Picture for Yixin Zhang

Yixin Zhang

Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach

Add code
Dec 21, 2023
Viaarxiv icon

How to Efficiently Annotate Images for Best-Performing Deep Learning Based Segmentation Models: An Empirical Study with Weak and Noisy Annotations and Segment Anything Model

Dec 20, 2023
Viaarxiv icon

Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations

Add code
Nov 22, 2023
Figure 1 for Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations
Figure 2 for Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations
Figure 3 for Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations
Figure 4 for Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations
Viaarxiv icon

On the IRS Deployment in Smart Factories Considering Blockage Effects: Collocated or Distributed?

Nov 14, 2023
Figure 1 for On the IRS Deployment in Smart Factories Considering Blockage Effects: Collocated or Distributed?
Figure 2 for On the IRS Deployment in Smart Factories Considering Blockage Effects: Collocated or Distributed?
Figure 3 for On the IRS Deployment in Smart Factories Considering Blockage Effects: Collocated or Distributed?
Figure 4 for On the IRS Deployment in Smart Factories Considering Blockage Effects: Collocated or Distributed?
Viaarxiv icon

Exploiting Low-confidence Pseudo-labels for Source-free Object Detection

Oct 19, 2023
Figure 1 for Exploiting Low-confidence Pseudo-labels for Source-free Object Detection
Figure 2 for Exploiting Low-confidence Pseudo-labels for Source-free Object Detection
Figure 3 for Exploiting Low-confidence Pseudo-labels for Source-free Object Detection
Figure 4 for Exploiting Low-confidence Pseudo-labels for Source-free Object Detection
Viaarxiv icon

Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation

May 11, 2023
Figure 1 for Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation
Figure 2 for Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation
Figure 3 for Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation
Figure 4 for Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation
Viaarxiv icon

Segment Anything Model for Medical Image Analysis: an Experimental Study

Add code
Apr 25, 2023
Figure 1 for Segment Anything Model for Medical Image Analysis: an Experimental Study
Figure 2 for Segment Anything Model for Medical Image Analysis: an Experimental Study
Figure 3 for Segment Anything Model for Medical Image Analysis: an Experimental Study
Figure 4 for Segment Anything Model for Medical Image Analysis: an Experimental Study
Viaarxiv icon

Mutilmodal Feature Extraction and Attention-based Fusion for Emotion Estimation in Videos

Add code
Mar 18, 2023
Figure 1 for Mutilmodal Feature Extraction and Attention-based Fusion for Emotion Estimation in Videos
Figure 2 for Mutilmodal Feature Extraction and Attention-based Fusion for Emotion Estimation in Videos
Figure 3 for Mutilmodal Feature Extraction and Attention-based Fusion for Emotion Estimation in Videos
Viaarxiv icon

Enhancing Sequential Recommendation with Graph Contrastive Learning

Jun 07, 2022
Figure 1 for Enhancing Sequential Recommendation with Graph Contrastive Learning
Figure 2 for Enhancing Sequential Recommendation with Graph Contrastive Learning
Figure 3 for Enhancing Sequential Recommendation with Graph Contrastive Learning
Figure 4 for Enhancing Sequential Recommendation with Graph Contrastive Learning
Viaarxiv icon

Who will stay? Using Deep Learning to predict engagement of citizen scientists

Apr 28, 2022
Figure 1 for Who will stay? Using Deep Learning to predict engagement of citizen scientists
Figure 2 for Who will stay? Using Deep Learning to predict engagement of citizen scientists
Figure 3 for Who will stay? Using Deep Learning to predict engagement of citizen scientists
Figure 4 for Who will stay? Using Deep Learning to predict engagement of citizen scientists
Viaarxiv icon