Related papers: End-to-end Video-level Representation Learning for…

Videos have become ubiquitous on the Internet. And video analysis can provide lots of information for detecting and recognizing objects as well as help people understand human actions and interactions with the real world. However, facing…

In this paper, we propose Spatio-TEmporal Progressive (STEP) action detector---a progressive learning framework for spatio-temporal action detection in videos. Starting from a handful of coarse-scale proposal cuboids, our approach…

Existing multimodal-based human action recognition approaches are computationally intensive, limiting their deployment in real-time applications. In this work, we present a novel and efficient pose-driven attention-guided multimodal network…

This work proposes a new end-to-end DCNN based approach for motion segmentation, especially for video sequences captured with such non-static cameras, called MOSNET. While other approaches focus on spatial or temporal context only, the…

In this paper, we propose to improve the traditional use of RNNs by employing a many to many model for video classification. We analyze the importance of modeling spatial layout and temporal encoding for daily living action recognition.…

In this paper we address the problem of human action recognition from video sequences. Inspired by the exemplary results obtained via automatic feature learning and deep learning approaches in computer vision, we focus our attention towards…

We address the problem of spatio-temporal action detection in videos. Existing methods commonly either ignore temporal context in action recognition and localization, or lack the modelling of flexible shapes of action tubes. In this paper,…

The objective of this paper is self-supervised learning from video, in particular for representations for action recognition. We make the following contributions: (i) We propose a new architecture and learning framework Memory-augmented…

Video depth estimation is essential for providing 3D scene structure in applications ranging from autonomous driving to mixed reality. Current end-to-end video depth models have established state-of-the-art performance. Although current…

Temporal action segmentation in untrimmed videos has gained increased attention recently. However, annotating action classes and frame-wise boundaries is extremely time consuming and cost intensive, especially on large-scale datasets. To…

This paper addresses the problem of face video inpainting. Existing video inpainting methods target primarily at natural scenes with repetitive patterns. They do not make use of any prior knowledge of the face to help retrieve…

Most existing 3D CNNs for video representation learning are clip-based methods, and thus do not consider video-level temporal evolution of spatio-temporal features. In this paper, we propose Video-level 4D Convolutional Neural Networks,…

Most of existing video action recognition models ingest raw RGB frames. However, the raw video stream requires enormous storage and contains significant temporal redundancy. Video compression (e.g., H.264, MPEG-4) reduces superfluous…

Recently, deep learning approach has achieved promising results in various fields of computer vision. In this paper, a new framework called Hierarchical Depth Motion Maps (HDMM) + 3 Channel Deep Convolutional Neural Networks (3ConvNets) is…

Deep neural networks require collecting and annotating large amounts of data to train successfully. In order to alleviate the annotation bottleneck, we propose a novel self-supervised representation learning approach for spatiotemporal…

This paper proposes a method to visualize the discrimination power of intermediate-layer visual patterns encoded by a DNN. Specifically, we visualize (1) how the DNN gradually learns regional visual patterns in each intermediate layer…

For video recognition task, a global representation summarizing the whole contents of the video snippets plays an important role for the final performance. However, existing video architectures usually generate it by using a simple, global…

This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDNI) and Dynamic Depth Motion Normal Images (DDMNI), for both…

We propose a novel landmarks-assisted collaborative end-to-end deep framework for automatic 4D FER. Using 4D face scan data, we calculate its various geometrical images, and afterwards use rank pooling to generate their dynamic images…

Despite the fact that notable improvements have been made recently in the field of feature extraction and classification, human action recognition is still challenging, especially in images, in which, unlike videos, there is no motion.…