Search Results for author:
Found 44 papers, 13 papers with code
AgentPolyp: Accurate Polyp Segmentation via Image Enhancement Agent
Since human and environmental factors interfere, captured polyp images usually suffer from issues such as dim lighting, blur, and overexposure, which pose challenges for downstream polyp segmentation tasks.
DanceMosaic: High-Fidelity Dance Generation with Multimodal Editability
Recent advances in dance generation have enabled automatic synthesis of 3D dance motions.
Ranked #1 on
Motion Synthesis
on FineDance
UAKNN: Label Distribution Learning via Uncertainty-Aware KNN
Label Distribution Learning (LDL) aims to characterize the polysemy of an instance by building a set of descriptive degrees corresponding to the instance.
LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives
This review, for the first time, adopts a unified weakly supervised learning perspective to systematically examine research on both LiDAR interpretation and inversion.
PolypFlow: Reinforcing Polyp Segmentation with Flow-Driven Dynamics
Accurate polyp segmentation remains challenging due to irregular lesion morphologies, ambiguous boundaries, and heterogeneous imaging conditions.
mmCooper: A Multi-agent Multi-stage Communication-efficient and Collaboration-robust Cooperative Perception Framework
Collaborative perception significantly enhances individual vehicle perception performance through the exchange of sensory information among agents.
BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos
Recent advancements in 3D human pose estimation from single-camera images and videos have relied on parametric models, like SMPL.
Ranked #4 on
3D Human Pose Estimation
on EMDB
MS-Temba : Multi-Scale Temporal Mamba for Efficient Temporal Action Detection
In this work, we innovatively adapt the Mamba architecture for action detection and propose Multi-scale Temporal Mamba (MS-Temba), comprising two key components: Temporal Mamba (Temba) Blocks and the Temporal Mamba Fuser.
Exploiting Aggregation and Segregation of Representations for Domain Adaptive Human Pose Estimation
To cope with the label deficiency issue, one common solution is to train the HPE models with easily available synthetic datasets (source) and apply them to real-world data (target) through domain adaptation (DA).
GenHMR: Generative Human Mesh Recovery
HMR from monocular images has predominantly been addressed by deterministic methods that output a single prediction for a given 2D image.
Ranked #3 on
3D Human Pose Estimation
on EMDB
MMHMR: Generative Masked Modeling for Hand Mesh Recovery
Traditional discriminative methods, which learn a deterministic mapping from a 2D image to a single 3D mesh, often struggle with the inherent ambiguities in 2D-to-3D mapping.
Disentangled-Transformer: An Explainable End-to-End Automatic Speech Recognition Model with Speech Content-Context Separation
End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
ControlMM: Controllable Masked Motion Generation
To further enhance control precision, we introduce inference-time logit editing, which manipulates the predicted conditional motion distribution so that the generated motion, sampled from the adjusted distribution, closely adheres to the input control signals.
MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning
We introduce a novel federated learning framework, named Multimodal Large Language Model Assisted Federated Learning (MLLM-LLaVA-FL), which employs powerful MLLMs at the server end to address the heterogeneous and long-tailed challenges.
Learning Traffic Crashes as Language: Datasets, Benchmarks, and What-if Causal Analyses
Leveraging this rich dataset, we further formulate the crash event feature learning as a novel text reasoning problem and further fine-tune various large language models (LLMs) to predict detailed accident outcomes, such as crash types, severity and number of injuries, based on contextual and environmental factors.
Diffusion Gaussian Mixture Audio Denoise
To overcome these challenges, we propose a DiffGMM model, a denoising model based on the diffusion and Gaussian mixture models.
LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living
To address this, we propose a semi-automated framework for curating ADL datasets, creating ADL-X, a multiview, multimodal RGBS instruction-tuning dataset.
BAMM: Bidirectional Autoregressive Motion Model
To address these challenges, we propose Bidirectional Autoregressive Motion Model (BAMM), a novel text-to-motion generation framework.
Ranked #7 on
Motion Synthesis
on KIT Motion-Language
MMM: Generative Masked Motion Model
MMM consists of two key components: (1) a motion tokenizer that transforms 3D human motion into a sequence of discrete tokens in latent space, and (2) a conditional masked motion transformer that learns to predict randomly masked motion tokens, conditioned on the pre-computed text tokens.
Ranked #13 on
Motion Synthesis
on KIT Motion-Language
DPATD: Dual-Phase Audio Transformer for Denoising
Recent high-performance transformer-based speech enhancement models demonstrate that time domain methods could achieve similar performance as time-frequency domain methods.
DiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from Videos
While image-based HMR methods have achieved impressive results, they often struggle to recover humans in dynamic scenarios, leading to temporal inconsistencies and non-smooth 3D motion predictions due to the absence of human motion.
Ranked #66 on
3D Human Pose Estimation
on 3DPW
A Modular Multi-stage Lightweight Graph Transformer Network for Human Pose and Shape Estimation from 2D Human Pose
In this research, we address the challenge faced by existing deep learning-based human mesh reconstruction methods in balancing accuracy and computational efficiency.
Skeleton-based Human Action Recognition via Convolutional Neural Networks (CNN)
Recently, there has been a remarkable increase in the interest towards skeleton-based action recognition within the research community, owing to its various advantageous features, including computational efficiency, representative features, and illumination invariance.
GaitSADA: Self-Aligned Domain Adaptation for mmWave Gait Recognition
mmWave radar-based gait recognition is a novel user identification method that captures human gait biometrics from mmWave radar return signals.
GaitMixer: Skeleton-based Gait Representation Learning via Wide-spectrum Multi-axial Mixer
Most existing gait recognition methods are appearance-based, which rely on the silhouettes extracted from the video data of human walking activities.
Ranked #9 on
Multiview Gait Recognition
on CASIA-B
Exploring Parameter-Efficient Fine-Tuning to Enable Foundation Models in Federated Learning
Recently, the use of small pre-trained models has been shown to be effective in federated learning optimization and improving convergence.
Quantum Feature Extraction for THz Multi-Layer Imaging
A learning-based THz multi-layer imaging has been recently used for contactless three-dimensional (3D) positioning and encoding.
Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding
End-to-end spoken language understanding (SLU) systems benefit from pretraining on large corpora, followed by fine-tuning on application-specific data.
Deep learning on rail profiles matching
Matching the rail cross-section profiles measured on site with the designed profile is a must to evaluate the wear of the rail, which is very important for track maintenance and rail safety.
AutoQML: Automated Quantum Machine Learning for Wi-Fi Integrated Sensing and Communications
Commercial Wi-Fi devices can be used for integrated sensing and communications (ISAC) to jointly exchange data and monitor indoor environment.
Quantum Transfer Learning for Wi-Fi Sensing
Beyond data communications, commercial-off-the-shelf Wi-Fi devices can be used to monitor human activities, track device locomotion, and sense the ambient environment.
Exploiting Temporal Relations on Radar Perception for Autonomous Driving
We consider the object recognition problem in autonomous driving using automotive radar sensors.
Ranked #2 on
Multiple Object Tracking
on RADIATE
Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning
To alleviate this issue, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by introducing a variety of proximal terms, some incurring considerable compute and/or memory overheads, to restrain local updates with respect to the global model.
A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose
We propose a pose analysis module that uses graph transformers to exploit structured and implicit joint correlations, and a mesh regression module that combines the extracted pose feature with the mesh template to reconstruct the final human mesh.
Ranked #71 on
3D Human Pose Estimation
on 3DPW
Sim-to-Real Transfer in Multi-agent Reinforcement Networking for Federated Edge Computing
Federated Learning (FL) over wireless multi-hop edge computing networks, i. e., multi-hop FL, is a cost-effective distributed on-device deep learning paradigm.
EdgeML: Towards Network-Accelerated Federated Learning over Wireless Edge
To solve such MDP, multi-agent reinforcement learning (MA-RL) algorithms along with domain-specific action space refining schemes are developed, which online learn the delay-minimum forwarding paths to minimize the model exchange latency between the edge devices (i. e., workers) and the remote server.
A Study into Pre-training Strategies for Spoken Language Understanding on Dysarthric Speech
The acoustic model is pre-trained in two stages: initialization with a corpus of normal speech and finetuning on a mixture of dysarthric and normal speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations
MutualNet is a general training methodology that can be applied to various network structures (e. g., 2D networks: MobileNets, ResNet, 3D networks: SlowFast, X3D) and various tasks (e. g., image classification, object detection, segmentation, and action recognition), and is demonstrated to achieve consistent improvements on a variety of datasets.
Pre-training for low resource speech-to-intent applications
In this paper we combine the encoder of an end-to-end ASR system with the prior NMF/capsule network-based user-taught decoder, and investigate whether pre-training methodology can reduce training data requirements for the NMF and capsule network.
KST-GCN: A Knowledge-Driven Spatial-Temporal Graph Convolutional Network for Traffic Forecasting
On this background, this study presents a knowledge representation-driven traffic forecasting method based on spatial-temporal graph convolutional networks.
AST-GCN: Attribute-Augmented Spatiotemporal Graph Convolutional Network for Traffic Forecasting
Traffic forecasting is a fundamental and challenging task in the field of intelligent transportation.
Deep CSI Learning for Gait Biometric Sensing and Recognition
Gait is a person's natural walking style and a complex biological process that is unique to each person.
T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction
However, traffic forecasting has always been considered an open scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time, namely, spatial dependence and temporal dependence.
Ranked #4 on
Traffic Prediction
on SZ-Taxi
Pattern-Coupled Sparse Bayesian Learning for Recovery of Block-Sparse Signals
In this paper, we develop a new sparse Bayesian learning method for recovery of block-sparse signals with unknown cluster patterns.
