Related papers: TEAM-Net: Multi-modal Learning for Video Action Re…
The canonical approach to video action recognition dictates a neural model to do a classic and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined categories, limiting their transferable ability on new…
Learning for manipulation requires using policies that have access to rich sensory information such as point clouds or RGB images. Point clouds efficiently capture geometric structures, making them essential for manipulation tasks in…
This paper presents a collaborative implicit neural simultaneous localization and mapping (SLAM) system with RGB-D image sequences, which consists of complete front-end and back-end modules including odometry, loop detection, sub-map…
Deep neural networks have achieved remarkable success for video-based action recognition. However, most of existing approaches cannot be deployed in practice due to the high computational cost. To address this challenge, we propose a new…
Human activity recognition based on video streams has received numerous attentions in recent years. Due to lack of depth information, RGB video based activity recognition performs poorly compared to RGB-D video based solutions. On the other…
In the few-shot scenario, a learner must effectively generalize to unseen classes given a small support set of labeled examples. While a relatively large amount of research has gone into few-shot learning for image classification, little…
Graph convolutional networks (GCNs), which can model the human body skeletons as spatial and temporal graphs, have shown remarkable potential in skeleton-based action recognition. However, in the existing GCN-based methods, graph-structured…
Owing to the difficulties of mining spatial-temporal cues, the existing approaches for video salient object detection (VSOD) are limited in understanding complex and noisy scenarios, and often fail in inferring prominent objects. To…
This paper introduces a new method for inter-frame coding based on two complementary autoencoders: MOFNet and CodecNet. MOFNet aims at computing and conveying the Optical Flow and a pixel-wise coding Mode selection. The optical flow is used…
Given two consecutive RGB-D images, we propose a model that estimates a dense 3D motion field, also known as scene flow. We take advantage of the fact that in robot manipulation scenarios, scenes often consist of a set of rigidly moving…
Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network that explicitly…
Video understanding is to recognize and classify different actions or activities appearing in the video. A lot of previous work, such as video captioning, has shown promising performance in producing general video understanding. However, it…
The recognition of behaviors in videos usually requires a combinatorial analysis of the spatial information about objects and their dynamic action information in the temporal dimension. Specifically, behavior recognition may even rely more…
Applications of surveillance video have developed rapidly in recent years to protect public safety and daily life, which often detect and recognize objects in video sequences. Traditional coding frameworks remove temporal redundancy in…
We propose a novel neural representation for videos (NeRV) which encodes videos in neural networks. Unlike conventional representations that treat videos as frame sequences, we represent videos as neural networks taking frame index as…
In recent years, RGB-T salient object detection (SOD) has attracted continuous attention, which makes it possible to identify salient objects in environments such as low light by introducing thermal image. However, most of the existing…
The task of semi-supervised video object segmentation (VOS) has been greatly advanced and state-of-the-art performance has been made by dense matching-based methods. The recent methods leverage space-time memory (STM) networks and learn to…
Recognizing human actions based on videos has became one of the most popular areas of research in computer vision in recent years. This area has many applications such as surveillance, robotics, health care, video search and human-computer…
This paper addresses the problem of real-time action recognition in trimmed videos, for which deep neural networks have defined the state-of-the-art performance in the recent literature. For attaining higher recognition accuracies with…
Moving Object Detection (MOD) is a critical vision task for successfully achieving safe autonomous driving. Despite plausible results of deep learning methods, most existing approaches are only frame-based and may fail to reach reasonable…