Related papers: Super-Trajectories: A Compact Yet Rich Video Repre…
We introduce a novel semi-supervised video segmentation approach based on an efficient video representation, called as "super-trajectory". Each super-trajectory corresponds to a group of compact trajectories that exhibit consistent motion…
Due to the advent of new mobile devices and tracking sensors in recent years, huge amounts of data are being produced every day. Therefore, novel methodologies need to emerge that dive through this vast sea of information and generate…
Finding correspondences between structural entities decomposing images is of high interest for computer vision applications. In particular, we analyze how to accurately track superpixels - visual primitives generated by aggregating adjacent…
Tracking pixels in videos is typically studied as an optical flow estimation problem, where every pixel is described with a displacement vector that locates it in the next frame. Even though wider temporal context is freely available, prior…
Motion is a fundamental cue for scene analysis and human activity understan- ding in videos. It can be encoded in trajectories for tracking objects and for action recognition, or in form of flow to address behaviour analysis in crowded…
We propose a concise representation of videos that encode perceptually meaningful features into graphs. With this representation, we aim to leverage the large amount of redundancies in videos and save computations. First, we construct…
Effective spatio-temporal representation is fundamental to modeling, understanding, and predicting dynamics in videos. The atomic unit of a video, the pixel, traces a continuous 3D trajectory over time, serving as the primitive element of…
Identifying human actions in complex scenes is widely considered as a challenging research problem due to the unpredictable behaviors and variation of appearances and postures. For extracting variations in motion and postures, trajectories…
Trajectory analysis is essential in many applications. In this paper, we address the problem of representing motion trajectories in a highly informative way, and consequently utilize it for analyzing trajectories. Our approach first…
Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…
Trajectory representation learning on a network enhances our understanding of vehicular traffic patterns and benefits numerous downstream applications. Existing approaches using classic machine learning or deep learning embed trajectories…
The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a.k.a. dense tracking). We make the following contributions: (i) we propose to improve the existing…
Pixels operate locally. Superpixels have some potential to collect information across many pixels; supervoxels have more potential by implicitly operating across time. In this paper, we explore this well established notion thoroughly…
Current video representations heavily rely on unstable and over-grained priors for motion and appearance modelling, \emph{i.e.}, pixel-level matching and tracking. A tracking error of just a few pixels would lead to the collapse of the…
Trajectories can be regarded as time-series of coordinates, typically arising from motile objects. Methods for trajectory classification are particularly important to detect different movement patterns, while methods for regression to…
This paper reports on ongoing research investigating more expressive approaches to spatial-temporal trajectory clustering. Spatial-temporal data is increasingly becoming universal as a result of widespread use of GPS and mobile devices,…
True understanding of videos comes from a joint analysis of all its modalities: the video frames, the audio track, and any accompanying text such as closed captions. We present a way to learn a compact multimodal feature representation that…
We introduce a representation learning framework for spatial trajectories. We represent partial observations of trajectories as probability distributions in a learned latent space, which characterize the uncertainty about unobserved parts…
This paper provides a review on representation learning for videos. We classify recent spatiotemporal feature learning methods for sequential visual data and compare their pros and cons for general video analysis. Building effective…
The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion. However, due to noise and background motion, many generated trajectories are…