143 citations · 500 across the 20 of their papers we have counts for
20 papers
SALS: Sparse Attention in Latent Space for KV cache Compression
Junlin Mu, Hantao Huang, Jihang Zhang +3
Large Language Models capable of handling extended contexts are in high demand, yet their inference remains challenging due to substantial Key-Value cache size and high memory band…
GrassNet: State Space Model Meets Graph Neural Network
Gongpei Zhao, Tao Wang, Yi Jin +3
Designing spectral convolutional networks is a formidable task in graph learning. In traditional spectral graph neural networks (GNNs), polynomial-based methods are commonly used t…
DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment
Gongpei Zhao, Tao Wang, Congyan Lang +3
Graph neural networks are recognized for their strong performance across various applications, with the backpropagation algorithm playing a central role in the development of most…
Bridging the Gap: Multi-Level Cross-Modality Joint Alignment for Visible-Infrared Person Re-Identification
Tengfei Liang, Yi Jin, Wu Liu +3
Visible-Infrared person Re-IDentification (VI-ReID) is a challenging cross-modality image retrieval task that aims to match pedestrians' images across visible and infrared cameras.…
The Cascaded Forward Algorithm for Neural Network Training
Gongpei Zhao, Tao Wang, Yidong Li +3
Backpropagation algorithm has been widely used as a mainstream learning procedure for neural networks in the past decade, and has played a significant role in the development of de…
Boundary Corrected Multi-scale Fusion Network for Real-time Semantic Segmentation
Tianjiao Jiang, Yi Jin, Tengfei Liang +2
Image semantic segmentation aims at the pixel-level classification of images, which has requirements for both accuracy and speed in practical application. Existing semantic segment…
LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling
Xu Wang, Yi Jin, Yigang Cen +3
Compared with traditional task-irrelevant downsampling methods, task-oriented neural networks have shown improved performance in point cloud downsampling range. Recently, Transform…
GLAN: A Graph-based Linear Assignment Network
He Liu, Tao Wang, Congyan Lang +3
Differentiable solvers for the linear assignment problem (LAP) have attracted much research attention in recent years, which are usually embedded into learning frameworks as compon…
Deep Probabilistic Graph Matching
He Liu, Tao Wang, Yidong Li +3
Most previous learning-based graph matching algorithms solve the \textit{quadratic assignment problem} (QAP) by dropping one or more of the matching constraints and adopting a rela…
Camera-aware Style Separation and Contrastive Learning for Unsupervised Person Re-identification
Xue Li, Tengfei Liang, Yi Jin +2
Unsupervised person re-identification (ReID) is a challenging task without data annotation to guide discriminative learning. Existing methods attempt to solve this problem by clust…
MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification
Yajun Gao, Tengfei Liang, Yi Jin +4
The RGB-infrared cross-modality person re-identification (ReID) task aims to recognize the images of the same identity between the visible modality and the infrared modality. Exist…
CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification
Tengfei Liang, Yi Jin, Yajun Gao +4
Visible-infrared cross-modality person re-identification is a challenging ReID task, which aims to retrieve and match the same identity's images between the heterogeneous visible a…
Joint Graph Learning and Matching for Semantic Feature Correspondence
He Liu, Tao Wang, Yidong Li +3
In recent years, powered by the learned discriminative representation via graph neural network (GNN) models, deep graph matching methods have made great progresses in the task of m…
A Universal Model for Cross Modality Mapping by Relational Reasoning
Zun Li, Congyan Lang, Liqian Liang +4
With the aim of matching a pair of instances from two different modalities, cross modality mapping has attracted growing attention in the computer vision community. Existing method…
Attention Models for Point Clouds in Deep Learning: A Survey
Xu Wang, Yi Jin, Yigang Cen +2
Recently, the advancement of 3D point clouds in deep learning has attracted intensive research in different application domains such as computer vision and robotic tasks. However,…
EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising
Tengfei Liang, Yi Jin, Yidong Li +3
In the past few decades, to reduce the risk of X-ray in computed tomography (CT), low-dose CT image denoising has attracted extensive attention from researchers, which has become a…
Cross-layer Feature Pyramid Network for Salient Object Detection
Zun Li, Congyan Lang, Junhao Liew +3
Feature pyramid network (FPN) based models, which fuse the semantics and salient details in a progressive manner, have been proven highly effective in salient object detection. How…
HERA: Partial Label Learning by Combining Heterogeneous Loss with Sparse and Low-Rank Regularization
Gengyu Lyu, Songhe Feng, Yi Jin +3
Partial Label Learning (PLL) aims to learn from the data where each training instance is associated with a set of candidate labels, among which only one is correct. Most existing m…
Domain Adaptive Attention Learning for Unsupervised Person Re-Identification
Yangru Huang, Peixi Peng, Yi Jin +3
Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotat…
Multiple-Human Parsing in the Wild
Jianshu Li, Jian Zhao, Yunchao Wei +5
Human parsing is attracting increasing research attention. In this work, we aim to push the frontier of human parsing by introducing the problem of multi-human parsing in the wild.…