Picture for Siyuan Shen

Siyuan Shen

Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition

Add code
Mar 28, 2024
Figure 1 for Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition
Figure 2 for Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition
Figure 3 for Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition
Figure 4 for Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition
Viaarxiv icon

EyeLS: Shadow-Guided Instrument Landing System for Intraocular Target Approaching in Robotic Eye Surgery

Add code
Nov 15, 2023
Figure 1 for EyeLS: Shadow-Guided Instrument Landing System for Intraocular Target Approaching in Robotic Eye Surgery
Figure 2 for EyeLS: Shadow-Guided Instrument Landing System for Intraocular Target Approaching in Robotic Eye Surgery
Figure 3 for EyeLS: Shadow-Guided Instrument Landing System for Intraocular Target Approaching in Robotic Eye Surgery
Figure 4 for EyeLS: Shadow-Guided Instrument Landing System for Intraocular Target Approaching in Robotic Eye Surgery
Viaarxiv icon

Cached Operator Reordering: A Unified View for Fast GNN Training

Add code
Aug 23, 2023
Figure 1 for Cached Operator Reordering: A Unified View for Fast GNN Training
Figure 2 for Cached Operator Reordering: A Unified View for Fast GNN Training
Figure 3 for Cached Operator Reordering: A Unified View for Fast GNN Training
Figure 4 for Cached Operator Reordering: A Unified View for Fast GNN Training
Viaarxiv icon

Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction

Add code
Apr 21, 2023
Figure 1 for Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction
Figure 2 for Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction
Figure 3 for Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction
Figure 4 for Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction
Viaarxiv icon

High-resolution tomographic reconstruction of optical absorbance through scattering media using neural fields

Add code
Apr 04, 2023
Figure 1 for High-resolution tomographic reconstruction of optical absorbance through scattering media using neural fields
Figure 2 for High-resolution tomographic reconstruction of optical absorbance through scattering media using neural fields
Figure 3 for High-resolution tomographic reconstruction of optical absorbance through scattering media using neural fields
Figure 4 for High-resolution tomographic reconstruction of optical absorbance through scattering media using neural fields
Viaarxiv icon

Mingling or Misalignment? Temporal Shift for Speech Emotion Recognition with Pre-trained Representations

Add code
Mar 01, 2023
Figure 1 for Mingling or Misalignment? Temporal Shift for Speech Emotion Recognition with Pre-trained Representations
Figure 2 for Mingling or Misalignment? Temporal Shift for Speech Emotion Recognition with Pre-trained Representations
Figure 3 for Mingling or Misalignment? Temporal Shift for Speech Emotion Recognition with Pre-trained Representations
Figure 4 for Mingling or Misalignment? Temporal Shift for Speech Emotion Recognition with Pre-trained Representations
Viaarxiv icon

PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objects

Add code
May 18, 2022
Figure 1 for PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objects
Figure 2 for PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objects
Figure 3 for PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objects
Figure 4 for PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objects
Viaarxiv icon

Onsite Non-Line-of-Sight Imaging via Online Calibrations

Add code
Dec 29, 2021
Figure 1 for Onsite Non-Line-of-Sight Imaging via Online Calibrations
Figure 2 for Onsite Non-Line-of-Sight Imaging via Online Calibrations
Figure 3 for Onsite Non-Line-of-Sight Imaging via Online Calibrations
Figure 4 for Onsite Non-Line-of-Sight Imaging via Online Calibrations
Viaarxiv icon

LMR-CBT: Learning Modality-fused Representations with CB-Transformer for Multimodal Emotion Recognition from Unaligned Multimodal Sequences

Add code
Dec 03, 2021
Figure 1 for LMR-CBT: Learning Modality-fused Representations with CB-Transformer for Multimodal Emotion Recognition from Unaligned Multimodal Sequences
Figure 2 for LMR-CBT: Learning Modality-fused Representations with CB-Transformer for Multimodal Emotion Recognition from Unaligned Multimodal Sequences
Figure 3 for LMR-CBT: Learning Modality-fused Representations with CB-Transformer for Multimodal Emotion Recognition from Unaligned Multimodal Sequences
Figure 4 for LMR-CBT: Learning Modality-fused Representations with CB-Transformer for Multimodal Emotion Recognition from Unaligned Multimodal Sequences
Viaarxiv icon

High-order Differentiable Autoencoder for Nonlinear Model Reduction

Add code
Feb 19, 2021
Figure 1 for High-order Differentiable Autoencoder for Nonlinear Model Reduction
Figure 2 for High-order Differentiable Autoencoder for Nonlinear Model Reduction
Figure 3 for High-order Differentiable Autoencoder for Nonlinear Model Reduction
Figure 4 for High-order Differentiable Autoencoder for Nonlinear Model Reduction
Viaarxiv icon