Search Results for author:
Found 18 papers, 8 papers with code
SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance
Second, SGFormer leverages the geometric features of partial-missing pairs as the explicit symmetric guidance that can constrain the refinement process for initial point clouds.
Imagine with the Teacher: Complete Shape in a Multi-View Distillation Way
Motivated by the knowledge distillation's teacher-student learning strategy, we design a knowledge transfer way for completing 3d shape.
Towards Lightweight and Stable Zero-shot TTS with Self-distilled Representation Disentanglement
Furthermore, we present a two-stage self-distillation framework that constructs parallel data pairs for effectively disentangling linguistic content and speakers from the perspective of training data.
ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features
Based on the ALIF pipeline, we present the ALIF-OTL and ALIF-OTA schemes for launching attacks in both the digital domain and the physical playback environment on four commercial ASRs and voice assistants.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection
In this paper, we try to tackle these challenges through three designs: (1) We present a novel framework to capture broader forgery clues by extracting multiple non-overlapping local representations and fusing them into a global semantic-rich feature.
FLTracer: Accurate Poisoning Attack Provenance in Federated Learning
In this paper, we first conduct a comprehensive study on prior FL attacks and detection methods.
Privacy-Utility Balanced Voice De-Identification Using Adversarial Examples
In this paper, we propose a voice de-identification system, which uses adversarial examples to balance the privacy and utility of voice services.
FBNet: Feedback Network for Point Cloud Completion
The rapid development of point cloud learning has driven point cloud completion into a new era.
WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses
To improve the accuracy and naturalness of synthesized singing voice, we design several specifical modules and techniques: 1) A deep bi-directional LSTM-based duration model with multi-scale rhythm loss and post-processing step; 2) A Transformer-alike acoustic model with progressive pitch-weighted decoder loss; 3) a 24 kHz pitch-aware LPCNet neural vocoder to produce high-quality singing waveforms; 4) A novel data augmentation method with multi-singer pre-training for stronger robustness and naturalness.
Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS
Thirdly, a duration predictor instead of an attention model that connects the above hybrid encoder and decoder.
Learning Inner-Group Relations on Point Clouds
We further verify the expandability of RPNet, in terms of both depth and width, on the tasks of classification and segmentation.
Ranked #21 on
Semantic Segmentation
on S3DIS
SSPNet: Scale Selection Pyramid Network for Tiny Person Detection from UAV Images
With the increasing demand for search and rescue, it is highly demanded to detect objects of interest in large-scale images captured by Unmanned Aerial Vehicles (UAVs), which is quite challenging due to extremely small scales of objects.
Equivalence of Correlation Filter and Convolution Filter in Visual Tracking
On the surface, correlation filter and convolution filter are usually used for different purposes.
Prediction, Selection, and Generation: Exploration of Knowledge-Driven Conversation System
The system includes modules such as dialogue topic prediction, knowledge matching and dialogue generation.
Triple M: A Practical Text-to-speech Synthesis System With Multi-guidance Attention And Multi-band Multi-time LPCNet
In this work, a robust and efficient text-to-speech (TTS) synthesis system named Triple M is proposed for large-scale online application.
Deeper or Wider Networks of Point Clouds with Self-attention?
Specifically, SepNet achieves state-of-the-art for the tasks of classification and segmentation on most of the datasets.
RIN: Textured Human Model Recovery and Imitation with a Single Image
Human imitation has become topical recently, driven by GAN's ability to disentangle human pose and body content.
Emergence of Chern insulating states in non-Magic angle twisted bilayer graphene
For {\theta}=1. 25{\deg}, we observe an emergence of topological insulating states at hole side with a sequence of Chern number |C|=4-|v|, where v is the number of electrons (holes) in moir\'e unite cell.
Mesoscale and Nanoscale Physics Materials Science
