Search Results for author:
Found 29 papers, 9 papers with code
"Security for Everyone" in Finite Blocklength IRS-aided Systems With Perfect and Imperfect CSI
The problem is even more difficult under finite blocklength constraints that are popular in ultra-reliable low-latency communication (URLLC) and massive machine-type communications (mMTC).
SPAC-Net: Rethinking Point Cloud Completion with Structural Prior
Point cloud completion aims to infer a complete shape from its partial observation.
Enhanced Over-the-Air Federated Learning Using AI-based Fluid Antenna System
This paper investigates an over-the-air federated learning (OTA-FL) system that employs fluid antennas (FAs) at an access point.
Large Language Models in the Clinic: A Comprehensive Benchmark
The adoption of large language models (LLMs) to assist clinicians has attracted remarkable attention.
RHanDS: Refining Malformed Hands for Generated Images with Decoupled Structure and Style Guidance
The style guidance is a hand image, e. g., the malformed hand itself, and is employed to furnish the style reference for hand refining.
Auto-Encoder Optimized PAM IM/DD Transceivers for Amplified Fiber Links
We present an experimental validation of 4 dB improvement of an ASE-limited PAM4 at 60 Gbaud using an optimized constellation and a NN decoder.
Physical Layer Security for NOMA Systems: Requirements, Issues, and Recommendations
Nevertheless, from a security view-point, when multiple users are utilizing the same time-frequency resource, there may be concerns regarding keeping information confidential.
Robust Ranking Explanations
Robust explanations of machine learning models are critical to establish human trust in the models.
EMEF: Ensemble Multi-Exposure Image Fusion
In the second stage, we tune the imitator network by optimizing the style code, in order to find an optimal fusion result for each input pair.
MusicFace: Music-driven Expressive Singing Face Synthesis
In this paper, we present a method for this task with natural motions of the lip, facial expression, head pose, and eye states.
Provable Robust Saliency-based Explanations
To foster trust in machine learning models, explanations must be faithful and stable for consistent insights.
PointCMC: Cross-Modal Multi-Scale Correspondences Learning for Point Cloud Understanding
To solve it, we proposed PointCMC, a novel cross-modal method to model multi-scale correspondences across modalities for self-supervised point cloud representation learning.
MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining
Second, masked self-distillation is also consistent with vision-language contrastive from the perspective of training objective as both utilize the visual encoder for feature aligning, and thus is able to learn local semantics getting indirect supervision from the language.
I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation
In this paper, we present the Intra- and Inter-Human Relation Networks (I^2R-Net) for Multi-Person Pose Estimation.
Ranked #2 on
Multi-Person Pose Estimation
on OCHuman
General Facial Representation Learning in a Visual-Linguistic Manner
In this paper, we study the transfer performance of pre-trained models on face analysis tasks and introduce a framework, called FaRL, for general Facial Representation Learning in a visual-linguistic manner.
Ranked #1 on
Face Parsing
on CelebAMask-HQ
(using extra training data)
FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning
In this paper, we propose a talking face generation method that takes an audio signal as input and a short target video clip as reference, and synthesizes a photo-realistic video of the target face with natural lip motions, head poses, and eye blinks that are in-sync with the input audio signal.
Exploring Temporal Coherence for More General Video Face Forgery Detection
The first stage is a fully temporal convolution network (FTCN).
Ranked #4 on
DeepFake Detection
on FakeAVCeleb
Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering
The prior of view-common variable obeys approximately discrete Gumbel Softmax distribution, which is introduced to extract the common cluster factor of multiple views.
Customizing Graph Neural Networks using Path Reweighting
Specifically, the proposed CustomGNN can automatically learn the high-level semantics for specific downstream tasks to highlight semantically relevant paths as well to filter out task-irrelevant noises in a graph.
UAV Communications for Sustainable Federated Learning
Finally, simulations illustrate the potential of our proposed UAV-SFL approach in providing a sustainable solution for FL-based wireless networks, and in reducing the UAV transmit power by 32. 95%, 63. 18%, and 78. 81% compared with the benchmarks.
Heatmap-based Vanishing Point boosts Lane Detection
Vision-based lane detection (LD) is a key part of autonomous driving technology, and it is also a challenging problem.
D-VPnet: A Network for Real-time Dominant Vanishing Point Detection in Natural Scenes
As an important part of linear perspective, vanishing points (VPs) provide useful clues for mapping objects from 2D photos to 3D space.
Unstructured Road Vanishing Point Detection Using the Convolutional Neural Network and Heatmap Regression
Unstructured road vanishing point (VP) detection is a challenging problem, especially in the field of autonomous driving.
Customized Graph Embedding: Tailoring Embedding Vectors to different Applications
For these applications, graph embedding is crucial as it provides vector representations of the graph.
Face Parsing with RoI Tanh-Warping
It uses hierarchical local based method for inner facial components and global methods for outer facial components.
Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention
To address these issues, we propose two attention models for human activity recognition: temporal attention and sensor attention.
Semi-Supervised Convolutional Neural Networks for Human Activity Recognition
Labeled data used for training activity recognition classifiers are usually limited in terms of size and diversity.
City-Identification of Flickr Videos Using Semantic Acoustic Features
In particular, we present a method to compute and use semantic acoustic features to perform city-identification and the features show semantic evidence of the identification.
Templateless Quasi-rigid Shape Modeling with Implicit Loop-Closure
We represent the shape motion by a deformation graph, and propose a model-to-part method to gradually integrate sampled points of depth scans into the deformation graph.
