Related papers: TDN: Temporal Difference Networks for Efficient Ac…

With the success of deep learning in classifying short trimmed videos, more attention has been focused on temporally segmenting and classifying activities in long untrimmed videos. State-of-the-art approaches for action segmentation utilize…

Recent two-stream deep Convolutional Neural Networks (ConvNets) have made significant progress in recognizing human actions in videos. Despite their success, methods extending the basic two-stream ConvNet have not systematically explored…

To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone. However, they all exploit 1D temporal convolution of fixed…

Video-based person reID is an important task, which has received much attention in recent years due to the increasing demand in surveillance and camera networks. A typical video-based person reID system consists of three parts: an…

The goal of weakly supervised video anomaly detection is to learn a detection model using only video-level labeled data. However, prior studies typically divide videos into fixed-length segments without considering the complexity or…

Although current face manipulation techniques achieve impressive performance regarding quality and controllability, they are struggling to generate temporal coherent face videos. In this work, we explore to take full advantage of the…

Interpreting human actions requires understanding the spatial and temporal context of the scenes. State-of-the-art action detectors based on Convolutional Neural Network (CNN) have demonstrated remarkable results by adopting two-stream or…

Temporal action localization is an important yet challenging problem. Given a long, untrimmed video consisting of multiple action instances and complex background contents, we need not only to recognize their action categories, but also to…

Recently, three dimensional (3D) convolutional neural networks (CNNs) have emerged as dominant methods to capture spatiotemporal representations in videos, by adding to pre-existing 2D CNNs a third, temporal dimension. Such 3D CNNs,…

Efficient long-short temporal modeling is key for enhancing the performance of action recognition task. In this paper, we propose a new two-stream action recognition network, termed as MENet, consisting of a Motion Enhancement (ME) module…

Depth super-resolution has achieved impressive performance, and the incorporation of multi-frame information further enhances reconstruction quality. Nevertheless, statistical analyses reveal that video depth super-resolution remains…

Temporal Action Localization (TAL) remains a fundamental challenge in video understanding, aiming to identify the start time, end time, and category of all action instances within untrimmed videos. While recent single-stage, anchor-free…

Time series data usually contains local and global patterns. Most of the existing feature networks pay more attention to local features rather than the relationships among them. The latter is, however, also important yet more difficult to…

Video Analytics Software as a Service (VA SaaS) has been rapidly growing in recent years. VA SaaS is typically accessed by users using a lightweight client. Because the transmission bandwidth between the client and cloud is usually limited…

Deep video models, for example, 3D CNNs or video transformers, have achieved promising performance on sparse video tasks, i.e., predicting one result per video. However, challenges arise when adapting existing deep video models to dense…

Skeleton-based action recognition has made great progress recently, but many problems still remain unsolved. For example, most of the previous methods model the representations of skeleton sequences without abundant spatial structure…

In this paper, we propose an end-to-end 3D CNN for action detection and segmentation in videos. The proposed architecture is a unified deep network that is able to recognize and localize action based on 3D convolution features. A video is…

Video prediction is a complex time-series forecasting task with great potential in many use cases. However, traditional methods prioritize accuracy and overlook slow prediction speeds due to complex model structures, redundant information,…

Graph convolution networks (GCN) have been widely used in skeleton-based action recognition. We note that existing GCN-based approaches primarily rely on prescribed graphical structures (ie., a manually defined topology of skeleton joints),…

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…