2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
MLSP-44: Multimodal Data and Applications |
| Session Type: Poster |
| Time: Friday, 11 June, 13:00 - 13:45 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| Session Chair: Shi-Xiong Zhang, Tencent AI Lab |
| MLSP-44.1: MULTIMODAL PUNCTUATION PREDICTION WITH CONTEXTUAL DROPOUT |
| Andrew Silva; Georgia Institute of Technology |
| Barry-John Theobald; Apple |
| Nicholas Apostoloff; Apple |
| MLSP-44.2: MULTI-MODAL LABEL DEQUANTIZED GAUSSIAN PROCESS LATENT VARIABLE MODEL FOR ORDINAL LABEL ESTIMATION |
| Masanao Matsumoto; Hokkaido University |
| Keisuke Maeda; Hokkaido University |
| Naoki Saito; National Institute of Technology, Kushiro College |
| Takahiro Ogawa; Hokkaido University |
| Miki Haseyama; Hokkaido University |
| MLSP-44.3: GENERATIVE INFORMATION FUSION |
| Kenneth Tran; North Carolina State University |
| Wesam Sakla; Lawrence Livermore National Laboratory |
| Hamid Krim; North Carolina State University |
| MLSP-44.4: SELF-AUGMENTED MULTI-MODAL FEATURE EMBEDDING |
| Shinnosuke Matsuo; Kyushu University |
| Seiichi Uchida; Kyushu University |
| Brian Kenji Iwana; Kyushu University |
| MLSP-44.5: OPTIMIZE WHAT MATTERS: TRAINING DNN-HMM KEYWORD SPOTTING MODEL USING END METRIC |
| Ashish Shrivastava; Apple |
| Arnav Kundu; Apple |
| Chandra Dhir; Apple |
| Devang Naik; Apple |
| Oncel Tuzel; Apple |
| MLSP-44.6: CO-ATTENTIONAL TRANSFORMERS FOR STORY-BASED VIDEO UNDERSTANDING |
| Björn Bebensee; Seoul National University |
| Byoung-Tak Zhang; Seoul National University |