相关论文: MetaDance: Few-shot Dancing Video Retargeting via …

Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods take the correlations in the video sequence into…

Few-shot Learning aims to learn classifiers for new classes with only a few training examples per class. Existing meta-learning or metric-learning based few-shot learning approaches are limited in handling diverse domains with various…

Latent Video Diffusion Models can easily deceive casual observers and domain experts alike thanks to the produced image quality and temporal consistency. Beyond entertainment, this creates opportunities around safe data sharing of fully…

Human video generation remains challenging due to the difficulty of jointly modeling human appearance, motion, and camera viewpoint under limited multi-view data. Existing methods often address these factors separately, resulting in limited…

There currently exist two main approaches to reproducing visual appearance using Machine Learning (ML): The first is training models that generalize over different instances of a problem, e.g., different images of a dataset. As one-shot…

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…

We propose an attention-based networks for transferring motions between arbitrary objects. Given a source image(s) and a driving video, our networks animate the subject in the source images according to the motion in the driving video. In…

Deep neural networks have been able to outperform humans in some cases like image recognition and image classification. However, with the emergence of various novel categories, the ability to continuously widen the learning capability of…

We address the problem of temporal localization of repetitive activities in a video, i.e., the problem of identifying all segments of a video that contain some sort of repetitive or periodic motion. To do so, the proposed method represents…

Metric learning aims to build a distance metric typically by learning an effective embedding function that maps similar objects into nearby points in its embedding space. Despite recent advances in deep metric learning, it remains…

This paper presents a simple method for "do as I do" motion transfer: given a source video of a person dancing, we can transfer that performance to a novel (amateur) target after only a few minutes of the target subject performing standard…

Few-shot video object segmentation aims to reduce annotation costs; however, existing methods still require abundant dense frame annotations for training, which are scarce in the medical domain. We investigate an extremely low-data regime…

This paper introduces a novel deep-learning approach for human-to-robot motion retargeting, enabling robots to mimic human poses accurately. Contrary to prior deep-learning-based works, our method does not require paired human-to-robot…

In this paper, we newly introduce the concept of temporal attention filters, and describe how they can be used for human activity recognition from videos. Many high-level activities are often composed of multiple temporal parts (e.g.,…

The goal of this paper is to bypass the need for labelled examples in few-shot video understanding at run time. While proven effective, in many practical video settings even labelling a few examples appears unrealistic. This is especially…

In this paper, we investigate the challenging task of person re-identification from a new perspective and propose an end-to-end attention-based architecture for few-shot re-identification through meta-learning. The motivation for this task…

Few-shot learning focuses on learning a new visual concept with very limited labelled examples. A successful approach to tackle this problem is to compare the similarity between examples in a learned metric space based on convolutional…

In the research field of few-shot learning, the main difference between image-based and video-based is the additional temporal dimension. In recent years, some works have used the Transformer to deal with frames, then get the attention…

We address the problem of detecting attention targets in video. Our goal is to identify where each person in each frame of a video is looking, and correctly handle the case where the gaze target is out-of-frame. Our novel architecture…

Long-range temporal alignment is critical yet challenging for video restoration tasks. Recently, some works attempt to divide the long-range alignment into several sub-alignments and handle them progressively. Although this operation is…