A review of convolutional neural network architectures and their optimizations
The research advances concerning the typical architectures of convolutional neural
networks (CNNs) as well as their optimizations are analyzed and elaborated in detail in this …
networks (CNNs) as well as their optimizations are analyzed and elaborated in detail in this …
Deep learning technique for human parsing: A survey and outlook
Human parsing aims to partition humans in image or video into multiple pixel-level semantic
parts. In the last decade, it has gained significantly increased interest in the computer vision …
parts. In the last decade, it has gained significantly increased interest in the computer vision …
Boosting video object segmentation via space-time correspondence learning
Current top-leading solutions for video object segmentation (VOS) typically follow a
matching-based regime: for each query frame, the segmentation mask is inferred according …
matching-based regime: for each query frame, the segmentation mask is inferred according …
Joint inductive and transductive learning for video object segmentation
Semi-supervised video object segmentation is a task of segmenting the target object in a
video sequence given only a mask annotation in the first frame. The limited information …
video sequence given only a mask annotation in the first frame. The limited information …
Cmd: Self-supervised 3d action representation learning with cross-modal mutual distillation
In 3D action recognition, there exists rich complementary information between skeleton
modalities. Nevertheless, how to model and utilize this information remains a challenging …
modalities. Nevertheless, how to model and utilize this information remains a challenging …
Reformulating graph kernels for self-supervised space-time correspondence learning
Self-supervised space-time correspondence learning utilizing unlabeled videos holds great
potential in computer vision. Most existing methods rely on contrastive learning with mining …
potential in computer vision. Most existing methods rely on contrastive learning with mining …
Locality-aware inter-and intra-video reconstruction for self-supervised correspondence learning
Our target is to learn visual correspondence from unlabeled videos. We develop LIIR, a
locality-aware inter-and intra-video reconstruction framework that fills in three missing …
locality-aware inter-and intra-video reconstruction framework that fills in three missing …
Unified mask embedding and correspondence learning for self-supervised video segmentation
The objective of this paper is self-supervised learning of video object segmentation. We
develop a unified framework which simultaneously models cross-frame dense …
develop a unified framework which simultaneously models cross-frame dense …
Exposing the self-supervised space-time correspondence learning via graph kernels
Self-supervised space-time correspondence learning is emerging as a promising way of
leveraging unlabeled video. Currently, most methods adapt contrastive learning with mining …
leveraging unlabeled video. Currently, most methods adapt contrastive learning with mining …
Dense unsupervised learning for video segmentation
N Araslanov, S Schaub-Meyer… - Advances in neural …, 2021 - proceedings.neurips.cc
We present a novel approach to unsupervised learning for video object segmentation (VOS).
Unlike previous work, our formulation allows to learn dense feature representations directly …
Unlike previous work, our formulation allows to learn dense feature representations directly …