Juncheng Billy Li

发表

Acoustic Scene Recognition with Deep Neural Networks ( DCASE challenge 2016 )

Samarjit Das, Phuong Pham, Dai Wei, 2016 .

Detection for Real Life Audio DCASE Challenge

Florian Metze, Juncheng Li, Shuhui Qu, 2016 .

Adversarial camera stickers: A physical camera-based attack on deep learning systems pdf

J. Zico Kolter, Frank R. Schmidt, J. Z. Kolter, 2019, ICML.

Music Theory Inspired Policy Gradient Method for Piano Music Transcription

Florian Metze, Samarjit Das, Juncheng Billy Li, 2018 .

Robustness of Neural Architectures for Audio Event Detection

Florian Metze, Juncheng Billy Li, Shuhui Qu, 2022, ArXiv.

Masked Autoencoders that Listen

Michael Auli, Florian Metze, Alexei Baevski, 2022, Neural Information Processing Systems.

Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos

Shengyu Zhang, Longhui Wei, Siliang Tang, 2022, ACM Multimedia.

Masked Autoencoders that Listen

Michael Auli, Florian Metze, Alexei Baevski, 2022, Neural Information Processing Systems.

AudioTagging Done Right: 2nd comparison of deep learning methods for environmental sound classification

Florian Metze, Po-Yao Huang, Juncheng Billy Li, 2022, INTERSPEECH.

SQuAT: Sharpness- and Quantization-Aware Training for BERT

Florian Metze, Juncheng Billy Li, Shuhui Qu, 2022, ArXiv.

A comparison of Deep Learning methods for environmental sound detection

Florian Metze, Samarjit Das, Wei Dai, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Learning Filter Banks Using Deep Learning For Acoustic Signals pdf

Wei Dai, Samarjit Das, Juncheng Li, 2016, ArXiv.

Masked Autoencoders that Listen

Michael Auli, Florian Metze, Alexei Baevski, 2022, NeurIPS.

Very deep convolutional neural networks for raw waveforms

Wei Dai, Samarjit Das, Juncheng Li, 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling

Florian Metze, Yun Wang, Juncheng Li, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Universal Phone Recognition with a Multilingual Allophone System

Alan W Black, Graham Neubig, Juncheng Li, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Adversarial Music: Real World Audio Adversary Against Wake-word Detection System

J. Zico Kolter, Xinjian Li, Florian Metze, 2019, NeurIPS.

Learning Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval

Amit K. Roy-Chowdhury, Florian Metze, Niluthpol Chowdhury Mithun, 2018, ICMR.

Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization

Siliang Tang, Juncheng Billy Li, Xiaozhong Liu, 2023, 2303.12314.

Meta-augmented Prompt Tuning for Better Few-shot Learning

Siliang Tang, Juncheng Billy Li, Xiaozhong Liu, 2023, ArXiv.

Adversarial camera stickers: A Physical Camera Attack on Deep Learning Classifier

J. Zico Kolter, Frank R. Schmidt, J. Z. Kolter, 2019 .

On Adversarial Robustness Of Large-Scale Audio Visual Learning

Florian Metze, Juncheng Billy Li, Shuhui Qu, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A numerical separation method for incident wave of ground motion in time domain

Juncheng Billy Li, B. Ruan, Suyang Wang, 2022, Soil Dynamics and Earthquake Engineering.

Real-Time Fine Grained Occupancy Estimation Using Depth Sensors on ARM Embedded Platforms

Anthony Rowe, Sirajum Munir, Jonathan Francis, 2017, 2017 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS).

Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection

Florian Metze, Samarjit Das, Shao-Yen Tseng, 2017, INTERSPEECH.

Comparing the Max and Noisy-Or Pooling Functions in Multiple Instance Learning for Weakly Supervised Sequence Learning Tasks pdf

Florian Metze, Yun Wang, Juncheng Li, 2018, INTERSPEECH.

Error-aware Quantization through Noise Tempering

Florian Metze, Juncheng Billy Li, Shuhui Qu, 2022, arXiv.org.

Very deep convolutional neural networks for raw waveforms

Samarjit Das, Juncheng Billy Li, Shuhui Qu, 2016, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Eventness: Object Detection on Spectrograms for Temporal Localization of Audio Events

Samarjit Das, Joseph Szurley, Juncheng Li, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-based Active Learning

Shengyu Zhang, Zhedong Zheng, Juncheng Billy Li, 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization

Siliang Tang, Juncheng Billy Li, Xiaozhong Liu, 2023, EMNLP.

Adversarial camera stickers: A Physical Camera Attack on Deep Learning Classifier

Frank R. Schmidt, J. Z. Kolter, Juncheng Billy Li, 2019 .