Picture for Trung Pham

Trung Pham

DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning

Add code
Sep 21, 2023
Viaarxiv icon

DPPD: Deformable Polar Polygon Object Detection

Add code
Apr 05, 2023
Figure 1 for DPPD: Deformable Polar Polygon Object Detection
Figure 2 for DPPD: Deformable Polar Polygon Object Detection
Figure 3 for DPPD: Deformable Polar Polygon Object Detection
Figure 4 for DPPD: Deformable Polar Polygon Object Detection
Viaarxiv icon

NVAutoNet: Fast and Accurate 360$^{\circ}$ 3D Visual Perception For Self Driving

Add code
Mar 30, 2023
Figure 1 for NVAutoNet: Fast and Accurate 360$^{\circ}$ 3D Visual Perception For Self Driving
Figure 2 for NVAutoNet: Fast and Accurate 360$^{\circ}$ 3D Visual Perception For Self Driving
Figure 3 for NVAutoNet: Fast and Accurate 360$^{\circ}$ 3D Visual Perception For Self Driving
Figure 4 for NVAutoNet: Fast and Accurate 360$^{\circ}$ 3D Visual Perception For Self Driving
Viaarxiv icon

On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning

Add code
Aug 11, 2022
Figure 1 for On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning
Figure 2 for On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning
Figure 3 for On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning
Figure 4 for On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning
Viaarxiv icon

Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning

Add code
Mar 15, 2021
Figure 1 for Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning
Figure 2 for Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning
Figure 3 for Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning
Figure 4 for Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning
Viaarxiv icon

Modality Shifting Attention Network for Multi-modal Video Question Answering

Add code
Jul 04, 2020
Figure 1 for Modality Shifting Attention Network for Multi-modal Video Question Answering
Figure 2 for Modality Shifting Attention Network for Multi-modal Video Question Answering
Figure 3 for Modality Shifting Attention Network for Multi-modal Video Question Answering
Figure 4 for Modality Shifting Attention Network for Multi-modal Video Question Answering
Viaarxiv icon

Structure Aware SLAM using Quadrics and Planes

Add code
Nov 02, 2018
Figure 1 for Structure Aware SLAM using Quadrics and Planes
Figure 2 for Structure Aware SLAM using Quadrics and Planes
Figure 3 for Structure Aware SLAM using Quadrics and Planes
Figure 4 for Structure Aware SLAM using Quadrics and Planes
Viaarxiv icon

Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation

Add code
Aug 02, 2018
Figure 1 for Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation
Figure 2 for Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation
Figure 3 for Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation
Figure 4 for Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation
Viaarxiv icon

Bayesian Semantic Instance Segmentation in Open Set World

Add code
Jul 30, 2018
Figure 1 for Bayesian Semantic Instance Segmentation in Open Set World
Figure 2 for Bayesian Semantic Instance Segmentation in Open Set World
Figure 3 for Bayesian Semantic Instance Segmentation in Open Set World
Figure 4 for Bayesian Semantic Instance Segmentation in Open Set World
Viaarxiv icon

SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes

Add code
May 24, 2018
Figure 1 for SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes
Figure 2 for SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes
Figure 3 for SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes
Figure 4 for SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes
Viaarxiv icon