Related papers: Shrinkage Optimized Directed Information using Pic…
Human action recognition has recently become one of the popular research topics in the computer vision community. Various 3D-CNN based methods have been presented to tackle both the spatial and temporal dimensions in the task of video…
This paper presents a novel unsupervised domain adaptation framework, called Synergistic Image and Feature Adaptation (SIFA), to effectively tackle the problem of domain shift. Domain adaptation has become an important and hot topic in…
Spatio-temporal representations in frame sequences play an important role in the task of action recognition. Previously, a method of using optical flow as a temporal information in combination with a set of RGB images that contain spatial…
We propose a novel approach based on deep Convolutional Neural Networks (CNN) to recognize human actions in still images by predicting the future motion, and detecting the shape and location of the salient parts of the image. We make the…
Zero-shot skeleton-based action recognition aims to recognize actions of unseen categories after training on data of seen categories. The key is to build the connection between visual and semantic space from seen to unseen classes. Previous…
Automated surgical gesture recognition is of great importance in robot-assisted minimally invasive surgery. However, existing methods assume that training and testing data are from the same domain, which suffers from severe performance…
Understanding human actions in videos requires more than raw pixel analysis; it relies on high-level semantic reasoning and effective integration of multimodal features. We propose a deep translational action recognition framework that…
Incremental methods for structure learning of pairwise Markov random fields (MRFs), such as grafting, improve scalability by avoiding inference over the entire feature space in each optimization step. Instead, inference is performed over an…
Discriminatively learned correlation filters (DCF) have been widely used in online visual tracking filed due to its simplicity and efficiency. These methods utilize a periodic assumption of the training samples to construct a circulant data…
Multi-Source Domain Adaptation (MSDA) focuses on transferring the knowledge from multiple source domains to the target domain, which is a more practical and challenging problem compared to the conventional single-source domain adaptation.…
Recently, with the availability of cost-effective depth cameras coupled with real-time skeleton estimation, the interest in skeleton-based human action recognition is renewed. Most of the existing skeletal representation approaches use…
Motion representation plays a vital role in human action recognition in videos. In this study, we introduce a novel compact motion representation for video action recognition, named Optical Flow guided Feature (OFF), which enables the…
Online action detection (OAD) is challenging since 1) robust yet computationally expensive features cannot be straightforwardly used due to the real-time processing requirements and 2) the localization and classification of actions have to…
Slow Feature Analysis is a unsupervised representation learning method that extracts slowly varying features from temporal data and can be used as a basis for subsequent reinforcement learning. Often, the behavior that generates the data on…
Recently, Convolutional Neural Networks (ConvNets) have shown promising performances in many computer vision tasks, especially image-based recognition. How to effectively use ConvNets for video-based recognition is still an open problem. In…
Spatial and temporal stream model has gained great success in video action recognition. Most existing works pay more attention to designing effective features fusion methods, which train the two-stream model in a separate way. However, it's…
Developing policies that can adjust to non-stationary environments is essential for real-world reinforcement learning applications. However, learning such adaptable policies in offline settings, with only a limited set of pre-collected…
Skeleton data carries valuable motion information and is widely explored in human action recognition. However, not only the motion information but also the interaction with the environment provides discriminative cues to recognize the…
Markov Random Fields (MRFs), a formulation widely used in generative image modeling, have long been plagued by the lack of expressive power. This issue is primarily due to the fact that conventional MRFs formulations tend to use simplistic…
There has been an increasing interest in spiking neural networks in recent years. SNNs are seen as hypothetical solutions for the bottlenecks of ANNs in pattern recognition, such as energy efficiency. But current methods such as ANN-to-SNN…