相关论文: ActionFlowNet: Learning Motion Representation for …

In this paper, we are interested in self-supervised learning the motion cues in videos using dynamic motion filters for a better motion representation to finally boost human action recognition in particular. Thus far, the vision community…

We investigate two crucial and closely related aspects of CNNs for optical flow estimation: models and training. First, we design a compact but effective CNN model, called PWC-Net, according to simple and well-established principles:…

Dynamic imaging is a recently proposed action description paradigm for simultaneously capturing motion and temporal evolution information, particularly in the context of deep convolutional neural networks (CNNs). Compared with optical flow…

For the two-stream style methods in action recognition, fusing the two streams' predictions is always by the weighted averaging scheme. This fusion method with fixed weights lacks of pertinence to different action videos and always needs…

The existing action recognition methods are mainly based on clip-level classifiers such as two-stream CNNs or 3D CNNs, which are trained from the randomly selected clips and applied to densely sampled clips during testing. However, this…

Most two-stream action recognition networks apply the same convolutional backbone to both RGB and optical flow streams, ignoring the fact that the two modalities have fundamentally different structural properties. Optical flow captures…

Micro-expression (ME) recognition plays a crucial role in a wide range of applications, particularly in public security and psychotherapy. Recently, traditional methods rely excessively on machine learning design and the recognition rate is…

Optical flow estimation with convolutional neural networks (CNNs) has recently solved various tasks of computer vision successfully. In this paper we adapt a state-of-the-art approach for optical flow estimation to omnidirectional images.…

Object recognition and motion understanding are key components of perception that complement each other. While self-supervised learning methods have shown promise in their ability to learn from unlabeled data, they have primarily focused on…

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…

Deep neural networks, albeit their great success on feature learning in various computer vision tasks, are usually considered as impractical for online visual tracking because they require very long training time and a large number of…

Action recognition has seen a dramatic performance improvement in the last few years. Most of the current state-of-the-art literature either aims at improving performance through changes to the backbone CNN network, or they explore…

Activity recognition has become a popular research branch in the field of pervasive computing in recent years. A large number of experiments can be obtained that activity sensor-based data's characteristic in activity recognition is…

In this paper we deal with the problem of predicting action progress in videos. We argue that this is an extremely important task since it can be valuable for a wide range of interaction applications. To this end we introduce a novel…

Action recognition is a prerequisite for many applications in laparoscopic video analysis including but not limited to surgical training, operation room planning, follow-up surgery preparation, post-operative surgical assessment, and…

We study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only, which can be reused for downstream tasks such as action recognition. This task, however, is extremely…

Deep learning has been demonstrated to achieve excellent results for image classification and object detection. However, the impact of deep learning on video analysis (e.g. action detection and recognition) has been limited due to…

We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference. 3D convolutional neural networks (CNNs) are accurate at video recognition but…

Facial movements play a crucial role in conveying altitude and intentions, and facial optical flow provides a dynamic and detailed representation of it. However, the scarcity of datasets and a modern baseline hinders the progress in facial…

The ability to accurately identify human activities is essential for developing automatic rehabilitation and sports training systems. In this paper, large-scale exercise motion data obtained from a forearm-worn wearable sensor are…