Search Results for author:
Found 39 papers, 11 papers with code
GSLoc: Efficient Camera Pose Refinement via 3D Gaussian Splatting
We leverage 3D Gaussian Splatting (3DGS) as a scene representation and propose a novel test-time camera pose refinement framework, GSLoc.
SSRFlow: Semantic-aware Fusion with Spatial Temporal Re-embedding for Real-world Scene Flow
Scene flow, which provides the 3D motion field of the first frame from two consecutive point clouds, is vital for dynamic scene perception.
VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark
In this paper, we provide a large audio-visual speaker recognition dataset, VoxBlink2, which includes approximately 10M utterances with videos from 110K+ speakers in the wild.
MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation
Our study analyzed two common benchmarks, HumanEval and MBPP, and found that these might not thoroughly evaluate LLMs' code generation capacities due to limitations in quality, difficulty, and granularity.
GluMarker: A Novel Predictive Modeling of Glycemic Control Through Digital Biomarkers
This leaves a gap in expanding the scope of digital biomarkers for overall glycemic control in diabetes management.
Toward Short-Term Glucose Prediction Solely Based on CGM Time Series
The global diabetes epidemic highlights the importance of maintaining good glycemic control.
CrossGP: Cross-Day Glucose Prediction Excluding Physiological Information
Because diabetes may develop into potential serious complications, early glucose prediction for diabetic patients is necessary for timely medical treatment.
VeTraSS: Vehicle Trajectory Similarity Search Through Graph Modeling and Representation Learning
Trajectory similarity search plays an essential role in autonomous driving, as it enables vehicles to analyze the information and characteristics of different trajectories to make informed decisions and navigate safely in dynamic environments.
Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds
3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to annotating new domains.
STARFlow: Spatial Temporal Feature Re-embedding with Attentive Learning for Real-world Scene Flow
Scene flow prediction is a crucial underlying task in understanding dynamic scenes as it offers fundamental motion information.
Multi-Input Multi-Output Target-Speaker Voice Activity Detection For Unified, Flexible, and Robust Audio-Visual Speaker Diarization
The proposed method can take audio-visual input and leverage the speaker's acoustic footprint or lip track to flexibly conduct audio-based, video-based, and audio-visual speaker diarization in a unified sequence-to-sequence framework.
DiffLoc: Diffusion Model for Outdoor LiDAR Localization
We recognize APR's lack of robust features learning and iterative denoising process leads to suboptimal results.
SAIC: Integration of Speech Anonymization and Identity Classification
Speech anonymization and de-identification have garnered significant attention recently, especially in the healthcare area including telehealth consultations, patient voiceprint matching, and patient real-time monitoring.
FT2TF: First-Person Statement Text-To-Talking Face Generation
This achievement highlights our model capability to bridge first-person statements and dynamic face generation, providing insightful guidance for future work.
AV-MaskEnhancer: Enhancing Video Representations through Audio-Visual Masked Autoencoder
Learning high-quality video representation has shown significant applications in computer vision and remains challenging.
Masked Cross-image Encoding for Few-shot Segmentation
Few-shot segmentation (FSS) is a dense prediction task that aims to infer the pixel-wise labels of unseen classes using only a limited number of annotated images.
Ranked #27 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
The DKU-MSXF Diarization System for the VoxCeleb Speaker Recognition Challenge 2023
This paper describes the DKU-MSXF submission to track 4 of the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23).
VoxBlink: A Large Scale Speaker Verification Dataset on Camera
In this paper, we introduce a large-scale and high-quality audio-visual speaker verification dataset, named VoxBlink.
Hybrid Transformer and CNN Attention Network for Stereo Image Super-resolution
Multi-stage strategies are frequently employed in image restoration tasks.
OPDN: Omnidirectional Position-aware Deformable Network for Omnidirectional Image Super-Resolution
Model A aims to enhance the feature extraction ability of 360{\deg} image positional information, while Model B further focuses on the high-frequency information of 360{\deg} images.
Target-Speaker Voice Activity Detection via Sequence-to-Sequence Prediction
Target-speaker voice activity detection is currently a promising approach for speaker diarization in complex acoustic environments.
GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flow
Scene flow represents the motion information of each point in the 3D point clouds.
The DKU-DukeECE Diarization System for the VoxCeleb Speaker Recognition Challenge 2022
This paper discribes the DKU-DukeECE submission to the 4th track of the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22).
H2-Stereo: High-Speed, High-Resolution Stereoscopic Video System
We utilize a disparity network to transfer spatiotemporal information across views even in large disparity scenes, based on which, we propose disparity-guided flow-based warping for LSR-HFR view and complementary warping for HSR-LFR view.
Multi-Graph Fusion Networks for Urban Region Embedding
Human mobility data contains rich but abundant information, which yields to the comprehensive region embeddings for cross domain tasks.
DLA-Net: Learning Dual Local Attention Features for Semantic Segmentation of Large-Scale Building Facade Point Clouds
As there is a lack of 3D point clouds datasets related to the fine-grained building facade, we construct the first large-scale building facade point clouds benchmark dataset for semantic segmentation.
Outage Constrained Robust Secure Beamforming in Cognitive Satellite-Aerial Networks
This paper proposes a robust beamforming scheme to enhance the physical layer security (PLS) of multicast transmission in a cognitive satellite and aerial network (CSAN) operating in the millimeter wave frequency band.
The evolution of network controllability in growing networks
The study of network structural controllability focuses on the minimum number of driver nodes needed to control a whole network.
Physics and Society
DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization
Long-Term visual localization under changing environments is a challenging problem in autonomous driving and mobile robotics due to season, illumination variance, etc.
RWF-2000: An Open Large Scale Video Database for Violence Detection
In recent years, surveillance cameras are widely deployed in public places, and the general crime rate has been reduced significantly due to these ubiquitous devices.
Ranked #6 on
Activity Recognition
on RWF-2000
Bacteria Biotope Relation Extraction via Lexical Chains and Dependency Graphs
abstract In this article, we describe our approach for the Bacteria Biotopes relation extraction (BB-rel) subtask in the BioNLP Shared Task 2019.
A Dual Camera System for High Spatiotemporal Resolution Video Acquisition
This paper presents a dual camera system for high spatiotemporal resolution (HSTR) video acquisition, where one camera shoots a video with high spatial resolution and low frame rate (HSR-LFR) and another one captures a low spatial resolution and high frame rate (LSR-HFR) video.
RF-Net: An End-to-End Image Matching Network based on Receptive Field
This paper proposes a new end-to-end trainable matching network based on receptive field, RF-Net, to compute sparse correspondence between images.
Learned Quality Enhancement via Multi-Frame Priors for HEVC Compliant Low-Delay Applications
Networked video applications, e. g., video conferencing, often suffer from poor visual quality due to unexpected network fluctuation and limited bandwidth.
LO-Net: Deep Real-time Lidar Odometry
We present a novel deep convolutional network pipeline, LO-Net, for real-time lidar odometry estimation.
Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
In the second iteration of the competition in 2018, university teams advanced the state of the art by using context in dialog models, leveraging knowledge graphs for language understanding, handling complex utterances, building statistical and hierarchical dialog managers, and leveraging model-driven signals from user responses.
On Evaluating and Comparing Open Domain Dialog Systems
In this paper, we propose a comprehensive evaluation strategy with multiple metrics designed to reduce subjectivity by selecting metrics which correlate well with human judgement.
Conversational AI: The Science Behind the Alexa Prize
This paper outlines the advances created by the university teams as well as the Alexa Prize team to achieve the common goal of solving the problem of Conversational
Partial Procedural Geometric Model Fitting for Point Clouds
However, most geometric model fitting methods are unable to fit an arbitrary geometric model (e. g. a surface with holes) to incomplete data, due to that the similarity metrics used in these methods are unable to measure the rigid partial similarity between arbitrary models.
