the M outputs; setting a connection weight for a plurality of connections in the factorized computation network to 1 so that a weight density for the factorized computation network is

    PBCH SIGNAL DESIGN AND EFFICIENT CONTINUOUS MONITORING AND POLAR DECODING

    公开(公告)号:WO2018208682A1

    公开(公告)日:2018-11-15

    申请号:PCT/US2018/031414

    申请日:2018-05-07

    Abstract: Wireless communications systems and methods are introduced. A wireless communication device may arrange a first encoded information block including a first sub-block having a first bit location and a second sub-block having a second bit location. The second bit location is after the first bit location. The wireless communication device may also position the first location earlier in a decoding order of a receiving second wireless communication than the second bit location. The wireless communication device may transmit the first and second sub-blocks as an encoded information block to the second wireless communication device.

    CODING TO IMPROVE TRANSMISSION AND RECEPTION PROCESSING TIME
    17.
    发明申请
    CODING TO IMPROVE TRANSMISSION AND RECEPTION PROCESSING TIME 审中-公开
    编码以改进传输和接收处理时间

    公开(公告)号:WO2018034761A1

    公开(公告)日:2018-02-22

    申请号:PCT/US2017/042419

    申请日:2017-07-17

    Abstract: Methods, systems, and devices for wireless communication are described. The method, systems, and devices may include receiving a plurality of sets of input bits associated with respective transmission symbol periods at an encoder of a transmitting device, the plurality of sets of input bits associated with a single input vector to be encoded into a single codeword. The encoder may process the plurality of sets of input bits to generate a plurality of sets of output bits associated with respective transmission symbol periods, and output a first of the plurality of sets of output bits associated with a first of the plurality of sets of input bits prior receiving a second of the plurality of sets of input bits, the second of the plurality of sets of input bits being received at the encoder subsequent to the first of the plurality of sets of input bits.

    Abstract translation: 描述了用于无线通信的方法,系统和设备。 该方法,系统和设备可以包括:在发射设备的编码器处接收与各个发射符号周期相关联的多组输入比特,与输入比特相关联的多组输入比特被编码为单个 码字。 编码器可以处理多组输入比特以生成与各个传输符号周期相关联的多组输出比特,并且输出与多组输入位中的第一组相关联的多组输出位中的第一组 在接收多组输入比特中的第二组输入比特之前,多组输入比特中的第二组输入比特在编码器接收到多组输入比特中的第一组输入比特之后在编码器处被接收。

    TAILLESS CONVOLUTIONAL CODES
    18.
    发明申请
    TAILLESS CONVOLUTIONAL CODES 审中-公开
    无限卷积代码

    公开(公告)号:WO2017218221A1

    公开(公告)日:2017-12-21

    申请号:PCT/US2017/035858

    申请日:2017-06-03

    Abstract: Certain aspects of the present disclosure relate to techniques and apparatus for increasing decoding performance and/or reducing decoding complexity. An exemplary method generally includes receiving, via a wireless medium, a codeword encoded using a tailless convolutional code (TLCC) with a known start state, evaluating a set of decoding candidate paths through a trellis decoder that originate at the known start state of the TLCC, performing, for each of a plurality of the decoding candidate paths, a back trace from a respective end state to the known start state, and selecting one of the decoding candidate paths based, at least in part, on path metrics generated while performing the back trace. A TLCC is characterized by being encoded without trellis termination/a tail sequence resulting in an unknown end state.

    Abstract translation: 本公开的某些方面涉及用于提高解码性能和/或降低解码复杂度的技术和装置。 示例性方法一般包括经由无线介质接收使用具有已知开始状态的无尾卷积码(TLCC)编码的码字,评估通过网格解码器的解码候选路径集合,该网格解码器起源于TLCC的已知开始状态 针对多个解码候选路径中的每一个执行从相应结束状态到已知开始状态的回溯;以及至少部分地基于在执行所述解码候选路径时生成的路径量度来选择所述解码候选路径之一 回溯。 TLCC的特征是编码时没有网格终止/尾部序列导致未知的结束状态。

    SUBFRAME STRUCTURE WITH EMBEDDED CONTROL SIGNALING
    19.
    发明申请
    SUBFRAME STRUCTURE WITH EMBEDDED CONTROL SIGNALING 审中-公开
    具有嵌入式控制信号的子框架结构

    公开(公告)号:WO2016148947A1

    公开(公告)日:2016-09-22

    申请号:PCT/US2016/021014

    申请日:2016-03-04

    Abstract: An apparatus may utilize an air interface to transmit and/or receive a subframe having a data portion and a control channel that is at least partly embedded within the data portion. The control channel may include one or more pilot tones. The control channel may include an override indicator. The override indicator may indicate that data previously scheduled for transmission in the subframe is overridden by other data having a higher priority. The override indicator may indicate a puncturing of resource elements in the data portion of the subframe to include other data having a priority higher than data previously scheduled for transmission in the subframe. The control channel may include a modulation indicator when the subframe is included in a multi-user multiple-input multiple-output (MU-MIMO) transmission. The modulation indicator may indicate information corresponding to a modulation of another apparatus that is included in the MU-MIMO transmission.

    Abstract translation: 装置可以利用空中接口来发送和/或接收具有至少部分地嵌入数据部分内的数据部分和控制信道的子帧。 控制信道可以包括一个或多个导频音调。 控制通道可以包括超控指示器。 覆盖指示符可以指示预先在子帧中传输的数据被具有较高优先级的其他数据覆盖。 覆盖指示符可以指示子帧的数据部分中的资源元素的删截,以包括具有比先前调度用于子帧中的传输的数据的优先级的其他数据。 当子帧被包括在多用户多输入多输出(MU-MIMO)传输中时,控制信道可以包括调制指示符。 调制指示符可以指示与包括在MU-MIMO传输中的另一装置的调制相对应的信息。

    SPARSE OPTICAL FLOW ESTIMATION
    20.
    发明申请

    公开(公告)号:WO2022072199A1

    公开(公告)日:2022-04-07

    申请号:PCT/US2021/051582

    申请日:2021-09-22

    Abstract: Systems and techniques are described herein for performing optical flow estimation between one or more frames. For example, a process can include determining a subset of pixels of at least one of a first frame and a second frame, and generating a mask indicating the subset of pixels. The process can include determining, based on the mask, one or more features associated with the subset of pixels of at least the first frame and the second frame. The process can include determining optical flow vectors between the subset of pixels of the first frame and corresponding pixels of a second frame. The process can include generating an optical flow map for the second frame using the optical flow vectors.

Patent Agency Ranking