Loading contributions...
Top Repositories
Code for Referring Image Segmentation via Cross-Modal Progressive Comprehension, CVPR2020.
Website of The 3rd Workshop on UAVs in Multimedia: Capturing the World from a New Perspective
Code for Linguistic Structure Guided Context Modeling for Referring Image Segmentation, ECCV2020.
Official PyTorch implementation for 'Revisiting Audio-Visual Segmentation with Vision-Centric Transformer'
Repositories
43No description provided.
Website of The 3rd Workshop on UAVs in Multimedia: Capturing the World from a New Perspective
Official PyTorch implementation for 'Revisiting Audio-Visual Segmentation with Vision-Centric Transformer'
The Academic Personal Homepage of spyflying
Code for Referring Image Segmentation via Cross-Modal Progressive Comprehension, CVPR2020.
Code for Linguistic Structure Guided Context Modeling for Referring Image Segmentation, ECCV2020.
No description provided.
Generating cars' driving trajactories using generative adversarial imitation learning
No description provided.
[ECCV 2022 oral] OpenLane: Large-scale Realistic 3D Lane Dataset
OpenMMLab Detection Toolbox and Benchmark
Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)
No description provided.
Release of the pretrained S3D Network in PyTorch (ECCV 2018)
Spatiotemporal-separable 3D convolution network.
pytorch version of pseudo-3d-residual-networks(P-3D), pretrained model is supported
[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
No description provided.
No description provided.
A pytorch-version implementation codes of paper: "BMN: Boundary-Matching Network for Temporal Action Proposal Generation", which is accepted in ICCV 2019.
ResNeSt: Split-Attention Network
Tools to extract dense optical flow from videos, based on OpenCV
Code & Models for Temporal Segment Networks (TSN) in ECCV 2016
No description provided.
Extract TVL1 optical flows in python (multi-process && multi-server)
S3D Text-Video model trained on HowTo100M using MIL-NCE
PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
No description provided.
:books: A collection of papers about Referring Image Segmentation.
Cross-Modal Self-Attention Network for Referring Image Segmentation cvpr19