![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose
Recognition of human poses and actions is crucial for autonomous systems to interact smoothly with people. However, cameras generally capture human poses in 2D as images and videos, which can have significant ...
-
Chapter and Conference Paper
k-means Mask Transformer
The rise of transformers in vision tasks not only advances network backbone designs, but also starts a brand-new page to achieve end-to-end image recognition (e.g., object detection and panoptic segmentation). Or...
-
Chapter and Conference Paper
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
Convolution exploits locality for efficiency at a cost of missing long range context. Self-attention has been adopted to augment CNNs with non-local interactions. Recent works prove it possible to stack self-a...
-
Chapter and Conference Paper
Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
In this work we explore the task of instance segmentation with attribute localization, which unifies instance segmentation (detect and segment each object instance) and fine-grained visual attribute categorizatio...
-
Chapter and Conference Paper
View-Invariant Probabilistic Embedding for Human Pose
Depictions of similar human body configurations can vary with changing viewpoints. Using only 2D information, we would like to enable vision algorithms to recognize similarity in human body poses across multip...
-
Chapter and Conference Paper
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing ...
-
Chapter and Conference Paper
Large-Scale Object Classification Using Label Relation Graphs
In this paper we study how to perform object classification in a principled way that exploits the rich structure of real world labels. We develop a new model that allows encoding of flexible relations between ...