13 citations · 29 across the 7 of their papers we have counts for
7 papers
Inductive Attention for Video Action Anticipation
Tsung-Ming Tai, Giuseppe Fiameni, Cheng-Kuang Lee +2
Anticipating future actions based on spatiotemporal observations is essential in video understanding and predictive computer vision. Moreover, a model capable of anticipating the f…
NVIDIA-UNIBZ Submission for EPIC-KITCHENS-100 Action Anticipation Challenge 2022
Tsung-Ming Tai, Oswald Lanz, Giuseppe Fiameni +5
In this report, we describe the technical details of our submission for the EPIC-Kitchen-100 action anticipation challenge. Our modelings, the higher-order recurrent space-time tra…
Unified Recurrence Modeling for Video Action Anticipation
Tsung-Ming Tai, Giuseppe Fiameni, Cheng-Kuang Lee +2
Forecasting future events based on evidence of current conditions is an innate skill of human beings, and key for predicting the outcome of any decision making. In artificial visio…
Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning
Yi-Chen Chen, Shu-wen Yang, Cheng-Kuang Lee +2
Speech representation learning plays a vital role in speech processing. Among them, self-supervised learning (SSL) has become an important research direction. It has been shown tha…
SpeechNet: A Universal Modularized Model for Speech Processing Tasks
Yi-Chen Chen, Po-Han Chi, Shu-wen Yang +7
There is a wide variety of speech processing tasks ranging from extracting content information from speech signals to generating speech signals. For different tasks, model networks…
Higher Order Recurrent Space-Time Transformer for Video Action Prediction
Tsung-Ming Tai, Giuseppe Fiameni, Cheng-Kuang Lee +1
Endowing visual agents with predictive capability is a key step towards video intelligence at scale. The predominant modeling paradigm for this is sequence learning, mostly impleme…
DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation
Yi-Chen Chen, Jui-Yang Hsu, Cheng-Kuang Lee +1
In previous works, only parameter weights of ASR models are optimized under fixed-topology architecture. However, the design of successful model architecture has always relied on h…