Related papers: Im2Flow: Motion Hallucination from Static Images f…

We address unsupervised optical flow estimation for ego-centric motion. We argue that optical flow can be cast as a geometrical warping between two successive video frames and devise a deep architecture to estimate such transformation in…

Motion is an important cue for video prediction and often utilized by separating video content into static and dynamic components. Most of the previous work utilizing motion is deterministic but there are stochastic methods that can model…

This paper presents a survey of human action recognition approaches based on visual data recorded from a single video camera. We propose an organizing framework which puts in evidence the evolution of the area, with techniques moving from…

In this work we present a novel task of understanding unintentional human activities in videos. We formalize this problem as a reasoning task under zero-shot scenario, where given a video of an unintentional activity we want to know why it…

Predicting diverse object motions from a single static image remains challenging, as current video generation models often entangle object movement with camera motion and other scene changes. While recent methods can predict specific…

We introduce a way to learn to estimate a scene representation from a single image by predicting a low-dimensional subspace of optical flow for each training example, which encompasses the variety of possible camera and object movement.…

Unsupervised optical flow methods typically lack reliable uncertainty estimation, limiting their robustness and interpretability. We propose U$^{2}$Flow, the first recurrent unsupervised framework that jointly estimates optical flow and…

Among the existing modalities for 3D action recognition, 3D flow has been poorly examined, although conveying rich motion information cues for human actions. Presumably, its susceptibility to noise renders it intractable, thus challenging…

Learning and reasoning about physical phenomena is still a challenge in robotics development, and computational sciences play a capital role in the search for accurate methods able to provide explanations for past events and rigorous…

Current approaches for activity recognition often ignore constraints on computational resources: 1) they rely on extensive feature computation to obtain rich descriptors on all frames, and 2) they assume batch-mode access to the entire test…

We propose a method to interactively control the animation of fluid elements in still images to generate cinemagraphs. Specifically, we focus on the animation of fluid elements like water, smoke, fire, which have the properties of repeating…

Deep spatiotemporal models are used in a variety of computer vision tasks, such as action recognition and video object segmentation. Currently, there is a limited understanding of what information is captured by these models in their…

We present a method, Neural Radiance Flow (NeRFlow),to learn a 4D spatial-temporal representation of a dynamic scene from a set of RGB images. Key to our approach is the use of a neural implicit representation that learns to capture the 3D…

We present a method for decomposing the 3D scene flow observed from a moving stereo rig into stationary scene elements and dynamic object motion. Our unsupervised learning framework jointly reasons about the camera motion, optical flow, and…

Video recognition models often learn scene-biased action representation due to the spurious correlation between actions and scenes in the training data. Such models show poor performance when the test data consists of videos with unseen…

As a bio-inspired sensor with high temporal resolution, the spiking camera has an enormous potential in real applications, especially for motion estimation in high-speed scenes. However, frame-based and event-based methods are not well…

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

Identifying human behaviors is a challenging research problem due to the complexity and variation of appearances and postures, the variation of camera settings, and view angles. In this paper, we try to address the problem of human behavior…

We tackle the problem of estimating optical flow from a monocular camera in the context of autonomous driving. We build on the observation that the scene is typically composed of a static background, as well as a relatively small number of…

The deep two-stream architecture exhibited excellent performance on video based action recognition. The most computationally expensive step in this approach comes from the calculation of optical flow which prevents it to be real-time. This…