先週の進捗
今週の木曜日（6月3日）の予備審査会を準備します。
- <学位論文審査願等>(学生用)を改正しました。
- 発表用PPTを作成しました。
- 論文を提出する。
「画像関連」カテゴリーアーカイブ
画像・CG関連
先週の進捗(ZHOU)
Make a analysis about the pose result from the self-supervised depth estimation. But with different evaluation indicators, the results are different. Maybe I make some mistakes.
M１ゼミ
出席：杜、大城、新野、井川
6月２日に、序論発表練習、全員 １０−１２分・一人当たり
新野：マスター研究テーマは学部のテーマの延長、機能追加などを考える
他、TOEIC受験に頑張ること。
先週の進捗(ZHOU)
- About the network architecture of depth prediction, pose estimation and semantic segmentation, I make an analysis. In the future, I plan to build a SLAM system based all the information.
- Paper reading: Towards Better Generalization: Joint Depth-Pose Learning without PoseNet. About my understand of the details, I write a note. All the … Continue Reading ››
先週の進捗(ZHU)
先週の進捗
- Finished the 《学位論文審査願等（学生用)》,and updated to gitlab.
- Did some experiments:
（1） Regarding improving the processing speed, changing the distance comparison method, but the effect is not good.
（2）According to the application in the real scene, considering the occlusion and other complex application scenarios, … Continue Reading ››
先週の進捗(ZHU)
先週の進捗
According to the comments given by the two reviewers, finished the modification of Journal ISAROB paper, and submitted the final manuscript, including a letter to the reviewers so that they would know how I revised the paper.
- Just like the reviewer's comments, environmental changes and occlusion … Continue Reading ››
M２ゼミ
出席：全員
就職関連の確認と研究テーマの決定について話し合った。
先週の進捗(ZHU)
先週の進捗：
- After working during the holidays, the first draft of the doctoral thesis can be said to be basically completed, but many new problems will be gradually found in the process of writing, and experimental functions have always been required perfect, such as the processing speed and occlusion. … Continue Reading ››
近藤の週報(5/6 ~ 5/12)
- 5/6 8:50 ~ 12:00 電気回路
- 5/7 14:00 ~16:30 電磁気
研究
GANを用いてadversarial examples の生成 (https://www.ijcai.org/Proceedings/2018/0543.pdf)
近藤の週報(4/29〜5/5)
- 4/29 14:30〜19:00 電気回路
- 4/30 14:00～ 22:00 電気回路