Related papers: BiCnet-TKS: Learning Efficient Spatial-Temporal Re…
In this paper we consider the problem of video-based person re-identification, which is the task of associating videos of the same person captured by different and non-overlapping cameras. We propose a Siamese framework in which video…
Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos,…
We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The…
In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device. However, this pipeline…
In this work we propose a new architecture for person re-identification. As the task of re-identification is inherently associated with embedding learning and non-rigid appearance description, our architecture is based on the deep bilinear…
In the past five years we have observed the rise of incredibly well performing feed-forward neural networks trained supervisedly for vision related tasks. These models have achieved super-human performance on object recognition,…
Video-based person re-identification (re-ID) is an important technique in visual surveillance systems which aims to match video snippets of people captured by different cameras. Existing methods are mostly based on convolutional neural…
We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a…
In this paper we introduce an ensemble method for convolutional neural network (CNN), called "virtual branching," which can be implemented with nearly no additional parameters and computation on top of standard CNNs. We propose our method…
LiDAR-based semantic perception tasks are critical yet challenging for autonomous driving. Due to the motion of objects and static/dynamic occlusion, temporal information plays an essential role in reinforcing perception by enhancing and…
The goal of moving object segmentation is separating moving objects from stationary backgrounds in videos. One major challenge in this problem is how to develop a universal model for videos from various natural scenes since previous methods…
Deep ConvNets have been shown to be effective for the task of human pose estimation from single images. However, several challenging issues arise in the video-based case such as self-occlusion, motion blur, and uncommon poses with few or no…
Performing a real-time and accurate instrument segmentation from videos is of great significance for improving the performance of robotic-assisted surgery. We identify two important clues for surgical instrument perception, including local…
Skeleton-based action recognition has attracted considerable attention due to its compact representation of the human body's skeletal sructure. Many recent methods have achieved remarkable performance using graph convolutional networks…
Video-based person re-identification (re-ID) aims at matching the same person across video clips. Efficiently exploiting multi-scale fine-grained features while building the structural interaction among them is pivotal for its success. In…
Skeleton-based action recognition has made great progress recently, but many problems still remain unsolved. For example, most of the previous methods model the representations of skeleton sequences without abundant spatial structure…
Video action recognition has made significant strides, but challenges remain in effectively using both spatial and temporal information. While existing methods often focus on either spatial features (e.g., object appearance) or temporal…
Generalizable person re-identification (Re-ID) is a very hot research topic in machine learning and computer vision, which plays a significant role in realistic scenarios due to its various applications in public security and video…
Person re-identification (re-ID) aims to accurately re- trieve a person from a large-scale database of images cap- tured across multiple cameras. Existing works learn deep representations using a large training subset of unique per- sons.…
Learning efficient and expressive visual representation has long been the pursuit of computer vision research. While Vision Transformers (ViTs) gradually replace traditional Convolutional Neural Networks (CNNs) as more scalable vision…