Picture for Zhengeng Yang

Zhengeng Yang

OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition

Add code
Nov 30, 2023
Viaarxiv icon

First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment

Add code
Jun 23, 2023
Figure 1 for First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment
Figure 2 for First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment
Figure 3 for First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment
Figure 4 for First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment
Viaarxiv icon

DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds

Add code
Mar 08, 2023
Figure 1 for DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds
Figure 2 for DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds
Figure 3 for DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds
Figure 4 for DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds
Viaarxiv icon

Full Point Encoding for Local Feature Aggregation in 3D Point Clouds

Add code
Mar 08, 2023
Viaarxiv icon

Domain-invariant Prototypes for Semantic Segmentation

Add code
Aug 12, 2022
Figure 1 for Domain-invariant Prototypes for Semantic Segmentation
Figure 2 for Domain-invariant Prototypes for Semantic Segmentation
Figure 3 for Domain-invariant Prototypes for Semantic Segmentation
Figure 4 for Domain-invariant Prototypes for Semantic Segmentation
Viaarxiv icon

Deep Learning based 3D Segmentation: A Survey

Add code
Mar 10, 2021
Figure 1 for Deep Learning based 3D Segmentation: A Survey
Figure 2 for Deep Learning based 3D Segmentation: A Survey
Figure 3 for Deep Learning based 3D Segmentation: A Survey
Figure 4 for Deep Learning based 3D Segmentation: A Survey
Viaarxiv icon

Self-supervised Learning with Fully Convolutional Networks

Add code
Dec 18, 2020
Figure 1 for Self-supervised Learning with Fully Convolutional Networks
Figure 2 for Self-supervised Learning with Fully Convolutional Networks
Figure 3 for Self-supervised Learning with Fully Convolutional Networks
Figure 4 for Self-supervised Learning with Fully Convolutional Networks
Viaarxiv icon

FastORB-SLAM: a Fast ORB-SLAM Method with Coarse-to-Fine Descriptor Independent Keypoint Matching

Add code
Aug 22, 2020
Figure 1 for FastORB-SLAM: a Fast ORB-SLAM Method with Coarse-to-Fine Descriptor Independent Keypoint Matching
Figure 2 for FastORB-SLAM: a Fast ORB-SLAM Method with Coarse-to-Fine Descriptor Independent Keypoint Matching
Figure 3 for FastORB-SLAM: a Fast ORB-SLAM Method with Coarse-to-Fine Descriptor Independent Keypoint Matching
Figure 4 for FastORB-SLAM: a Fast ORB-SLAM Method with Coarse-to-Fine Descriptor Independent Keypoint Matching
Viaarxiv icon

Real time backbone for semantic segmentation

Add code
Mar 16, 2019
Figure 1 for Real time backbone for semantic segmentation
Figure 2 for Real time backbone for semantic segmentation
Figure 3 for Real time backbone for semantic segmentation
Figure 4 for Real time backbone for semantic segmentation
Viaarxiv icon