Related papers: Unsupervised learning from videos using temporal c…
Time-series representation learning can extract representations from data with temporal dynamics and sparse labels. When labeled data are sparse but unlabeled data are abundant, contrastive learning, i.e., a framework to learn a latent…
Extracting physical dynamical system parameters from recorded observations is key in natural science. Current methods for automatic parameter estimation from video train supervised deep networks on large datasets. Such datasets require…
Medical image analysis using supervised deep learning methods remains problematic because of the reliance of deep learning methods on large amounts of labelled training data. Although medical imaging data repositories continue to expand…
There is a natural correlation between the visual and auditive elements of a video. In this work we leverage this connection to learn general and effective models for both audio and video analysis from self-supervised temporal…
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…
Neural networks for multi-domain learning empowers an effective combination of information from different domains by sharing and co-learning the parameters. In visual tracking, the emerging features in shared layers of a multi-domain…
Deep convolutional networks have proven to be very successful in learning task specific features that allow for unprecedented performance on various computer vision tasks. Training of such networks follows mostly the supervised learning…
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…
We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn…
We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn spatiotemporal visual representations from unlabeled videos. Our representations are learned using a contrastive loss, where two augmented clips…
Unsupervised video domain adaptation is a practical yet challenging task. In this work, for the first time, we tackle it from a disentanglement view. Our key idea is to handle the spatial and temporal domain divergence separately through…
We present a novel method for simultaneous learning of depth, egomotion, object motion, and camera intrinsics from monocular videos, using only consistency across neighboring video frames as supervision signal. Similarly to prior work, our…
We present a novel unsupervised method for face identity learning from video sequences. The method exploits the ResNet deep network for face detection and VGGface fc7 face descriptors together with a smart learning mechanism that exploits…
Domain gaps of sensor modalities pose a challenge for the design of autonomous robots. Taking a step towards closing this gap, we propose two unsupervised training frameworks for finding a common representation of LiDAR and camera data. The…
The standard way of training video models entails sampling at each iteration a single clip from a video and optimizing the clip prediction with respect to the video-level label. We argue that a single clip may not have enough temporal…
Deep learning methods are successfully used in applications pertaining to ubiquitous computing, health, and well-being. Specifically, the area of human activity recognition (HAR) is primarily transformed by the convolutional and recurrent…
A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias. While most existing works implicitly achieve this with video-specific pretext tasks (e.g., predicting…
Temporal prediction is inherently uncertain, but representing the ambiguity in natural image sequences is a challenging high-dimensional probabilistic inference problem. For natural scenes, the curse of dimensionality renders explicit…
Automated Human Activity Recognition has long been a problem of great interest in human-centered and ubiquitous computing. In the last years, a plethora of supervised learning algorithms based on deep neural networks has been suggested to…
The recent success in deep learning has lead to various effective representation learning methods for videos. However, the current approaches for video representation require large amount of human labeled datasets for effective learning. We…