Search Results for author: Siqi Li

Found 31 papers, 13 papers with code

RealVVT: Towards Photorealistic Video Virtual Try-on via Spatio-Temporal Consistency

no code implementations15 Jan 2025 Siqi Li, Zhengkai Jiang, Jiawei Zhou, Zhihong Liu, Xiaowei Chi, Haoqian Wang

Virtual try-on has emerged as a pivotal task at the intersection of computer vision and fashion, aimed at digitally simulating how clothing items fit on the human body.

Virtual Try-on

Locate n' Rotate: Two-stage Openable Part Detection with Foundation Model Priors

1 code implementation17 Dec 2024 Siqi Li, Xiaoxue Chen, Haoyu Cheng, Guyue Zhou, Hao Zhao, Guanzhong Tian

In this paper, we propose a Transformer-based Openable Part Detection (OPD) framework named Multi-feature Openable Part Detection (MOPD) that incorporates perceptual grouping and geometric priors, outperforming previous methods in performance.

Parameter Prediction

Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach

1 code implementation13 Sep 2024 Siqi Li, Danni Liu, Jan Niehues

To leverage these valuable resources, we propose a retrieval-and-demonstration approach to enhance rare word translation accuracy in direct ST models.

In-Context Learning Retrieval +3

A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning

no code implementations9 Aug 2024 Ye Yuan, Chengwu Liu, Jingyang Yuan, Gongbo Sun, Siqi Li, Ming Zhang

Both the local and online evaluations demonstrate that our system significantly enhances complex reasoning capabilities.

Attribute RAG +1

OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks

1 code implementation7 Jul 2024 Jingyang Xiang, Zuohui Chen, Siqi Li, Qing Wu, Yong liu

We observe that, for vanilla BNNs, over 50\% of the weights remain their signs unchanged during training, and these weights are not only distributed at the tails of the weight distribution but also universally present in the vicinity of zero.

Quantization

Hypergraph-based Multi-View Action Recognition using Event Cameras

no code implementations28 Mar 2024 Yue Gao, Jiaxuan Lu, Siqi Li, Yipeng Li, Shaoyi Du

By treating segments as vertices and constructing hyperedges using rule-based and KNN-based strategies, a multi-view hypergraph neural network that captures relationships across viewpoint and temporal features is established.

Action Recognition

AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction

no code implementations13 Mar 2024 Siqi Li, Jun Chen, Jingyang Xiang, Chengrui Zhu, Yong liu

AutoDFP assesses the similarity of channels for each layer and provides this information to the reinforcement learning agent, guiding the pruning and reconstruction process of the network.

3D Feature Tracking via Event Camera

1 code implementation CVPR 2024 Siqi Li, Zhikuan Zhou, Zhou Xue, Yipeng Li, Shaoyi Du, Yue Gao

To achieve this our method leverages a joint framework to predict the 2D feature motion offsets and the 3D feature spatial position simultaneously.

Motion Compensation Patch Matching +1

CR-SFP: Learning Consistent Representation for Soft Filter Pruning

no code implementations17 Dec 2023 Jingyang Xiang, Zhuangzhi Chen, Jianbiao Mei, Siqi Li, Jun Chen, Yong liu

In this paper, we propose to mitigate this gap by learning consistent representation for soft filter pruning, dubbed as CR-SFP.

MaxQ: Multi-Axis Query for N:M Sparsity Network

1 code implementation CVPR 2024 Jingyang Xiang, Siqi Li, JunHao Chen, Zhuangzhi Chen, Tianxin Huang, Linpeng Peng, Yong liu

Meanwhile, a sparsity strategy that gradually increases the percentage of N:M weight blocks is applied, which allows the network to heal from the pruning-induced damage progressively.

Image Classification Instance Segmentation +3

SUBP: Soft Uniform Block Pruning for 1xN Sparse CNNs Multithreading Acceleration

1 code implementation10 Oct 2023 Jingyang Xiang, Siqi Li, Jun Chen, Shipeng Bai, Yukai Ma, Guang Dai, Yong liu

To overcome them, this paper proposes a novel \emph{\textbf{S}oft \textbf{U}niform \textbf{B}lock \textbf{P}runing} (SUBP) approach to train a uniform 1$\times$N sparse structured network from scratch.

FedScore: A privacy-preserving framework for federated scoring system development

1 code implementation1 Mar 2023 Siqi Li, Yilin Ning, Marcus Eng Hock Ong, Bibhas Chakraborty, Chuan Hong, Feng Xie, Han Yuan, Mingxuan Liu, Daniel M. Buckland, Yong Chen, Nan Liu

We also calculated the average AUC values and SDs for each local model, and the FedScore model showed promising accuracy and stability with a high average AUC value which was closest to the one of the pooled model and SD which was lower than that of most local models.

Federated Learning Model Selection +2

UFO2: A unified pre-training framework for online and offline speech recognition

no code implementations26 Oct 2022 Li Fu, Siqi Li, Qingtao Li, Liping Deng, Fangzhu Li, Lu Fan, Meng Chen, Xiaodong He

In this paper, we propose a Unified pre-training Framework for Online and Offline (UFO2) Automatic Speech Recognition (ASR), which 1) simplifies the two separate training workflows for online and offline modes into one process, and 2) improves the Word Error Rate (WER) performance with limited utterance annotating.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Parotid Gland MRI Segmentation Based on Swin-Unet and Multimodal Images

no code implementations7 Jun 2022 Zi'an Xu, Yin Dai, Fayu Liu, Siqi Li, Sheng Liu, Lifu Shi, Jun Fu

Preoperative tumor localization, differential diagnosis, and subsequent selection of appropriate treatment for parotid gland tumors are critical.

MRI segmentation Segmentation +1

Neural KEM: A Kernel Method with Deep Coefficient Prior for PET Image Reconstruction

no code implementations5 Jan 2022 Siqi Li, Kuang Gong, Ramsey D. Badawi, Edward J. Kim, Jinyi Qi, Guobao Wang

In this paper, we propose an implicit regularization for the kernel method by using a deep coefficient prior, which represents the kernel coefficient image in the PET forward model using a convolutional neural-network.

Image Reconstruction

Benchmarking emergency department triage prediction models with machine learning and large public electronic health records

1 code implementation22 Nov 2021 Feng Xie, Jun Zhou, Jin Wee Lee, Mingrui Tan, Siqi Li, Logasan S/O Rajnthern, Marcel Lucas Chee, Bibhas Chakraborty, An-Kwok Ian Wong, Alon Dagan, Marcus Eng Hock Ong, Fei Gao, Nan Liu

In this paper, based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we developed a publicly available benchmark suite for ED triage predictive models and created a benchmark dataset that contains over 400, 000 ED visits from 2011 to 2019.

Benchmarking

Deep Kernel Representation for Image Reconstruction in PET

no code implementations4 Oct 2021 Siqi Li, Guobao Wang

Kernel methods address this challenge by using kernel representation to incorporate image prior information in the forward model of iterative PET image reconstruction.

Image Reconstruction

Event Stream Super-Resolution via Spatiotemporal Constraint Learning

no code implementations ICCV 2021 Siqi Li, Yutong Feng, Yipeng Li, Yu Jiang, Changqing Zou, Yue Gao

Therefore, it is imperative to explore the algorithm of event stream super-resolution, which is a non-trivial task due to the sparsity and strong spatio-temporal correlation of the events from an event camera.

Image Reconstruction Philosophy +1

Low-Dose CT Image Denoising Using Parallel-Clone Networks

no code implementations14 May 2020 Siqi Li, Guobao Wang

In this paper, we propose a parallel-clone neural network method that utilizes a modularized network model and exploits the benefit of parallel input, parallel-output loss, and clone-toclone feature transfer.

Image Denoising Medical Image Denoising

Attention-based Multi-modal Fusion Network for Semantic Scene Completion

no code implementations31 Mar 2020 Siqi Li, Changqing Zou, Yipeng Li, Xibin Zhao, Yue Gao

This paper presents an end-to-end 3D convolutional network named attention-based multi-modal fusion network (AMFNet) for the semantic scene completion (SSC) task of inferring the occupancy and semantic labels of a volumetric 3D scene from single-view RGB-D images.

2D Semantic Segmentation 3D Semantic Scene Completion +2

Cannot find the paper you are looking for? You can Submit a new open access paper.