CVPR 2020
| title | author | length |
|---|---|---|
| Channel Gating for Cheaper and More Accurate Neural Nets | Babak Ehteshami Bejnordi | 56m |
Introduces per-filter channel gating trained with Gumbel-softmax, an L0 sparsity term and a novel batch-shaping loss that matches the empirical CDF of gate… | ||
| Invariance, Geometry and Deep Neural Networks | Pavan Turaga | 47m |
Argues that encoding physics and geometry into networks reduces data needs and increases robustness, using orthonormal latent blocks and manifold/tangent‑space… | ||
| AI for High-Stakes Decision Making | Hima Lakkaraju | 46m |
Perturbation-based explainers like LIME and SHAP can be spoofed: an adversarial wrapper makes a model behave innocently on synthetic perturbations while still… | ||
| Deep Learning for Automatic Basketball Video Production | Julian Quiroga | 42m |
A system that turns a fixed wide camera into a live, watchable basketball broadcast by combining Gaussian-based actionness (mixture of player-position… | ||
| Computer Vision for Remote AR | Flora Tasse | 41m |
Describes a production pipeline that turns phone video into a real-time textured 3D mesh for remote AR, using motion stereo (and LiDAR when available), plus a… | ||
| nothing matches | ||