相关论文: Knowing What, Where and When to Look: Efficient Vi…

With the increasing computational demands of neural networks, many hardware accelerators for the neural networks have been proposed. Such existing neural network accelerators often focus on popular neural network types such as convolutional…

Video salient object detection aims to find the most visually distinctive objects in a video. To explore the temporal dependencies, existing methods usually resort to recurrent neural networks or optical flow. However, these approaches…

Human action recognition has become an important research focus in computer vision due to the wide range of applications where it is used. 3D Resnet-based CNN models, particularly MC3, R3D, and R(2+1)D, have different convolutional filters…

Many few-shot learning models focus on recognising images. In contrast, we tackle a challenging task of few-shot action recognition from videos. We build on a C3D encoder for spatio-temporal video blocks to capture short-range action…

We present a new model to determine relative skill from long videos, through learnable temporal attention modules. Skill determination is formulated as a ranking problem, making it suitable for common and generic tasks. However, for long…

Recent advances in deep neural networks have been developed via architecture search for stronger representational power. In this work, we focus on the effect of attention in general deep neural networks. We propose a simple and effective…

We investigate a human-like interpretable model of video understanding. Humans recognise complex activities in video by recognising critical spatio-temporal relations among explicitly recognised objects and parts, for example, an object…

We present an attention-based modular neural framework for computer vision. The framework uses a soft attention mechanism allowing models to be trained with gradient descent. It consists of three modules: a recurrent attention module…

Modern video understanding systems excel at tasks such as scene classification, object detection, and short video retrieval. However, as video analysis becomes increasingly central to real-world applications, there is a growing need for…

The dominant paradigm in spatiotemporal action detection is to classify actions using spatiotemporal features learned by 2D or 3D Convolutional Networks. We argue that several actions are characterized by their context, such as relevant…

Recently, channel attention mechanism has demonstrated to offer great potential in improving the performance of deep convolutional neural networks (CNNs). However, most existing methods dedicate to developing more sophisticated attention…

An important challenge in vision-based action recognition is the embedding of spatiotemporal features with two or more heterogeneous modalities into a single feature. In this study, we propose a new 3D deformable transformer for action…

Recently, substantial research effort has focused on how to apply CNNs or RNNs to better extract temporal patterns from videos, so as to improve the accuracy of video classification. In this paper, however, we show that temporal…

Understanding human actions in wild videos is an important task with a broad range of applications. In this paper we propose a novel approach named Hierarchical Attention Network (HAN), which enables to incorporate static spatial…

Anticipating future actions in videos is challenging, as the observed frames provide only evidence of past activities, requiring the inference of latent intentions to predict upcoming actions. Existing transformer-based approaches, which…

The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel…

The interactions between human and objects are important for recognizing object-centric actions. Existing methods usually adopt a two-stage pipeline, where object proposals are first detected using a pretrained detector, and then are fed to…

A dominant paradigm for learning-based approaches in computer vision is training generic models, such as ResNet for image recognition, or I3D for video understanding, on large datasets and allowing them to discover the optimal…

Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy is not…

Spatio-temporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D).…