Alert button
Picture for Andy J. Ma

Andy J. Ma

Alert button

DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detection

Sep 07, 2023
Manlin Zhang, Jie Wu, Yuxi Ren, Ming Li, Jie Qin, Xuefeng Xiao, Wei Liu, Rui Wang, Min Zheng, Andy J. Ma

Figure 1 for DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detection
Figure 2 for DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detection
Figure 3 for DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detection
Figure 4 for DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detection
Viaarxiv icon

Adversarial Feature Augmentation for Cross-domain Few-shot Classification

Aug 23, 2022
Yanxu Hu, Andy J. Ma

Figure 1 for Adversarial Feature Augmentation for Cross-domain Few-shot Classification
Figure 2 for Adversarial Feature Augmentation for Cross-domain Few-shot Classification
Figure 3 for Adversarial Feature Augmentation for Cross-domain Few-shot Classification
Figure 4 for Adversarial Feature Augmentation for Cross-domain Few-shot Classification
Viaarxiv icon

Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning

Dec 08, 2021
Manlin Zhang, Jinpeng Wang, Andy J. Ma

Figure 1 for Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning
Figure 2 for Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning
Figure 3 for Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning
Figure 4 for Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning
Viaarxiv icon

Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning

Sep 12, 2020
Jinpeng Wang, Yuting Gao, Ke Li, Yiqi Lin, Andy J. Ma, Xing Sun

Figure 1 for Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning
Figure 2 for Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning
Figure 3 for Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning
Figure 4 for Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning
Viaarxiv icon

Self-supervised Temporal Discriminative Learning for Video Representation Learning

Aug 05, 2020
Jinpeng Wang, Yiqi Lin, Andy J. Ma, Pong C. Yuen

Figure 1 for Self-supervised Temporal Discriminative Learning for Video Representation Learning
Figure 2 for Self-supervised Temporal Discriminative Learning for Video Representation Learning
Figure 3 for Self-supervised Temporal Discriminative Learning for Video Representation Learning
Figure 4 for Self-supervised Temporal Discriminative Learning for Video Representation Learning
Viaarxiv icon

Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognition

Aug 05, 2020
Jinpeng Wang, Yiqi Lin, Andy J. Ma

Figure 1 for Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognition
Figure 2 for Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognition
Figure 3 for Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognition
Figure 4 for Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognition
Viaarxiv icon