Zhenguang Liu
YOU?
Author Swipe
View article: Insight into the excellent corrosion resistance of a new type of weathering steel in high chloride environment by dissolution-diffusion-deposition-synergy model
Insight into the excellent corrosion resistance of a new type of weathering steel in high chloride environment by dissolution-diffusion-deposition-synergy model Open
View article: OpenAVS: Training-Free Open-Vocabulary Audio Visual Segmentation with Foundational Models
OpenAVS: Training-Free Open-Vocabulary Audio Visual Segmentation with Foundational Models Open
Audio-visual segmentation aims to separate sounding objects from videos by predicting pixel-level masks based on audio signals. Existing methods primarily concentrate on closed-set scenarios and direct audio-visual alignment and fusion, wh…
View article: PhyCamo: A Robust Physical Camouflage via Contrastive Learning for Multi-View Physical Adversarial Attack
PhyCamo: A Robust Physical Camouflage via Contrastive Learning for Multi-View Physical Adversarial Attack Open
Deep neural networks (DNNs) have achieved remarkable success in widespread applications. Meanwhile, its vulnerability towards carefully crafted adversarial attacks captures special attention. Not only adversarial perturbations in digital s…
View article: MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation
MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation Open
Smart contracts, closely intertwined with cryptocurrency transactions, have sparked widespread concerns about considerable financial losses of security issues. To counteract this, a variety of tools have been developed to identify vulnerab…
View article: Optimizing Human Pose Estimation Through Focused Human and Joint Regions
Optimizing Human Pose Estimation Through Focused Human and Joint Regions Open
Human pose estimation has given rise to a broad spectrum of novel and compelling applications, including action recognition, sports analysis, as well as surveillance. However, accurate video pose estimation remains an open challenge. One a…
View article: HVIS: A Human-like Vision and Inference System for Human Motion Prediction
HVIS: A Human-like Vision and Inference System for Human Motion Prediction Open
Grasping the intricacies of human motion, which involve perceiving spatio-temporal dependence and multi-scale effects, is essential for predicting human motion. While humans inherently possess the requisite skills to navigate this issue, i…
View article: SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos
SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos Open
Human pose estimation in videos remains a challenge, largely due to the reliance on extensive manual annotation of large datasets, which is expensive and labor-intensive. Furthermore, existing approaches often struggle to capture long-rang…
View article: Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation
Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation Open
Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. Howeve…
View article: Towards blockchain interoperability: a comprehensive survey on cross-chain solutions
Towards blockchain interoperability: a comprehensive survey on cross-chain solutions Open
The rapid expansion of decentralized finance (DeFi) applications has catalyzed the emergence of new blockchain systems at an unprecedented pace. However, these systems are largely evolving in isolation, hindering the development of a cohes…
View article: HVIS: A Human-like Vision and Inference System for Human Motion Prediction
HVIS: A Human-like Vision and Inference System for Human Motion Prediction Open
Grasping the intricacies of human motion, which involve perceiving spatio-temporal dependence and multi-scale effects, is essential for predicting human motion. While humans inherently possess the requisite skills to navigate this issue, i…
View article: Optimizing Human Pose Estimation Through Focused Human and Joint Regions
Optimizing Human Pose Estimation Through Focused Human and Joint Regions Open
Human pose estimation has given rise to a broad spectrum of novel and compelling applications, including action recognition, sports analysis, as well as surveillance. However, accurate video pose estimation remains an open challenge. One a…
View article: SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos
SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos Open
Human pose estimation in videos remains a challenge, largely due to the reliance on extensive manual annotation of large datasets, which is expensive and labor-intensive. Furthermore, existing approaches often struggle to capture long-rang…
View article: Optimizing Human Pose Estimation Through Focused Human and Joint Regions
Optimizing Human Pose Estimation Through Focused Human and Joint Regions Open
Human pose estimation has given rise to a broad spectrum of novel and compelling applications, including action recognition, sports analysis, as well as surveillance. However, accurate video pose estimation remains an open challenge. One a…
View article: Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation
Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation Open
Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. Howeve…
View article: FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning
FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning Open
This work asks: with abundant, unlabeled real faces, how to learn a robust and transferable facial representation that boosts various face security tasks with respect to generalization performance? We make the first attempt and propose a s…
View article: Blockchain-based Federated Recommendation with Incentive Mechanism
Blockchain-based Federated Recommendation with Incentive Mechanism Open
Nowadays, federated recommendation technology is rapidly evolving to help multiple organisations share data and train models while meeting user privacy, data security and government regulatory requirements. However, federated recommendatio…
View article: ETGuard: Malicious Encrypted Traffic Detection in Blockchain-based Power Grid Systems
ETGuard: Malicious Encrypted Traffic Detection in Blockchain-based Power Grid Systems Open
The escalating prevalence of encryption protocols has led to a concomitant surge in the number of malicious attacks that hide in encrypted traffic. Power grid systems, as fundamental infrastructure, are becoming prime targets for such atta…
View article: Joint-Motion Mutual Learning for Pose Estimation in Videos
Joint-Motion Mutual Learning for Pose Estimation in Videos Open
Human pose estimation in videos has long been a compelling yet challenging task within the realm of computer vision. Nevertheless, this task remains difficult because of the complex video scenes, such as video defocus and self-occlusion. R…
View article: Multi-threshold deep metric learning for facial expression recognition
Multi-threshold deep metric learning for facial expression recognition Open
View article: Do As I Do: Pose Guided Human Motion Copy
Do As I Do: Pose Guided Human Motion Copy Open
Human motion copy is an intriguing yet challenging task in artificial intelligence and computer vision, which strives to generate a fake video of a target person performing the motion of a source person. The problem is inherently challengi…
View article: Multi-threshold Deep Metric Learning for Facial Expression Recognition
Multi-threshold Deep Metric Learning for Facial Expression Recognition Open
Effective expression feature representations generated by a triplet-based deep metric learning are highly advantageous for facial expression recognition (FER). The performance of triplet-based deep metric learning is contingent upon identi…
View article: Let All Be Whitened: Multi-Teacher Distillation for Efficient Visual Retrieval
Let All Be Whitened: Multi-Teacher Distillation for Efficient Visual Retrieval Open
Visual retrieval aims to search for the most relevant visual items, e.g., images and videos, from a candidate gallery with a given query item. Accuracy and efficiency are two competing objectives in retrieval tasks. Instead of crafting a n…
View article: Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection
Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection Open
Deepfake technology has given rise to a spectrum of novel and compelling applications. Unfortunately, the widespread proliferation of high-fidelity fake videos has led to pervasive confusion and deception, shattering our faith that seeing …
View article: GITPose: going shallow and deeper using vision transformers for human pose estimation
GITPose: going shallow and deeper using vision transformers for human pose estimation Open
In comparison to convolutional neural networks (CNN), the newly created vision transformer (ViT) has demonstrated impressive outcomes in human pose estimation (HPE). However, (1) there is a quadratic rise in complexity with respect to imag…
View article: Conan's Bow Tie: A Streaming Voice Conversion for Real-Time VTuber Livestreaming
Conan's Bow Tie: A Streaming Voice Conversion for Real-Time VTuber Livestreaming Open
Recent years have witnessed a dramatic growing trend of Virtual YouTubers (VTubers) as a new business on social media, such as YouTube, Twitch, and TikTok. However, a significant challenge arises when VTuber voice actors face health issues…
View article: Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection
Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection Open
Deepfake technology has given rise to a spectrum of novel and compelling applications. Unfortunately, the widespread proliferation of high-fidelity fake videos has led to pervasive confusion and deception, shattering our faith that seeing …
View article: Blockchain for finance: A survey
Blockchain for finance: A survey Open
As an innovative technology for enhancing authenticity, security, and risk management, blockchain is being widely adopted in trade and finance systems. The unique capabilities of blockchain, such as immutability and transparency, enable ne…
View article: Blockchain for Finance: A Survey
Blockchain for Finance: A Survey Open
As an innovative technology for enhancing authenticity, security, and risk management, blockchain is being widely adopted in trade and finance systems. The unique capabilities of blockchain, such as immutability and transparency, enable ne…
View article: Red Teaming Visual Language Models
Red Teaming Visual Language Models Open
VLMs (Vision-Language Models) extend the capabilities of LLMs (Large Language Models) to accept multimodal inputs. Since it has been verified that LLMs can be induced to generate harmful or inaccurate content through specific test cases (t…
View article: Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrieval
Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrieval Open
Visual retrieval aims to search for the most relevant visual items, e.g., images and videos, from a candidate gallery with a given query item. Accuracy and efficiency are two competing objectives in retrieval tasks. Instead of crafting a n…