Picture for Xin Du

Xin Du

Prompt When the Animal is: Temporal Animal Behavior Grounding with Positional Recovery Training

Add code
May 09, 2024
Figure 1 for Prompt When the Animal is: Temporal Animal Behavior Grounding with Positional Recovery Training
Figure 2 for Prompt When the Animal is: Temporal Animal Behavior Grounding with Positional Recovery Training
Figure 3 for Prompt When the Animal is: Temporal Animal Behavior Grounding with Positional Recovery Training
Figure 4 for Prompt When the Animal is: Temporal Animal Behavior Grounding with Positional Recovery Training
Viaarxiv icon

LAECIPS: Large Vision Model Assisted Adaptive Edge-Cloud Collaboration for IoT-based Perception System

Add code
Apr 16, 2024
Figure 1 for LAECIPS: Large Vision Model Assisted Adaptive Edge-Cloud Collaboration for IoT-based Perception System
Figure 2 for LAECIPS: Large Vision Model Assisted Adaptive Edge-Cloud Collaboration for IoT-based Perception System
Figure 3 for LAECIPS: Large Vision Model Assisted Adaptive Edge-Cloud Collaboration for IoT-based Perception System
Figure 4 for LAECIPS: Large Vision Model Assisted Adaptive Edge-Cloud Collaboration for IoT-based Perception System
Viaarxiv icon

A Hierarchical Framework with Spatio-Temporal Consistency Learning for Emergence Detection in Complex Adaptive Systems

Add code
Jan 18, 2024
Viaarxiv icon

Digital Twin Brain: a simulation and assimilation platform for whole human brain

Add code
Aug 02, 2023
Viaarxiv icon

Physical-layer Adversarial Robustness for Deep Learning-based Semantic Communications

Add code
May 12, 2023
Figure 1 for Physical-layer Adversarial Robustness for Deep Learning-based Semantic Communications
Figure 2 for Physical-layer Adversarial Robustness for Deep Learning-based Semantic Communications
Figure 3 for Physical-layer Adversarial Robustness for Deep Learning-based Semantic Communications
Figure 4 for Physical-layer Adversarial Robustness for Deep Learning-based Semantic Communications
Viaarxiv icon

Cross-Modal Retrieval for Motion and Text via MildTriple Loss

Add code
May 07, 2023
Figure 1 for Cross-Modal Retrieval for Motion and Text via MildTriple Loss
Figure 2 for Cross-Modal Retrieval for Motion and Text via MildTriple Loss
Figure 3 for Cross-Modal Retrieval for Motion and Text via MildTriple Loss
Figure 4 for Cross-Modal Retrieval for Motion and Text via MildTriple Loss
Viaarxiv icon

Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaboration

Add code
Apr 22, 2023
Figure 1 for Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaboration
Figure 2 for Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaboration
Figure 3 for Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaboration
Figure 4 for Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaboration
Viaarxiv icon

ClassPruning: Speed Up Image Restoration Networks by Dynamic N:M Pruning

Add code
Nov 10, 2022
Viaarxiv icon

Modular Degradation Simulation and Restoration for Under-Display Camera

Add code
Sep 23, 2022
Figure 1 for Modular Degradation Simulation and Restoration for Under-Display Camera
Figure 2 for Modular Degradation Simulation and Restoration for Under-Display Camera
Figure 3 for Modular Degradation Simulation and Restoration for Under-Display Camera
Figure 4 for Modular Degradation Simulation and Restoration for Under-Display Camera
Viaarxiv icon

Rethinking Performance Gains in Image Dehazing Networks

Add code
Sep 23, 2022
Figure 1 for Rethinking Performance Gains in Image Dehazing Networks
Figure 2 for Rethinking Performance Gains in Image Dehazing Networks
Figure 3 for Rethinking Performance Gains in Image Dehazing Networks
Figure 4 for Rethinking Performance Gains in Image Dehazing Networks
Viaarxiv icon