Related papers: Temporal Transformer Networks with Self-Supervisio…
Temporally locating and classifying action segments in long untrimmed videos is of particular interest to many applications like surveillance and robotics. While traditional approaches follow a two-step pipeline, by generating frame-wise…
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…
We introduce a novel self-supervised learning approach to learn representations of videos that are responsive to changes in the motion dynamics. Our representations can be learned from data without human annotation and provide a substantial…
The video based CNN works have focused on effective ways to fuse appearance and motion networks, but they typically lack utilizing temporal information over video frames. In this work, we present a novel spatio-temporal fusion network…
Most work on temporal action detection is formulated as an offline problem, in which the start and end times of actions are determined after the entire video is fully observed. However, important real-time applications including…
Skeleton-based Human Activity Recognition has achieved great interest in recent years as skeleton data has demonstrated being robust to illumination changes, body scales, dynamic camera views, and complex background. In particular,…
Temporal cues in videos provide important information for recognizing actions accurately. However, temporal-discriminative features can hardly be extracted without using an annotated large-scale video action dataset for training. This paper…
We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequences of financial transactions. The model is trained using a self-supervised contrastive…
Video super-resolution plays an important role in surveillance video analysis and ultra-high-definition video display, which has drawn much attention in both the research and industrial communities. Although many deep learning-based VSR…
The work in this paper is driven by the question how to exploit the temporal cues available in videos for their accurate classification, and for human action recognition in particular? Thus far, the vision community has focused on…
Time series forecasting is essential for a wide range of real-world applications. Recent studies have shown the superiority of Transformer in dealing with such problems, especially long sequence time series input(LSTI) and long sequence…
Video super-resolution (VSR) is a task that aims to reconstruct high-resolution (HR) frames from the low-resolution (LR) reference frame and multiple neighboring frames. The vital operation is to utilize the relative misaligned frames for…
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. There are many real-world challenges in those datasets, such as composite action, co-occurring action, and high temporal…
Action classification has made great progress, but segmenting and recognizing actions from long untrimmed videos remains a challenging problem. Most state-of-the-art methods focus on designing temporal convolution-based models, but the…
Automatic surgical phase recognition is one of the key technologies to support Video-Based Assessment (VBA) systems for surgical education. Utilizing temporal information is crucial for surgical phase recognition, hence various recent…
In this paper, we propose self-supervised training for video transformers using unlabeled video data. From a given video, we create local and global spatiotemporal views with varying spatial sizes and frame rates. Our self-supervised…
Real-time networks based on Ethernet require robust quality-of-service for time-critical traffic. The Time-Sensitive Networking (TSN) collection of standards enables this in real-time environments like vehicle on-board networks. Runtime…
Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…
Predicting motion of surrounding agents is critical to real-world applications of tactical path planning for autonomous driving. Due to the complex temporal dependencies and social interactions of agents, on-line trajectory prediction is a…
Efficiency is an important issue in designing video architectures for action recognition. 3D CNNs have witnessed remarkable progress in action recognition from videos. However, compared with their 2D counterparts, 3D convolutions often…