Related papers: Joint Network based Attention for Action Recogniti…

Graph Neural Networks are perfectly suited to capture latent interactions between various entities in the spatio-temporal domain (e.g. videos). However, when an explicit structure is not available, it is not obvious what atomic elements…

Streaming perception is a critical task in autonomous driving that requires balancing the latency and accuracy of the autopilot system. However, current methods for streaming perception are limited as they only rely on the current and…

As compared to simple actions, activities are much more complex, but semantically consistent with a human's real life. Techniques for action recognition from sensor generated data are mature. However, there has been relatively little work…

We propose a new spatio-temporal attention based mechanism for human action recognition able to automatically attend to the hands most involved into the studied action and detect the most discriminative moments in an action. Attention is…

In this report, our approach to tackling the task of ActivityNet 2018 Kinetics-600 challenge is described in detail. Though spatial-temporal modelling methods, which adopt either such end-to-end framework as I3D \cite{i3d} or two-stage…

Algorithms for video action recognition should consider not only spatial information but also temporal relations, which remains challenging. We propose a 3D-CNN-based action recognition model, called the blockwise temporal-spatial path-way…

In this work we propose a multi-task spatio-temporal network, called SUSiNet, that can jointly tackle the spatio-temporal problems of saliency estimation, action recognition and video summarization. Our approach employs a single network…

In this paper, we propose a multi-domain learning model for action recognition. The proposed method inserts domain-specific adapters between layers of domain-independent layers of a backbone network. Unlike a multi-head network that…

Despite excellent progress has been made, the performance on action recognition still heavily relies on specific datasets, which are difficult to extend new action classes due to labor-intensive labeling. Moreover, the high diversity in…

Spatial and temporal modeling is one of the most core aspects of few-shot action recognition. Most previous works mainly focus on long-term temporal relation modeling based on high-level spatial representations, without considering the…

We introduce Knowledge Fusion Transformers for video action classification. We present a self-attention based feature enhancer to fuse action knowledge in 3D inception based spatio-temporal context of the video clip intended to be…

Multi-modality is an important feature of sensor based activity recognition. In this work, we consider two inherent characteristics of human activities, the spatially-temporally varying salience of features and the relations between…

3D convolutional neural networks have achieved promising results for video tasks in computer vision, including video saliency prediction that is explored in this paper. However, 3D convolution encodes visual representation merely on fixed…

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…

Instance-level video segmentation requires a solid integration of spatial and temporal information. However, current methods rely mostly on domain-specific information (online learning) to produce accurate instance-level segmentations. We…

Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs). However, effective and efficient methods for incorporation of…

Video action analysis is a foundational technology within the realm of intelligent video comprehension, particularly concerning its application in Internet of Things(IoT). However, existing methodologies overlook feature semantics in…

Dominant approaches to action detection can only provide sub-optimal solutions to the problem, as they rely on seeking frame-level detections, to later compose them into "action tubes" in a post-processing step. With this paper we radically…

In this paper, we study the problem of one-shot skeleton-based action recognition, which poses unique challenges in learning transferable representation from base classes to novel classes, particularly for fine-grained actions. Existing…

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…