相关论文: A Symbolic Temporal Pooling method for Video-based…

In this paper we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of interest in each frame and leverage contrastive self-supervised (CSS) learning to…

Recent years have witnessed the remarkable progress of applying deep learning models in video person re-identification (Re-ID). A key factor for video person Re-ID is to effectively construct discriminative and robust video feature…

Popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the…

In this paper, we propose a novel fully unsupervised framework that learns action representations suitable for the action segmentation task from the single input video itself, without requiring any training data. Our method is a deep metric…

We present a novel algorithm for transferring artistic styles of semantically meaningful local regions of an image onto local regions of a target video while preserving its photorealism. Local regions may be selected either fully…

Several video-based 3D pose and shape estimation algorithms have been proposed to resolve the temporal inconsistency of single-image-based methods. However it still remains challenging to have stable and accurate reconstruction. In this…

In this paper, we propose the use of a semantic image, an improved representation for video analysis, principally in combination with Inception networks. The semantic image is obtained by applying localized sparse segmentation using global…

Representations that can compactly and effectively capture the temporal evolution of semantic content are important to computer vision and machine learning algorithms that operate on multi-variate time-series data. We investigate such…

Video-based person re-identification (Re-ID) is an important computer vision task. The batch-hard triplet loss frequently used in video-based person Re-ID suffers from the Distance Variance among Different Positives (DVDP) problem. In this…

We present a symbolic learning framework inspired by cognitive-like memory functionalities (i.e., storing, retrieving, consolidating and forgetting) to generate task representations to support high-level task planning and knowledge…

Motor imagery classification based on electroencephalography (EEG) signals is one of the most important brain-computer interface applications, although it needs further improvement. Several methods have attempted to obtain useful…

Recently, with the enormous growth of online videos, fast video retrieval research has received increasing attention. As an extension of image hashing techniques, traditional video hashing methods mainly depend on hand-crafted features and…

Weakly supervised temporal action localization (WTAL) aims to detect action instances in untrimmed videos using only video-level annotations. Since many existing works optimize WTAL models based on action classification labels, they…

Instance-level alignment is widely exploited for person re-identification, e.g. spatial alignment, latent semantic alignment and triplet alignment. This paper probes another feature alignment modality, namely cluster-level feature alignment…

State-of-the-art person re-identification systems that employ a triplet based deep network suffer from a poor generalization capability. In this paper, we propose a four stream Siamese deep convolutional neural network for person…

From the frame/clip-level feature learning to the video-level representation building, deep learning methods in action recognition have developed rapidly in recent years. However, current methods suffer from the confusion caused by partial…

This paper aims to develop a new architecture that can make full use of the feature maps of convolutional networks. To this end, we study a number of methods for video-based person re-identification and make the following findings: 1)…

Deep learning models for video-based action recognition usually generate features for short clips (consisting of a few frames); such clip-level features are aggregated to video-level representations by computing statistics on these…

In this paper, we propose an unsupervised video object co-segmentation framework based on the primary object proposals to extract the common foreground object(s) from a given video set. In addition to the objectness attributes and motion…

In this paper, we propose a new video object detector (VoD) method referred to as temporal feature aggregation and motion-aware VoD (TM-VoD), which produces a joint representation of temporal image sequences and object motion. The proposed…