Search Results for author:
Found 75 papers, 24 papers with code
Terahertz Aerospace Communications: Enabling Technologies and Future Directions
To achieve ubiquitous connectivity in next-generation networks through aerospace communications while maintaining high data rates, Terahertz (THz) band communications (0. 1-10 THz) with large continuous bandwidths are considered a promising candidate technology.
Joint Communication and Radar Sensing for Terahertz Space-Air-Ground Integrated Networks (SAGIN)
The transition from isolated systems to integrated solutions has driven the development of space-air-ground integrated networks (SAGIN) as well as the integration of communication and radar sensing functionalities.
Anatomical grounding pre-training for medical phrase grounding
Medical Phrase Grounding (MPG) maps radiological findings described in medical reports to specific regions in medical images.
Large Language Model for Lossless Image Compression with Visual Prompts
However, a significant challenge remains in bridging the gap between the textual prior knowledge within LLMs and lossless image compression.
Learnable Residual-based Latent Denoising in Semantic Communication
A latent denoising semantic communication (SemCom) framework is proposed for robust image transmission over noisy channels.
S2CFormer: Reorienting Learned Image Compression from Spatial Interaction to Channel Aggregation
Transformers have achieved significant success in learned image compression (LIC), with Swin Transformers emerging as the mainstream choice for nonlinear transforms.
Benchmarking Randomized Optimization Algorithms on Binary, Permutation, and Combinatorial Problem Landscapes
In this paper, we evaluate the performance of four randomized optimization algorithms: Randomized Hill Climbing (RHC), Simulated Annealing (SA), Genetic Algorithms (GA), and MIMIC (Mutual Information Maximizing Input Clustering), across three distinct types of problems: binary, permutation, and combinatorial.
AsymLLIC: Asymmetric Lightweight Learned Image Compression
Learned image compression (LIC) methods often employ symmetrical encoder and decoder architectures, evitably increasing decoding time.
Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression
Neural image compression often faces a challenging trade-off among rate, distortion and perception.
OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones?
We introduce OBI-Bench, a holistic benchmark crafted to systematically evaluate large multi-modal models (LMMs) on whole-process oracle bone inscriptions (OBI) processing tasks demanding expert-level domain knowledge and deliberate cognition.
Face De-identification: State-of-the-art Methods and Comparative Studies
The widespread use of image acquisition technologies, along with advances in facial recognition, has raised serious privacy concerns.
WDMoE: Wireless Distributed Mixture of Experts for Large Language Models
In this paper, we propose a wireless distributed Mixture of Experts (WDMoE) architecture to enable collaborative deployment of LLMs across edge servers at the base station (BS) and mobile devices in wireless networks.
Beyond Point Annotation: A Weakly Supervised Network Guided by Multi-Level Labels Generated from Four-Point Annotation for Thyroid Nodule Segmentation in Ultrasound Image
Weakly-supervised methods typically guided the pixel-wise training by comparing the predictions to single-level labels containing diverse segmentation-related information at once, but struggled to represent delicate feature differences between nodule and background regions and confused incorrect information, resulting in underfitting or overfitting in the segmentation predictions.
Two Birds with One Stone: Multi-Task Semantic Communications Systems over Relay Channel
In the MTML-RSC scheme, the source node broadcasts a signal using semantic communications, and the relay node forwards the signal to the destination.
MambaJSCC: Adaptive Deep Joint Source-Channel Coding with Generalized State Space Model
Lightweight and efficient neural network models for deep joint source-channel coding (JSCC) are crucial for semantic communications.
Blockchain-Enabled Variational Information Bottleneck for Data Extraction Based on Mutual Information in Internet of Vehicles
The Internet of Vehicles (IoV) network can address the issue of limited computing resources and data processing capabilities of individual vehicles, but it also brings the risk of privacy leakage to vehicle users.
Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild
RichIQA is characterized by two key novel designs: (1) a three-stage image quality prediction network which exploits the powerful feature representation capability of the Convolutional vision Transformer (CvT) and mimics the short-term and long-term memory mechanisms of human brain; (2) a multi-label training strategy in which rich subjective quality information like MOS, SOS and DOS are concurrently used to train the quality prediction network.
S4D: Streaming 4D Real-World Reconstruction with Gaussians and 3D Control Points
To address these challenges, we introduce a novel approach for streaming 4D real-world reconstruction utilizing discrete 3D control points.
PhysMamba: State Space Duality Model for Remote Physiological Measurement
Remote Photoplethysmography (rPPG) enables non-contact physiological signal extraction from facial videos, offering applications in psychological state analysis, medical assistance, and anti-face spoofing.
Distributed Deep Reinforcement Learning Based Gradient Quantization for Federated Learning Enabled Vehicle Edge Computing
Federated Learning (FL) can protect the privacy of the vehicles in vehicle edge computing (VEC) to a certain extent through sharing the gradients of vehicles' local models instead of local data.
MRIR: Integrating Multimodal Insights for Diffusion-based Realistic Image Restoration
In this work, we delve into the potential of utilizing pre-trained stable diffusion for image restoration and propose MRIR, a diffusion-based restoration method with multimodal insights.
Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration
Image restoration is a classic low-level problem aimed at recovering high-quality images from low-quality images with various degradations such as blur, noise, rain, haze, etc.
Multi-User Semantic Fusion for Semantic Communications over Degraded Broadcast Channels
In the proposed method, the transmitter extracts semantic features for two users separately.
GAIA: Rethinking Action Quality Assessment for AI-Generated Videos
Assessing action quality is both imperative and challenging due to its significant impact on the quality of AI-generated videos, further complicated by the inherently ambiguous nature of actions within AI-generated video (AIGV).
Robust Image Semantic Coding with Learnable CSI Fusion Masking over MIMO Fading Channels
In this paper, we incorporate MIMO CSI into system designs from a new perspective and propose the learnable CSI fusion semantic communication (LCFSC) framework, where CSI is treated as side information by the semantic extractor to enhance the semantic coding.
In-Context Translation: Towards Unifying Image Recognition, Processing, and Generation
Secondly, it standardizes the training of different tasks into a general in-context learning, where "in-context" means the input comprises an example input-output pair of the target task and a query image.
MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with its Application for Colonic Polyp Image Segmentation
In the study reported in this paper, based on the well-known hybridization principle, we proposed a method to combine CNN and Transformer to retain the strengths of both, and we applied this method to build a system called MugenNet for colonic polyp image segmentation.
MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model
With the evolution of storage and communication protocols, ultra-low bitrate image compression has become a highly demanding topic.
Pragmatic Communication in Multi-Agent Collaborative Perception
Following this strategy, we first formulate a mathematical optimization framework for the perception-communication trade-off and then propose PragComm, a multi-agent collaborative perception system with two key components: i) single-agent detection and tracking and ii) pragmatic collaboration.
Exploring the Naturalness of AI-Generated Images
In this paper, we take the first step to benchmark and assess the visual naturalness of AI-generated images.
FS-BAND: A Frequency-Sensitive Banding Detector
Banding artifact, as known as staircase-like contour, is a common quality annoyance that happens in compression, transmission, etc.
Detecting Abrupt Change of Channel Covariance Matrix in IRS-Assisted Communication
We first categorize two types of channel covariance matrix changes based on their impact on system design: Type I change, which denotes the change in the BS receive covariance matrix, and Type II change, which denotes the change in the IRS transmit/receive covariance matrix.
Communication-Efficient Framework for Distributed Image Semantic Wireless Transmission
Multi-node communication, which refers to the interaction among multiple devices, has attracted lots of attention in many Internet-of-Things (IoT) scenarios.
DocDeshadower: Frequency-Aware Transformer for Document Shadow Removal
Shadows in scanned documents pose significant challenges for document analysis and recognition tasks due to their negative impact on visual quality and readability.
Interruption-Aware Cooperative Perception for V2X Communication-Aided Autonomous Driving
To achieve comprehensive recovery, we design a communication-adaptive multi-scale spatial-temporal prediction model to extract multi-scale spatial-temporal features based on V2X communication conditions and capture the most significant information for the prediction of the missing information.
Boosting Video Object Segmentation via Space-time Correspondence Learning
Current top-leading solutions for video object segmentation (VOS) typically follow a matching-based regime: for each query frame, the segmentation mask is inferred according to its correspondence to previously processed and the first annotated frames.
Freestyle Layout-to-Image Synthesis
In this work, we explore the freestyle capability of the model, i. e., how far can it generate unseen semantics (e. g., classes, attributes, and styles) onto a given layout, and call the task Freestyle LIS (FLIS).
Frequency-Modulated Point Cloud Rendering with Easy Editing
We develop an effective point cloud rendering pipeline for novel view synthesis, which enables high fidelity local detail reconstruction, real-time rendering and user-friendly editing.
USR: Unsupervised Separated 3D Garment and Human Reconstruction via Geometry and Semantic Consistency
To address these issues, we propose an unsupervised separated 3D garments and human reconstruction model (USR), which reconstructs the human body and authentic textured clothes in layers without 3D models.
AudioEar: Single-View Ear Reconstruction for Personalized Spatial Audio
To this end, we propose to achieve personalized spatial audio by reconstructing 3D human ears with single-view images.
Learning Shape Primitives via Implicit Convexity Regularization
In this work, a novel regularization term named Implicit Convexity Regularization (ICR) imposed on implicit primitive learning is proposed to tackle this problem.
GARF:Geometry-Aware Generalized Neural Radiance Field
To address these issues, we propose Geometry-Aware Generalized Neural Radiance Field (GARF) with a geometry-aware dynamic sampling (GADS) strategy to perform real-time novel view rendering and unsupervised depth estimation on unseen scenes without per-scene optimization.
Boosting Point Clouds Rendering via Radiance Mapping
In this work, we focus on boosting the image quality of point clouds rendering with a compact model design.
Collaborative Perception for Autonomous Driving: Current Status and Future Trend
Perception is one of the crucial module of the autonomous driving system, which has made great progress recently.
Latency-Aware Collaborative Perception
Collaborative perception has recently shown great potential to improve perception capabilities over single-agent perception.
Detecting Abrupt Changes in Channel Covariance Matrix for MIMO Communication
Our paper aims to adopt the classic change detection theory to detect the change in the channel covariance matrix as accurately and quickly as possible such that the new covariance matrix can be re-estimated in time.
Pricing Path-dependent Options under Stochastic Volatility via Mellin Transform
In this paper, we derive closed-form formulas of first-order approximation for down-and-out barrier and floating strike lookback put option prices under a stochastic volatility model, by using an asymptotic approach.
Remember Intentions: Retrospective-Memory-based Trajectory Prediction
However, in this way, the model parameters come from all seen instances, which means a huge amount of irrelevant seen instances might also involve in predicting the current situation, disturbing the performance.
Ranked #7 on
Trajectory Prediction
on Stanford Drone
Enhanced Preamble Based MAC Mechanism for IIoT-oriented PLC Network
Finally, with our work, a PLC network based on E-PMAC mechanism can be realized.
Representation-Agnostic Shape Fields
In this study, we present Representation-Agnostic Shape Fields (RASF), a generalizable and computation-efficient shape embedding module for 3D deep learning.
Gradient Correction beyond Gradient Descent
GCGD consists of two plug-in modules: 1) inspired by the idea of gradient prediction, we propose a \textbf{GC-W} module for weight gradient correction; 2) based on Neural ODE, we propose a \textbf{GC-ODE} module for hidden states gradient correction.
Random Access with Massive MIMO-OTFS in LEO Satellite Communications
Next, by exploring the sparsity of channel in the delay-Doppler-angle domain, a two-dimensional pattern coupled hierarchical prior with the sparse Bayesian learning and covariance-free method (TDSBL-CF) is developed for the channel estimation.
Learning Distilled Collaboration Graph for Multi-Agent Perception
Our approach is validated on V2X-Sim 1. 0, a large-scale multi-agent perception dataset that we synthesized using CARLA and SUMO co-simulation.
Ranked #3 on
3D Object Detection
on V2X-SIM
Detection of Abrupt Change in Channel Covariance Matrix for Multi-Antenna Communication
This result verifies the possibility to detect the channel covariance change both accurately and quickly in practice.
Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement
For a given unsupervised task, we design multilevel tasks and define different learning stages for the deep network.
3D Human Action Representation Learning via Cross-View Consistency Pursuit
In this work, we propose a Cross-view Contrastive Learning framework for unsupervised 3D skeleton-based action Representation (CrosSCLR), by leveraging multi-view complementary supervision signal.
A More Fine-Grained Aspect-Sentiment-Opinion Triplet Extraction Task
Aspect Sentiment Triplet Extraction (ASTE) aims to extract aspect term, sentiment and opinion term triplets from sentences and tries to provide a complete solution for aspect-based sentiment analysis (ABSA).
Ranked #1 on
Aspect-Sentiment-Opinion Triplet Extraction
on Res14
Aspect-Based Sentiment Analysis
Aspect-Sentiment-Opinion Triplet Extraction
+3
Skeleton2Mesh: Kinematics Prior Injected Unsupervised Human Mesh Recovery
The challenges of the latter task are two folds: (1) pose failure (i. e., pose mismatching -- different skeleton definitions in dataset and SMPL , and pose ambiguity -- endpoints have arbitrary joint angle configurations for the same 3D joint coordinates).
Towards Alleviating the Modeling Ambiguity of Unsupervised Monocular 3D Human Pose Estimation
Furthermore, two temporal constraints are proposed to alleviate the scale and pose ambiguity respectively.
Monocular 3D Human Pose Estimation
Unsupervised 3D Human Pose Estimation
Geometric Granularity Aware Pixel-To-Mesh
Pixel-to-mesh has wide applications, especially in virtual or augmented reality, animation and game industry.
GraphSAD: Learning Graph Representations with Structure-Attribute Disentanglement
We propose to disentangle graph structure and node attributes into two distinct sets of representations, and such disentanglement can be done in either the input or the embedding space.
Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation
Transferring knowledges learned from multiple source domains to target domain is a more practical and challenging task than conventional single-source domain adaptation.
Domain Adaptation
Multi-Source Unsupervised Domain Adaptation
Cross-domain Detection via Graph-induced Prototype Alignment
To mitigate these problems, we propose a Graph-induced Prototype Alignment (GPA) framework to seek for category-level domain alignment via elaborate prototype representations.
Toward Better Understanding of Saliency Prediction in Augmented 360 Degree Videos
The saliency annotations of head and eye movements for both original and augmented videos are collected and together constitute the ARVR dataset.
Adversarial Domain Adaptation with Domain Mixup
In this paper, we present adversarial domain adaptation with domain mixup (DM-ADA), which guarantees domain-invariance in a more continuous latent space and guides the domain discriminator in judging samples' difference relative to source and target domains.
Towards Locally Consistent Object Counting with Constrained Multi-stage Convolutional Neural Networks
Towards this problem, in this paper we propose a constrained multi-stage Convolutional Neural Networks (CNNs) to jointly pursue locally consistent density map from two aspects.
Online Multi-Object Tracking with Dual Matching Attention Networks
In this paper, we propose an online Multi-Object Tracking (MOT) approach which integrates the merits of single object tracking and data association methods in a unified framework to handle noisy detections and frequent interactions between targets.
Ranked #5 on
Online Multi-Object Tracking
on MOT16
Learning an Inverse Tone Mapping Network with a Generative Adversarial Regularizer
Transferring a low-dynamic-range (LDR) image to a high-dynamic-range (HDR) image, which is the so-called inverse tone mapping (iTM), is an important imaging technique to improve visual effects of imaging devices.
Multi-Scale Spatially-Asymmetric Recalibration for Image Classification
Convolution is spatially-symmetric, i. e., the visual features are independent of its position in the image, which limits its ability to utilize contextual cues for visual recognition.
Performance Guaranteed Network Acceleration via High-Order Residual Quantization
Input binarization has shown to be an effective way for network acceleration.
SORT: Second-Order Response Transform for Visual Recognition
In this paper, we reveal the importance and benefits of introducing second-order operations into deep neural networks.
Deep Collaborative Learning for Visual Recognition
We formulate the function of a convolutional layer as learning a large visual vocabulary, and propose an alternative way, namely Deep Collaborative Learning (DCL), to reduce the computational complexity.
Pricing variance swaps with stochastic volatility and stochastic interest rate under full correlation structure
This paper considers the case of pricing discretely-sampled variance swaps under the class of equity-interest rate hybridization.
Improving a Credit Scoring Model by Incorporating Bank Statement Derived Features
In this paper, we investigate the extent to which features derived from bank statements provided by loan applicants, and which are not declared on an application form, can enhance a credit scoring model for a New Zealand lending company.
