Search Results for author: Liqiang He

Found 5 papers, 1 papers with code

Bidirectional Alignment for Domain Adaptive Detection with Transformers

1 code implementation ICCV 2023 Liqiang He, Wei Wang, Albert Chen, Min Sun, Cheng-Hao Kuo, Sinisa Todorovic

We propose a Bidirectional Alignment for domain adaptive Detection with Transformers (BiADT) to improve cross domain object detection performance.

Object object-detection +1

DESTR: Object Detection With Split Transformer

no code implementations CVPR 2022 Liqiang He, Sinisa Todorovic

Second, we use a mini-detector to initialize the content queries in the decoder with classification and regression embeddings of the respective heads in the mini-detector.

Classification Inductive Bias +4

Latency-Controlled Neural Architecture Search for Streaming Speech Recognition

no code implementations8 May 2021 Liqiang He, Shulin Feng, Dan Su, Dong Yu

Extensive experiments show that: 1) Based on the proposed neural architecture, the neural networks with a medium latency of 550ms (millisecond) and a low latency of 190ms can be learned in the vanilla and revised operation space respectively.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Learned Transferable Architectures Can Surpass Hand-Designed Architectures for Large Scale Speech Recognition

no code implementations25 Aug 2020 Liqiang He, Dan Su, Dong Yu

Extensive experiments show that: (i) the architecture searched on the small proxy dataset can be transferred to the large dataset for the speech recognition tasks.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Phrase-Level Class based Language Model for Mandarin Smart Speaker Query Recognition

no code implementations2 Sep 2019 Yiheng Huang, Liqiang He, Lei Han, Guangsen Wang, Dan Su

In this work, we propose to train pruned language models for the word classes to replace the slots in the root n-gram.

Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.