BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video RWTHVision

207 views - 3 years ago

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos (ECCV'20) RWTHVision

1.7K views - 5 years ago

Making a Case for 3D Convolutions for Object Segmentation in Videos (BMVC'20) RWTHVision

1.2K views - 5 years ago

CVPR Robust Video Scene Understanding Workshop RWTHVision

3.3K views - 4 years ago

Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds RWTHVision

709 views - 5 years ago

Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds RWTHVision

3.5K views - 8 years ago

Joint Object Pose Estimation and Shape Reconstruction in Urban Street Scenes Using 3D Shape Priors RWTHVision

1.5K views - 9 years ago

Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera (ICRA'21) RWTHVision

1.3K views - 4 years ago

CAMOT: Category-Agnostic Vision-based Multi-Object Tracking RWTHVision

1.7K views - 7 years ago

HODOR: High-Level Object Descriptors for Object Resegmentation in Video From Static Images (CVPR'22) RWTHVision

152 views - 3 years ago

Mask3D: Mask Transformer for 3D Instance Segmentation (ICRA'23) RWTHVision

3K views - 2 years ago

Reposing Humans by Warping 3D Features (CVPRW'20) RWTHVision

1.1K views - 5 years ago

Full-Resolution Residual Networks (FRRNs) for Semantic Image Segmentation in Street Scenes RWTHVision

32.2K views - 9 years ago

DROW: Real-Time Deep Learning based Wheelchair Detection in 2D Range Data RWTHVision

526 views - 9 years ago

TarViS: A Unified Approach for Target-based Video Segmentation (CVPR'23 Highlight) RWTHVision

937 views - 2 years ago

Detection-Tracking for Efficient Person Analysis: The DetTA Pipeline RWTHVision

593 views - 7 years ago

From Points to Multi-Object 3D Reconstruction [CVPR 2021] RWTHVision

3.1K views - 4 years ago

5th BMTT MOTChallenge Workshop: Multi-Object Tracking and Segmentation RWTHVision

2.6K views - 5 years ago

Learning 3D Human Pose Estimation from Dozens of Datasets by Bridging Skeleton Formats (WACV'23) RWTHVision

13.3K views - 3 years ago

DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes (CVPR'20 Oral) RWTHVision

405 views - 5 years ago