Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop

Perspectives in machine learning for wildlife conservation

“…Recent work defines the SMAL (Skinned Multi-Animal Linear) model, a 3D articulated shape model for a set of quadruped families 107 . Biggs et al built on this work for 3D shape and motion of dogs from video 108 and for recovery of dog shape and pose across many different breeds 109 . In ref.…”

Factors of Influence for Transfer Learning Across Diverse Appearance Domains and Task Types

“…For example, we find that semantic segmentation on COCO [60] is a good source for depth estimation on SUN RGB-D [89] (Tab. 4e); and even that keypoint detection on Stanford Dogs [8], [47] helps object detection on the Underwater Trash [30] dataset (Tab. 5b).…”

Progress on Computational Ethology

“…但是其中大部分是一些方法学的研究, 还缺乏与 脑中行为控制机制的关联分析. 从2015年起, 计算机视 觉领域开始关注利用深度学习解决从二维物体图像估 计三维形状的问题 [50] , 并在鸟类 [51] 、犬 [52] 以及其他多 种动物 . 数据降维有主成分分析(principal component analysis) [62] 、t分布随机邻近嵌入法(t-distributed stochastic neighbor embedding) [58] 、UMAP(uniform manifold approximation and projection for dimension reduction) [43] 等方法.…”