activity
20122023
most citedChoosing Transfer Languages for Cross-Lingual Learning

33 citations · 82 across the 9 of their papers we have counts for

collaborators

9 papers

cs.CV2023★ 1 cited

Can the Query-based Object Detector Be Designed with Fewer Stages?

Jialin Li, Weifu Fu, Yuhuan Lin +2

Query-based object detectors have made significant advancements since the publication of DETR. However, most existing methods still rely on multi-stage encoders and decoders, or a…

cs.CV2023

IIDM: Inter and Intra-domain Mixing for Semi-supervised Domain Adaptation in Semantic Segmentation

Weifu Fu, Qiang Nie, Jialin Li +6

Despite recent advances in semantic segmentation, an inevitable challenge is the performance degradation caused by the domain shift in real applications. Current dominant approach…

cs.CV2021★ 9 cited

Dual-Awareness Attention for Few-Shot Object Detection

Tung-I Chen, Yueh-Cheng Liu, Hung-Ting Su +5

While recent progress has significantly boosted few-shot classification (FSC) performance, few-shot object detection (FSOD) remains challenging for modern learning systems. Existin…

cs.LO2021★ 1 cited

Analysis of E-commerce Ranking Signals via Signal Temporal Logic

Tommaso Dreossi, Giorgio Ballardin, Parth Gupta +3

The timed position of documents retrieved by learning to rank models can be seen as signals. Signals carry useful information such as drop or rise of documents over time or user be…

cs.CL2019★ 33 cited

Choosing Transfer Languages for Cross-Lingual Learning

Yu-Hsiang Lin, Chian-Yu Chen, Jean Lee +10

Cross-lingual transfer, where a high-resource transfer language is used to improve the accuracy of a low-resource task language, is now an invaluable tool for improving performance…

cs.CL2018★ 3 cited

Towards a General-Purpose Linguistic Annotation Backend

Graham Neubig, Patrick Littell, Chian-Yu Chen +4

Language documentation is inherently a time-intensive process; transcription, glossing, and corpus management consume a significant portion of documentary linguists' work. Advances…

stat.ML2018★ 1 cited

Distributed Newton Methods for Deep Neural Networks

Chien-Chih Wang, Kent Loong Tan, Chun-Ting Chen +5

Deep learning involves a difficult non-convex optimization problem with a large number of weights between any two adjacent layers of a deep structure. To handle large data sets or…

gr-qc2017★ 5 cited

Suppression of long-wavelength CMB spectrum from the no-boundary initial condition

Pisin Chen, Yu-Hsiang Lin, Dong-han Yeom

The lack of correlations at the long-wavelength scales of the cosmic microwave background spectrum is a long-standing puzzle and it persists in the latest Planck data. By consideri…

astro-ph.CO2012★ 29 cited

Slow-Roll Inflation Preceded by a Topological Defect Phase à la Chaplygin Gas

Mariam Bouhmadi-Lopez, Pisin Chen, Yu-Chien Huang +1

We present a simple toy model corresponding to a network of frustrated topological defects of domain walls or cosmic strings that exist previous to the standard slow-roll inflation…