All times are in Alaska local time (AKDT/UTC−08:00)
MLR-APPL-IVSMR-1: Machine learning for image and video sensing, modeling and representation 1 |
Interactive Q&A Time: Tuesday, September 21, 13:30 - 15:00 |
Session Chair: Arman Zharmagambetov, University of California |
MLR-APPL-IVSMR-1.1: A SIMPLE, EFFECTIVE WAY TO IMPROVE NEURAL NET CLASSIFICATION: ENSEMBLING UNIT ACTIVATIONS WITH A SPARSE OBLIQUE DECISION TREE |
Arman Zharmagambetov; University of California, Merced |
Miguel Á. Carreira-Perpiñán; University of California, Merced |
MLR-APPL-IVSMR-1.2: ADAPTIVE SIGNAL VARIANCES: CNN INITIALIZATION THROUGH MODERN ARCHITECTURES |
Takahiko Henmi; Gunma University |
Esmeraldo Ronnie Rey Zara; Gunma University |
Yoshihiro Hirohashi; Individual |
Tsuyoshi Kato; Gunma University |
MLR-APPL-IVSMR-1.3: SPARSE AND STRUCTURED VISUAL ATTENTION |
Pedro Henrique Martins; Instituto de Telecomunicações |
Vlad Niculae; IvI, University of Amsterdam |
Zita Marinho; Institute of Systems and Robotics / Priberam Labs |
André F. T. Martins; Instituto de Telecomunicações / Unbabel |
MLR-APPL-IVSMR-1.4: VVS: ACTION RECOGNITION WITH VIRTUAL VIEW SYNTHESIS |
Gao Peng; Shanghai Jiao Tong University |
Yong-Lu Li; Shanghai Jiao Tong University |
Hao Zhu; Shanghai Jiao Tong University |
Jiajun Tang; Shanghai Jiao Tong University |
Jin Xia; Shanghai Jiao Tong University |
Cewu Lu; Shanghai Jiao Tong University |
MLR-APPL-IVSMR-1.5: MULTI-TASK DISTILLATION: TOWARDS MITIGATING THE NEGATIVE TRANSFER IN MULTI-TASK LEARNING |
Ze Meng; Tsinghua University |
Xin Yao; Tsinghua University |
Lifeng Sun; Tsinghua University |
MLR-APPL-IVSMR-1.6: U-NOISE: LEARNABLE NOISE MASKS FOR INTERPRETABLE IMAGE SEGMENTATION |
Teddy Koker; OpenMined |
Fatemehsadat Mireshghallah; University of California, San Diego |
Tom Titcombe; OpenMined |
Georgios Kaissis; Technical University of Munich |
MLR-APPL-IVSMR-1.7: NATURAL STATISTICS OF NETWORK ACTIVATIONS AND IMPLICATIONS FOR KNOWLEDGE DISTILLATION |
Michael Rotman; Tel-Aviv University |
Lior Wolf; Tel-Aviv University |
MLR-APPL-IVSMR-1.8: REGULARIZATION VIA DEEP GENERATIVE MODELS: AN ANALYSIS POINT OF VIEW |
Thomas Oberlin; ISAE-SUPAERO |
Mathieu Verm; ISAE-SUPAERO |
MLR-APPL-IVSMR-1.9: GET TO THE POINT: CONTENT CLASSIFICATION OF ANIMATED GRAPHICS INTERCHANGE FORMATS WITH KEY-FRAME ATTENTION |
Yongjuan Ma; Tianjin University |
Yu Wang; Tianjin University |
Pengfei Zhu; Tianjin University |
Junwen Pan; Tianjin University |
Hong Shi; Tianjin University |
MLR-APPL-IVSMR-1.10: DIFFERENTIABLE DYNAMIC CHANNEL ASSOCIATION FOR KNOWLEDGE DISTILLATION |
Qiankun Tang; Zhejiang Lab |
Xiaogang Xu; Zhejiang Gongshang University |
Jun Wang; Zhejiang Lab |
MLR-APPL-IVSMR-1.11: THE MAXIMUM A POSTERIOR ESTIMATION OF DARTS |
Jun-Liang Lin; Academia Sinica |
Yi-Lin Sung; Academia Sinica |
Cheng-Yao Hong; Academia Sinica |
Han-Hung Lee; Academia Sinica |
Tyng-Luh Liu; Academia Sinica |
MLR-APPL-IVSMR-1.12: IMPROVED MULTICLASS ADABOOST FOR IMAGE CLASSIFICATION: THE ROLE OF TREE OPTIMIZATION |
Arman Zharmagambetov; University of California, Merced |
Magzhan Gabidolla; University of California, Merced |
Miguel Á. Carreira-Perpiñán; University of California, Merced |