9 citations · 29 across the 19 of their papers we have counts for
19 papers
Mask6D: Masked Pose Priors For 6D Object Pose Estimation
Yuechen Xie, Haobo Jiang, Jin Xie
Robust 6D object pose estimation in cluttered or occluded conditions using monocular RGB images remains a challenging task. One reason is that current pose estimation networks stru…
Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphs
Linyan Yang, Jingwei Cheng, Chuanhao Xu +3
Entity alignment (EA) refers to the task of linking entities in different knowledge graphs (KGs). Existing EA methods rely heavily on structural isomorphism. However, in real-world…
Towards General Deepfake Detection with Dynamic Curriculum
Wentang Song, Yuzhen Lin, Bin Li
Most previous deepfake detection methods bent their efforts to discriminate artifacts by end-to-end training. However, the learned networks often fail to mine the general face forg…
Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms
Ahmed Ben Yahmed, Clément Calauzènes, Vianney Perchet
In the strategic multi-armed bandit setting, when arms possess perfect information about the player's behavior, they can establish an equilibrium where: 1. they retain almost all o…
Sec2Sec Co-attention for Video-Based Apparent Affective Prediction
Mingwei Sun, Kunpeng Zhang
Video-based apparent affect detection plays a crucial role in video understanding, as it encompasses various elements such as vision, audio, audio-visual interactions, and spatiote…
T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image
Shijie Zhang, Boyan Jiang, Keke He +5
Pixel2Mesh (P2M) is a classical approach for reconstructing 3D shapes from a single color image through coarse-to-fine mesh deformation. Although P2M is capable of generating plaus…
Maximum-Entropy Adversarial Audio Augmentation for Keyword Spotting
Zuzhao Ye, Gregory Ciccarelli, Brian Kulis
Data augmentation is a key tool for improving the performance of deep networks, particularly when there is limited labeled data. In some fields, such as computer vision, augmentati…
DarkShot: Lighting Dark Images with Low-Compute and High-Quality
Jiazhang Zheng, Lei Li, Qiuping Liao +3
Nighttime photography encounters escalating challenges in extremely low-light conditions, primarily attributable to the ultra-low signal-to-noise ratio. For real-world deployment,…
TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks
Khondoker Murad Hossain, Tim Oates
As deep neural networks and the datasets used to train them get larger, the default approach to integrating them into research and commercial projects is to download a pre-trained…
TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processing
Luyuan Xie, Cong Li, Xin Zhang +4
Representation learning frameworks in unlabeled time series have been proposed for medical signal processing. Despite the numerous excellent progresses have been made in previous w…
GMTR: Graph Matching Transformers
Jinpei Guo, Shaofeng Zhang, Runzhong Wang +2
Vision transformers (ViTs) have recently been used for visual matching beyond object detection and segmentation. However, the original grid dividing strategy of ViTs neglects the s…
Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification
Mohammed Maqsood Shaik, Dietrich Klakow, Badr M. Abdullah
Pre-trained Transformer-based speech models have shown striking performance when fine-tuned on various downstream tasks such as automatic speech recognition and spoken language ide…
Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter
Song Li, Yongbin You, Xuezhi Wang +2
Multilingual intelligent assistants, such as ChatGPT, have recently gained popularity. To further expand the applications of multilingual artificial intelligence assistants and fac…
Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding
Umberto Cappellazzo, Muqiao Yang, Daniele Falavigna +1
The ability to learn new concepts sequentially is a major weakness for modern neural networks, which hinders their use in non-stationary environments. Their propensity to fit the c…
Backdoor Attacks with Input-unique Triggers in NLP
Xukun Zhou, Jiwei Li, Tianwei Zhang +3
Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable…
Online Continual Learning of End-to-End Speech Recognition Models
Muqiao Yang, Ian Lane, Shinji Watanabe
Continual Learning, also known as Lifelong Learning, aims to continually learn from new data as it becomes available. While prior research on continual learning in automatic speech…
M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis
Xingbo Wang, Jianben He, Zhihua Jin +3
Multimodal sentiment analysis aims to recognize people's attitudes from multiple communication channels such as verbal content (i.e., text), voice, and facial expressions. It has b…
Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition
Yihong Dong, Ying Peng, Muqiao Yang +2
Deep neural networks have been shown as a class of useful tools for addressing signal recognition issues in recent years, especially for identifying the nonlinear feature structure…
Self-supervised Representation Learning with Relative Predictive Coding
Yao-Hung Hubert Tsai, Martin Q. Ma, Muqiao Yang +3
This paper introduces Relative Predictive Coding (RPC), a new contrastive representation learning objective that maintains a good balance among training stability, minibatch size s…