Related papers: A Perceptual Prediction Framework for Self Supervi…

Recent temporal action segmentation approaches need frame annotations during training to be effective. These annotations are very expensive and time-consuming to obtain. This limits their performances when only limited annotated data is…

Co-part segmentation is an important problem in computer vision for its rich applications. We propose an unsupervised learning approach for co-part segmentation from images. For the training stage, we leverage motion information embedded in…

Semi-supervised and unsupervised systems provide operators with invaluable support and can tremendously reduce the operators load. In the light of the necessity to process large volumes of video data and provide autonomous decisions, this…

This paper introduces a new, unsupervised method for automatic video summarization using ideas from generative adversarial networks but eliminating the discriminator, having a simple loss function, and separating training of different parts…

A major obstacle to building models for effective semantic segmentation, and particularly video semantic segmentation, is a lack of large and well annotated datasets. This bottleneck is particularly prohibitive in highly specialized and…

Self-supervised video representation learning aimed at maximizing similarity between different temporal segments of one video, in order to enforce feature persistence over time. This leads to loss of pertinent information related to…

We propose a weakly-supervised framework for action labeling in video, where only the order of occurring actions is required during training time. The key challenge is that the per-frame alignments between the input (video) and label…

The handling of long videos with complex and occluded sequences has recently emerged as a new challenge in the video instance segmentation (VIS) community. However, existing methods have limitations in addressing this challenge. We argue…

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…

In recent years, there has been remarkable progress in supervised image segmentation. Video segmentation is less explored, despite the temporal dimension being highly informative. Semantic labels, e.g. that cannot be accurately detected in…

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…

This thesis explores the central question of how to leverage temporal relations among video elements to advance video understanding. Addressing the limitations of existing methods, the work presents a five-fold contribution: (1) an…

This paper addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. The two streams of the network encode spatial and temporal…

We address the highly challenging problem of video object segmentation. Given only the initial mask, the task is to segment the target in the subsequent frames. In order to effectively handle appearance changes and similar background…

Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a…

Weakly-supervised action segmentation is a task of learning to partition a long video into several action segments, where training videos are only accompanied by transcripts (ordered list of actions). Most of existing methods need to infer…

Automatic video segmentation plays an important role in a wide range of computer vision and image processing applications. Recently, various methods have been proposed for this purpose. The problem is that most of these methods are far from…

This paper proposes a new framework for semantic segmentation of objects in videos. We address the label inconsistency problem of deep convolutional neural networks (DCNNs) by exploiting the fact that videos have multiple frames; in a few…

Temporal action proposals are a common module in action detection pipelines today. Most current methods for training action proposal modules rely on fully supervised approaches that require large amounts of annotated temporal action…

Deep neural networks for time series must capture complex temporal patterns, to effectively represent dynamic data. Self- and semi-supervised learning methods show promising results in pre-training large models, which -- when finetuned for…