Up-to-date List
- The following may not be updated timely. See the up-to-date paper list.
Computer Vision Track: CVPR, ICCV, ECCV etc
-
The following includs computer vision based papers.
-
Even thouhg some of them apear in NIPS etc, they will fall into this category if their main content is vision based or engineering based (instead of mathematic ones).
| Reversed Index | Paper Name | Conferences | Keywords or Short Info | Notes |
|---|---|---|---|---|
| 000006 | PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation | CVPR 2017 | PointNet, as a novel type of neural network, directly consumes point clouds, which well respects the permutation invariance of points in the input. PointNet provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective | |
| Code, Slide | ||||
| 000005 | Bi3D: Stereo Depth Estimation via Binary Classifications | CVPR 2020 | a method that estimates depth via a series of binary classifications. Rather than testing if objects are at a particular depth D, as existing stereo methods do, it classifies them as being closer or farther than D. This property offers a powerful mechanism to balance accuracy and latency. | code, |
| Slide | ||||
| 000004 | Hierarchical Neural Architecture Search for Deep Stereo Matching | NIPS 2020 | end-to-end hierarchical NAS framework for deep stereo matching by incorporating task-specific human knowledge into the neural architecture search framework | code |
| 000003 | Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods | TPAMI 2020 | survey, unsupervised learning | w/o code |
| 000002 | Bi3D: Stereo Depth Estimation via Binary Classifications | CVPR 2020 | Stereo Matching, real-time | code |
| 000001 | Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems | CVPR 2020 | MRF Energy Optimization, End-to-end, Stereo Matching, Semantic Segmentation, Optical Flow | code |
Machine Learning Track: NIPS, ICLR, ICML, AAAI etc
-
The following includs machine learning based papers. Most of them have sound theoritical proof.
-
NIPS 2020 Paper Lists: see link
| Reversed Index | Paper Name | Conferences | Keywords or Short Info | Notes |
|---|---|---|---|---|
| 000001 | Belief Propagation Neural Networks | NIPS 2020 | belief propagation neural networks (BPNNs), a class of parameterized operators that operate on factor graphs and generalize Belief Propagation (BP) | w/o code |