Pang

不知能否进一步扩展关于Object Detectors Emerge in Deep Scene CNNs和Understanding the Effective Receptive Field in Deep Convolutional Neural Networks中提到的两种关于有效感受野的计算

## MVS-Synth Dataset ### 简单介绍 MVS-Synth Dataset is a photo-realistic synthetic dataset prepared for learning-based Multi-View Stereo algorithms. It consists of 120 sequences, each with 100 frames of urban scenes...

## GTA-3D Dataset ### 简单介绍 A dataset of 2D imagery, 3D point cloud data, and 3D vehicle bounding box labels all generated using the Grand Theft Auto 5 game engine....

## DIH: Depth Images with Humans ### 简单介绍 The DIH dataset has been created for human body landmark detection and human pose estimation from depth images. Training and deploying good...

## LARGE-SCALE RGB+D DATABASE ### 简单介绍 We introduce an RGB-D scene dataset consisting of more than 200 indoor / outdoor scenes. This dataset contains synchronized RGB-D frames from both Kinect...

## B-T4SA ### 简单介绍 Much progress has been made in the field of sentiment analysis in the past years. Researchers relied on textual data for this task, while only recently...

## 相关项目补充 - [ ] https://github.com/TinyGrass/SODdataset

- [ ] http://places2.csail.mit.edu/index.html

## Segmentaon - [x] FCN https://arxiv.org/abs/1411.4038 - [x] SegNet https://arxiv.org/abs/1511.00561 - [x] Deeplab https://arxiv.org/pdf/1606.00915.pdf - [x] U‐Net https://arxiv.org/abs/1505.04597 - [x] RefineNet https://arxiv.org/abs/1611.06612 - [x] PSPNet https://arxiv.org/abs/1612.01105 - [ ] Mask‐RCNN...

## GNN - [ ] Situation Recognition with Graph Neural Networks - [ ] SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation - [x] Semantic Object Parsing with Graph LSTM...