Search Results for author:
Found 27 papers, 15 papers with code
Modeling Compositionality with Dependency Graph for Dialogue Generation
Because of the compositionality of natural language, syntactic structure which contains the information about the relationship between words is a key factor for semantic understanding.
SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations
Large language models (LLMs) have been widely applied in various fields due to their excellent capability for memorizing knowledge and chain of thought (CoT).
BianQue: Balancing the Questioning and Suggestion Ability of Health LLMs with Multi-turn Health Conversations Polished by ChatGPT
Large language models (LLMs) have performed well in providing general and extensive health suggestions in single-turn conversations, exemplified by systems such as ChatGPT, ChatGLM, ChatDoctor, DoctorGLM, and etc.
Robust Depth Linear Error Decomposition with Double Total Variation and Nuclear Norm for Dynamic MRI Reconstruction
By adding linear image domain error analysis, the noise is reduced after under-sampled and DFT processing, and the anti-interference ability of the algorithm is enhanced.
CorrTalk: Correlation Between Hierarchical Speech and Facial Activity Variances for 3D Animation
In this study, we propose a novel framework, CorrTalk, which effectively establishes the temporal correlation between hierarchical speech features and facial activities of different intensities across distinct regions.
Self-supervised Fetal MRI 3D Reconstruction Based on Radiation Diffusion Generation Model
Finally, the experimental results on real-world fetal brain MRI stacks demonstrate the state-of-the-art performance of our method.
Dynamic Shuffle: An Efficient Channel Mixture Method
To reduce the data-dependent redundancy, we devise a dynamic shuffle module to generate data-dependent permutation matrices for shuffling.
LAPP: Layer Adaptive Progressive Pruning for Compressing CNNs from Scratch
Therefore the pruning strategy can gradually prune the network and automatically determine the appropriate pruning rates for each layer.
Vesper: A Compact and Effective Pretrained Model for Speech Emotion Recognition
Although PTMs shed new light on artificial general intelligence, they are constructed with general tasks in mind, and thus, their efficacy for specific tasks can be further improved.
DWFormer: Dynamic Window transFormer for Speech Emotion Recognition
Self-attention mechanism is applied within windows for capturing temporal important information locally in a fine-grained way.
SpeechFormer++: A Hierarchical Efficient Framework for Paralinguistic Speech Processing
Paralinguistic speech processing is important in addressing many issues, such as sentiment and neurocognitive disorder analyses.
Ranked #1 on
Speech Emotion Recognition
on LSSED
Superpoint Transformer for 3D Scene Instance Segmentation
The key step in this framework is a novel query decoder with transformers that can capture the instance information through the superpoint cross-attention mechanism and generate the superpoint masks of the instances.
Ranked #4 on
3D Instance Segmentation
on ScanNet(v2)
Context Sensing Attention Network for Video-based Person Re-identification
In this work, we propose a novel Context Sensing Attention Network (CSA-Net), which improves both the frame feature extraction and temporal aggregation steps.
CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI
Finally, we provide baseline systems for these tasks and consider the function of speakers' personalities and emotions on conversation.
Ranked #1 on
Emotion Recognition in Conversation
on CPED
Compact Model Training by Low-Rank Projection with Energy Transfer
In this paper, we devise a new training method, low-rank projection with energy transfer (LRPET), that trains low-rank compressed networks from scratch and achieves competitive performance.
Weight Evolution: Improving Deep Neural Networks Training through Evolving Inferior Weight Values
Comprehensive experiments show that WE outperforms the other reactivation methods and plug-in training methods with typical convolutional neural networks, especially lightweight networks.
To Deconvolve, or Not to Deconvolve: Inferences of Neuronal Activities using Calcium Imaging Data
With the increasing popularity of calcium imaging data in neuroscience research, methods for analyzing calcium trace data are critical to address various questions.
LSSED: a large-scale dataset and benchmark for speech emotion recognition
Speech emotion recognition is a vital contributor to the next generation of human-computer interaction (HCI).
Ranked #3 on
Speech Emotion Recognition
on LSSED
Listwise View Ranking for Image Cropping
However, the performance of ranking-based methods is often poor and this is mainly due to two reasons: 1) image cropping is a listwise ranking task rather than pairwise comparison; 2) the rescaling caused by pooling layer and the deformation in view generation damage the performance of composition learning.
BIT: Biologically Inspired Tracker
Visual tracking is challenging due to image variations caused by various factors, such as object deformation, scale change, illumination change and occlusion.
Geometry Processing of Conventionally Produced Mouse Brain Slice Images
In this paper we present techniques and algorithms for automatic registration and 3D reconstruction of conventionally produced mouse brain slices in a standardized atlas space.
Deep Sampling Networks
With the powerful down-sampling process, the co-training DSN set a new state-of-the-art performance for image super-resolution.
FReLU: Flexible Rectified Linear Units for Improving Convolutional Neural Networks
Rectified linear unit (ReLU) is a widely used activation function for deep convolutional neural networks.
Manifold Regularized Slow Feature Analysis for Dynamic Texture Recognition
However, complex temporal variations require high-level semantic representations to fully achieve temporal slowness, and thus it is impractical to learn a high-level representation from dynamic textures directly by SFA.
Single Image Super-Resolution Using Multi-Scale Convolutional Neural Network
However, the previous methods mainly restore images from one single area in the low resolution (LR) input, which limits the flexibility of models to infer various scales of details for high resolution (HR) output.
Multi-scale Convolutional Neural Networks for Crowd Counting
Crowd counting on static images is a challenging problem due to scale variations.
DehazeNet: An End-to-End System for Single Image Haze Removal
The key to achieve haze removal is to estimate a medium transmission map for an input hazy image.
Ranked #7 on
Image Dehazing
on RS-Haze
