firstbacksecondback
10 Results
|
Poster
|
Tue 7:30 |
D4AM: A General Denoising Framework for Downstream Acoustic Models Chi-Chang Lee · Yu Tsao · Hsin-Min Wang · Chu-Song Chen |
|
|
Poster
|
Wed 2:30 |
Understanding Zero-shot Adversarial Robustness for Large-Scale Models Chengzhi Mao · Scott Geng · Junfeng Yang · Xin Wang · Carl Vondrick |
|
|
Poster
|
Discovering Informative and Robust Positives for Video Domain Adaptation Chang Liu · Kunpeng Li · Michael Stopa · Jun Amano · Yun Fu |
||
|
Workshop
|
Thu 3:07 |
Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness Yanqi Cheng · Lihao Liu · Shujun Wang · Yueming Jin · Carola-Bibiane Schönlieb · Angelica Aviles-Rivero |
|
|
Poster
|
Mon 7:30 |
In-Situ Text-Only Adaptation of Speech Models with Low-Overhead Speech Imputations Ashish Mittal · Sunita Sarawagi · Preethi Jyothi |
|
|
Poster
|
Defending against Adversarial Audio via Diffusion Model Shutong Wu · Jiongxiao Wang · Wei Ping · Weili Nie · Chaowei Xiao |
||
|
Poster
|
Tue 7:30 |
Jointly Learning Visual and Auditory Speech Representations from Raw Data Alexandros Haliassos · Pingchuan Ma · Rodrigo Mira · Stavros Petridis · Maja Pantic |
|
|
Poster
|
Revisiting the Entropy Semiring for Neural Speech Recognition Oscar Chang · Dongseong Hwang · Olivier Siohan |
||
|
Poster
|
Mon 2:30 |
Continuous pseudo-labeling from the start Dan Berrebbi · Ronan Collobert · Samy Bengio · Navdeep Jaitly · Tatiana Likhomanenko |
|
|
Poster
|
BAYES RISK CTC: CONTROLLABLE CTC ALIGNMENT IN SEQUENCE-TO-SEQUENCE TASKS Jinchuan Tian · Brian Yan · Jianwei Yu · CHAO WENG · Dong Yu · Shinji Watanabe |