Related papers: Enhancing Unsupervised Video Representation Learni…

We address the problem of data augmentation for video action recognition. Standard augmentation strategies in video are hand-designed and sample the space of possible augmented data points either at random, without knowing which augmented…

The problem of determining whether an object is in motion, irrespective of camera motion, is far from being solved. We address this challenging task by learning motion patterns in videos. The core of our approach is a fully convolutional…

Human action recognition has become one of the most active field of research in computer vision due to its wide range of applications, like surveillance, medical, industrial environments, smart homes, among others. Recently, deep learning…

Learning visual representations from observing actions to benefit robot visuo-motor policy generation is a promising direction that closely resembles human cognitive function and perception. Motivated by this, and further inspired by…

Supervised (pre-)training currently yields state-of-the-art performance for representation learning for visual recognition, yet it comes at the cost of (1) intensive manual annotations and (2) an inherent restriction in the scope of data…

Detecting anomalies in human-related videos is crucial for surveillance applications. Current methods primarily include appearance-based and action-based techniques. Appearance-based methods rely on low-level visual features such as color,…

We propose a deep neural network for the prediction of future frames in natural video sequences. To effectively handle complex evolution of pixels in videos, we propose to decompose the motion and content, two key components generating…

Learning object-centric representations from unsupervised videos is challenging. Unlike most previous approaches that focus on decomposing 2D images, we present a 3D generative model named DynaVol-S for dynamic scenes that enables…

This paper addresses the problem of self-supervised video representation learning from a new perspective -- by video pace prediction. It stems from the observation that human visual system is sensitive to video pace, e.g., slow motion, a…

Contrastive learning has shown great potential in video representation learning. However, existing approaches fail to sufficiently exploit short-term motion dynamics, which are crucial to various down-stream video understanding tasks. In…

In this paper, we present an approach for learning a visual representation from the raw spatiotemporal signals in videos. Our representation is learned without supervision from semantic labels. We formulate our method as an unsupervised…

While stochastic video prediction models enable future prediction under uncertainty, they mostly fail to model the complex dynamics of real-world scenes. For example, they cannot provide reliable predictions for scenes with a moving camera…

The Dynamic Saliency Prediction (DSP) task simulates the human selective attention mechanism to perceive the dynamic scene, which is significant and imperative in many vision tasks. Most of existing methods only consider visual cues, while…

Current state-of-the-art solutions for motion capture from a single camera are optimization driven: they optimize the parameters of a 3D human model so that its re-projection matches measurements in the video (e.g. person segmentation,…

Action recognition is a key problem in computer vision that labels videos with a set of predefined actions. Capturing both, semantic content and motion, along the video frames is key to achieve high accuracy performance on this task. Most…

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…

Maintaining proper form while exercising is important for preventing injuries and maximizing muscle mass gains. Detecting errors in workout form naturally requires estimating human's body pose. However, off-the-shelf pose estimators…

We study pre-training representations for decision-making using video data, which is abundantly available for tasks such as game agents and software testing. Even though significant empirical advances have been made on this problem, a…

We propose a method to train deep networks to decompose videos into 3D geometry (camera and depth), moving objects, and their motions, with no supervision. We build on the idea of view synthesis, which uses classical camera geometry to…

This project aims to develop a robust video surveillance system, which can segment videos into smaller clips based on the detection of activities. It uses CCTV footage, for example, to record only major events-like the appearance of a…