Search Results for author: Lingyun Wang

Found 12 papers, 4 papers with code

M-LLM Based Video Frame Selection for Efficient Video Understanding

no code implementations27 Feb 2025 Kai Hu, Feng Gao, Xiaohan Nie, Peng Zhou, Son Tran, Tal Neiman, Lingyun Wang, Mubarak Shah, Raffay Hamid, Bing Yin, Trishul Chilimbi

Empirical results show that the proposed M-LLM video frame selector improves the performances various downstream video Large Language Model (video-LLM) across medium (ActivityNet, NExT-QA) and long (EgoSchema, LongVideoBench) context video question answering benchmarks.

EgoSchema Language Modeling +6

SitPose: Real-Time Detection of Sitting Posture and Sedentary Behavior Using Ensemble Learning With Depth Sensor

1 code implementation16 Dec 2024 Hang Jin, Xin He, Lingyun Wang, Yujun Zhu, Weiwei Jiang, Xiaobo Zhou

Finally, we deployed the SitPose system based on this ensemble model to encourage better sitting posture and to reduce sedentary habits.

Ensemble Learning

Real-Time Fall Detection Using Smartphone Accelerometers and WiFi Channel State Information

no code implementations13 Dec 2024 Lingyun Wang, Deqi Su, Aohua Zhang, Yujun Zhu, Weiwei Jiang, Xin He, Panlong Yang

In recent years, as the population ages, falls have increasingly posed a significant threat to the health of the elderly.

Freqformer: Frequency-Domain Transformer for 3-D Visualization and Quantification of Human Retinal Circulation

no code implementations17 Nov 2024 Lingyun Wang, Bingjie Wang, Jay Chhablani, Jose Alain Sahel, Shaohua Pi

We introduce Freqformer, a novel Transformer-based architecture designed for 3-D, high-definition visualization of human retinal circulation from a single scan in commercial optical coherence tomography angiography (OCTA).

SSIM

Multimodal Instruction Tuning with Hybrid State Space Models

no code implementations13 Nov 2024 Jianing Zhou, Han Li, Shuai Zhang, Ning Xie, Ruijie Wang, Xiaohan Nie, Sheng Liu, Lingyun Wang

Remarkably, our model enhances inference efficiency for high-resolution images and high-frame-rate videos by about 4 times compared to current models, with efficiency gains increasing as image resolution or video frames rise.

Mamba State Space Models

BreakNet: Discontinuity-Resilient Multi-Scale Transformer Segmentation of Retinal Layers

no code implementations26 Aug 2024 Razieh Ganjee, Bingjie Wang, Lingyun Wang, Chengcheng Zhao, José-Alain Sahel, Shaohua Pi

Visible light optical coherence tomography (vis-OCT) is gaining traction for retinal imaging due to its high resolution and functional capabilities.

Decoder Segmentation

Label-Guided Prompt for Multi-label Few-shot Aspect Category Detection

no code implementations30 Jul 2024 Chaofeng Guan, Yaohui Zhu, Yu Bai, Lingyun Wang

This kind of category descriptions contain the characteristics of the aspect categories, guiding the construction of discriminative category prototypes.

Aspect Category Detection Language Modeling +3

Gaussian Time Machine: A Real-Time Rendering Methodology for Time-Variant Appearances

no code implementations22 May 2024 Licheng Shen, Ho Ngai Chow, Lingyun Wang, Tong Zhang, Mengqiu Wang, Yuxing Han

In this paper, we present Gaussian Time Machine (GTM) which models the time-dependent attributes of Gaussian primitives with discrete time embedding vectors decoded by a lightweight Multi-Layer-Perceptron(MLP).

3DGS 3D Reconstruction +2

Fully Automated OCT-based Tissue Screening System

no code implementations15 May 2024 Shaohua Pi, Razieh Ganjee, Lingyun Wang, Riley K. Arbuckle, Chengcheng Zhao, Jose A Sahel, Bingjie Wang, YuanYuan Chen

This study introduces a groundbreaking optical coherence tomography (OCT) imaging system dedicated for high-throughput screening applications using ex vivo tissue culture.

Drug Discovery

Sub2Full: split spectrum to boost OCT despeckling without clean data

3 code implementations18 Jan 2024 Lingyun Wang, Jose A Sahel, Shaohua Pi

Optical coherence tomography (OCT) suffers from speckle noise, causing the deterioration of image quality, especially in high-resolution modalities like visible light OCT (vis-OCT).

Denoising

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