J
Juncheng Li
Researcher at Carnegie Mellon University
Publications - 59
Citations - 1542
Juncheng Li is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 15, co-authored 36 publications receiving 1004 citations. Previous affiliations of Juncheng Li include Bosch & Charles III University of Madrid.
Papers
More filters
Proceedings ArticleDOI
Very deep convolutional neural networks for raw waveforms
TL;DR: Very deep convolutional neural networks (CNNs) were proposed in this article to directly use time-domain waveforms as inputs, which can optimize over very long sequences (e.g., vector of size 32000) necessary for processing acoustic waveforms.
Proceedings ArticleDOI
Learning Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval
TL;DR: This paper proposes a novel framework that simultaneously utilizes multi-modal features (different visual characteristics, audio inputs, and text) by a fusion strategy for efficient retrieval and explores several loss functions in training the embedding.
Proceedings ArticleDOI
A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling
TL;DR: This paper builds a neural network called TALNet, which is the first system to reach state-of-the-art audio tagging performance on Audio Set, while exhibiting strong localization performance on the DCASE 2017 challenge at the same time.
Posted Content
Very Deep Convolutional Neural Networks for Raw Waveforms
TL;DR: This work proposes very deep convolutional neural networks that directly use time-domain waveforms as inputs that are efficient to optimize over very long sequences, necessary for processing acoustic waveforms.
Proceedings ArticleDOI
A comparison of Deep Learning methods for environmental sound detection
TL;DR: This work presents a comparison of several state-of-the-art Deep Learning models on the IEEE challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) 2016 challenge task and data, classifying sounds into one of fifteen common indoor and outdoor acoustic scenes.