中文
相关论文

相关论文: Seeing Fast and Slow: Learning the Flow of Time in…

200 篇论文

We propose a method for generating a temporally remapped video that matches the desired target duration while maximally preserving natural video dynamics. Our approach trains a neural network through self-supervision to recognize and…

计算机视觉与模式识别 · 计算机科学 2022-05-12 Simon Jenni , Markus Woodson , Fabian Caba Heilbron

We wish to automatically predict the "speediness" of moving objects in videos---whether they move faster, at, or slower than their "natural" speed. The core component in our approach is SpeedNet---a novel deep network trained to detect if a…

计算机视觉与模式识别 · 计算机科学 2020-07-28 Sagie Benaim , Ariel Ephrat , Oran Lang , Inbar Mosseri , William T. Freeman , Michael Rubinstein , Michal Irani , Tali Dekel

Understanding temporal dynamics of video is an essential aspect of learning better video representations. Recently, transformer-based architectural designs have been extensively explored for video tasks due to their capability to capture…

计算机视觉与模式识别 · 计算机科学 2022-07-20 Sukmin Yun , Jaehyung Kim , Dongyoon Han , Hwanjun Song , Jung-Woo Ha , Jinwoo Shin

We propose a self-supervised visual learning method by predicting the variable playback speeds of a video. Without semantic labels, we learn the spatio-temporal visual representation of the video by leveraging the variations in the visual…

计算机视觉与模式识别 · 计算机科学 2021-06-02 Hyeon Cho , Taehoon Kim , Hyung Jin Chang , Wonjun Hwang

Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem using temporal cycle consistency jointly in vision and…

计算机视觉与模式识别 · 计算机科学 2021-09-14 Dave Epstein , Jiajun Wu , Cordelia Schmid , Chen Sun

We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time…

计算机视觉与模式识别 · 计算机科学 2022-06-10 Tim Brooks , Janne Hellsten , Miika Aittala , Ting-Chun Wang , Timo Aila , Jaakko Lehtinen , Ming-Yu Liu , Alexei A. Efros , Tero Karras

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…

计算机视觉与模式识别 · 计算机科学 2020-09-07 Jiangliu Wang , Jianbo Jiao , Yun-Hui Liu

Motion control is crucial for generating expressive and compelling video content; however, most existing video generation models rely mainly on text prompts for control, which struggle to capture the nuances of dynamic actions and temporal…

Based on life-long observations of physical, chemical, and biologic phenomena in the natural world, humans can often easily picture in their minds what an object will look like in the future. But, what about computers? In this paper, we…

计算机视觉与模式识别 · 计算机科学 2016-08-30 Yipin Zhou , Tamara L. Berg

Despite the recent success of neural networks in image feature learning, a major problem in the video domain is the lack of sufficient labeled data for learning to model temporal information. In this paper, we propose an unsupervised…

计算机视觉与模式识别 · 计算机科学 2016-11-29 Linchao Zhu , Zhongwen Xu , Yi Yang

Understanding temporal information and how the visual world changes over time is a fundamental ability of intelligent systems. In video understanding, temporal information is at the core of many current challenges, including compression,…

计算机视觉与模式识别 · 计算机科学 2019-10-31 Laura Sevilla-Lara , Shengxin Zha , Zhicheng Yan , Vedanuj Goswami , Matt Feiszli , Lorenzo Torresani

Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and the success of visual models trained contrastively with language. While these factors have…

计算机视觉与模式识别 · 计算机科学 2026-05-25 Mantas Skackauskas , Xinyue Hao , Laura Sevilla-Lara

In this dissertation, I present my work towards exploring temporal information for better video understanding. Specifically, I have worked on two problems: action recognition and semantic segmentation. For action recognition, I have…

计算机视觉与模式识别 · 计算机科学 2019-05-28 Yi Zhu

Video motion magnification techniques allow us to see small motions previously invisible to the naked eyes, such as those of vibrating airplane wings, or swaying buildings under the influence of the wind. Because the motion is small, the…

计算机视觉与模式识别 · 计算机科学 2019-02-18 Tae-Hyun Oh , Ronnachai Jaroensri , Changil Kim , Mohamed Elgharib , Frédo Durand , William T. Freeman , Wojciech Matusik

Traditionally, vision models have predominantly relied on spatial features extracted from static images, deviating from the continuous stream of spatiotemporal features processed by the brain in natural vision. While numerous…

计算机视觉与模式识别 · 计算机科学 2024-07-18 Amir Hosein Fadaei , Mohammad-Reza A. Dehaqani

Diffusion models have made significant strides in image generation, mastering tasks such as unconditional image synthesis, text-image translation, and image-to-image conversions. However, their capability falls short in the realm of video…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Gaurav Shrivastava , Abhinav Shrivastava

Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos,…

计算机视觉与模式识别 · 计算机科学 2023-08-24 Mohammadreza Salehi , Efstratios Gavves , Cees G. M. Snoek , Yuki M. Asano

Recent advances in generative video models have enabled the creation of high-quality videos based on natural language prompts. However, these models frequently lack fine-grained temporal control, meaning they do not allow users to specify…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Shira Schiber , Ofir Lindenbaum , Idan Schwartz

Text-to-video diffusion models are notoriously limited in their ability to model temporal aspects such as motion, physics, and dynamic interactions. Existing approaches address this limitation by retraining the model or introducing external…

计算机视觉与模式识别 · 计算机科学 2025-06-05 Ariel Shaulov , Itay Hazan , Lior Wolf , Hila Chefer

Understanding and predicting motion is a fundamental component of visual intelligence. Although modern video models exhibit strong comprehension of scene dynamics, exploring multiple possible futures through full video synthesis remains…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Nick Stracke , Kolja Bauer , Stefan Andreas Baumann , Miguel Angel Bautista , Josh Susskind , Björn Ommer
‹ 上一页 1 2 3 10 下一页 ›