论文修改建议(WangLR 20211223细节问题)

  1. Self-attention Two-Stage Progressive Seismic Data Enhancement
    → \rightarrow
    之前不是去噪吗,怎么题目感觉突然大变化?

  2. basis function to adaptively represent the data [39–42].
    → \rightarrow
    to represent the data adaptively. 会不会好一点

  3. for complex learning tasks. such as image processing
    → \rightarrow
    逗号,或者S大写哦

  4. sparse denoising autoencoder (SDAE)
    sparse denoising autoencoder (SDAE)
    Deep Noise Reduction Autoencoder (DDAE)
    Supervised Attention Module (SAM)
    → \rightarrow
    首字母要不要大写,可以自查一下文中其他地方这种情况

  5. (SAM), which is at the end of the first phase.
    → \rightarrow
    phase->stage会不会好一点

  6. It re-weight the features
    → \rightarrow
    It re-weights the features

  7. Finally, we exemplified the specific algorithm flow.
    → \rightarrow
    这里的时态是否正确(不确定)

  8. caused by pooling. Xdown∈RC×H/2×W/2.
    → \rightarrow
    Xdown∈RC×H/2×W/2. 不是一个句子,不能单独放吧

  9. (18) 前缺少标点

  10. One field data (field-data-1) is selected from Stratton survey
    The other field data (field-data-2) uses
    which contains
    The test data is selected from the additional three synthetic data.
    → \rightarrow
    data单数还是复数,若复数 are use contain are

  11. a lot of effective signals
    Without penalty terms, there are a lot of effective signals
    And the proposed method recovers more weak signals
    → \rightarrow
    signal是否可数,前文 but you should not lose too much signal
    (若确定,请检查全文的signal)

  12. The best and second best
    → \rightarrow
    一句中两个best,次好可否换种表达(不确定)

  13. And the proposed method recovers more weak signals than DnCNN (black arrow), and there is less signal leakage.
    → \rightarrow
    less 是后面接不可数名词,若signal认为是不可数的,前边就错了。
    (这里同前边一样,要统一signal形式)

  14. The results show that the penalty item may reduce the signal-to-noise ratio, but it can better protect the signal.
    → \rightarrow
    but很突然,逻辑不通

  15. Therefore, it can effectively suppress excessive denoising and further protect the effective signal.
    → \rightarrow
    effectively effective是否重复,把其中一个词换一种表达

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值