“2021-08-30”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
第138行: 第138行:
 
|Weida Liang
 
|Weida Liang
 
||   
 
||   
*  
+
* Try a two-step training to improve the baseline exemplar encoder
 +
* Collect test data of the method
 +
* Continue another possible method.
 
||
 
||
 
*  
 
*  

2021年8月30日 (一) 06:06的版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Neural PCA experiments on FashionMNIST and kMNIST, link
  • Some variants of NPCA, in terms of sampling scheme, loss function, etc.
  • Some work for thermal paper review
  • TASLP paper response
  • Continue the NPCA and paper review.
Yunqi Cai
  • TASLP paper experiments and response
  • Thermal Speaking project
Lantian Li
  • Prepare multi-modal datasets of CN-Celeb.
  • Monitor cvss 808 and 831.
  • Paper of `Hard trials'
Ying Shi
Haoran Sun
  • emotion recognition on MSP-IMPROV
  • subjective evaluation
Jiao Han
Di Wang
  • Complete cross-channel experiment doc.
  • Data processing for CNC1 and CNC2.
Tiankai Zhi
Chen Chen
  • read paper about SN-net(two branchs DAE)
  • attend graduate freshman lectures
  • run UASR code
  • attend graduate freshman lectures
Jingxin Shen
Pengqi Li
  • Compare MAML and R-MAML on MiniImagenet for Fast Adaptation
  • study of [808]
Qingyang Zhu
Weida Liang
  • Try a two-step training to improve the baseline exemplar encoder
  • Collect test data of the method
  • Continue another possible method.