2 papers
cs.CV2023
Multi-view knowledge distillation transformer for human action recognition
Ying-Chen Lin, Vincent S. Tseng
Recently, Transformer-based methods have been utilized to improve the performance of human action recognition. However, most of these studies assume that multi-view data is complet…
cs.LG2021
Breaking the Softmax Bottleneck for Sequential Recommender Systems with Dropout and Decoupling
Ying-Chen Lin
The Softmax bottleneck was first identified in language modeling as a theoretical limit on the expressivity of Softmax-based models. Being one of the most widely-used methods to ou…