中文
相关论文

相关论文: Unsupervised Learning of Long-Term Motion Dynamics…

200 篇论文

The problem of action recognition involves locating the action in the video, both over time and spatially in the image. The dominant current approaches use supervised learning to solve this problem, and require large amounts of annotated…

计算机视觉与模式识别 · 计算机科学 2020-03-30 Sathyanarayanan N. Aakur , Sudeep Sarkar

Pre-training on large scale unlabelled datasets has shown impressive performance improvements in the fields of computer vision and natural language processing. Given the advent of large-scale instructional video datasets, a common strategy…

计算机视觉与模式识别 · 计算机科学 2021-11-04 Valentin Gabeur , Arsha Nagrani , Chen Sun , Karteek Alahari , Cordelia Schmid

This paper presents a new self-supervised system for learning to detect novel and previously unseen categories of objects in images. The proposed system receives as input several unlabeled videos of scenes containing various objects. The…

计算机视觉与模式识别 · 计算机科学 2021-08-25 Juntao Tan , Changkyu Song , Abdeslam Boularias

Because of the rich dynamical structure of videos and their ubiquity in everyday life, it is a natural idea that video data could serve as a powerful unsupervised learning signal for training visual representations in deep neural networks.…

计算机视觉与模式识别 · 计算机科学 2020-03-12 Chengxu Zhuang , Tianwei She , Alex Andonian , Max Sobol Mark , Daniel Yamins

Anticipating actions and objects before they start or appear is a difficult problem in computer vision with several real-world applications. This task is challenging partly because it requires leveraging extensive knowledge of the world…

计算机视觉与模式识别 · 计算机科学 2016-12-01 Carl Vondrick , Hamed Pirsiavash , Antonio Torralba

We study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only, which can be reused for downstream tasks such as action recognition. This task, however, is extremely…

计算机视觉与模式识别 · 计算机科学 2021-03-16 Peihao Chen , Deng Huang , Dongliang He , Xiang Long , Runhao Zeng , Shilei Wen , Mingkui Tan , Chuang Gan

Learning-based video compression has been extensively studied over the past years, but it still has limitations in adapting to various motion patterns and entropy models. In this paper, we propose multi-mode video compression (MMVC), a…

图像与视频处理 · 电气工程与系统科学 2023-04-06 Bowen Liu , Yu Chen , Rakesh Chowdary Machineni , Shiyu Liu , Hun-Seok Kim

Human activity understanding with 3D/depth sensors has received increasing attention in multimedia processing and interactions. This work targets on developing a novel deep model for automatic activity recognition from RGB-D videos. We…

计算机视觉与模式识别 · 计算机科学 2017-08-01 Keze Wang , Xiaolong Wang , Liang Lin , Meng Wang , Wangmeng Zuo

Action recognition and detection in the context of long untrimmed video sequences has seen an increased attention from the research community. However, annotation of complex activities is usually time consuming and challenging in practice.…

计算机视觉与模式识别 · 计算机科学 2021-05-04 Sirnam Swetha , Hilde Kuehne , Yogesh S Rawat , Mubarak Shah

With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly…

计算机视觉与模式识别 · 计算机科学 2026-02-23 Yuxiao Chen , Jue Wang , Zhikang Zhang , Jingru Yi , Xu Zhang , Yang Zou , Zhaowei Cai , Jianbo Yuan , Xinyu Li , Hao Yang , Davide Modolo

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

Human motion prediction and understanding is a challenging problem. Due to the complex dynamic of human motion and the non-deterministic aspect of future prediction. We propose a novel sequence-to-sequence model for human motion prediction…

计算机视觉与模式识别 · 计算机科学 2021-01-01 Emad Barsoum , John Kender , Zicheng Liu

Video object segmentation is challenging due to the factors like rapidly fast motion, cluttered backgrounds, arbitrary object appearance variation and shape deformation. Most existing methods only explore appearance information between two…

计算机视觉与模式识别 · 计算机科学 2016-12-28 Kaihua Zhang , Xuejun Li , Qingshan Liu

Learning reliable motion representation between consecutive frames, such as optical flow, has proven to have great promotion to video understanding. However, the TV-L1 method, an effective optical flow solver, is time-consuming and…

计算机视觉与模式识别 · 计算机科学 2021-03-08 Xiaohang Yang , Lingtong Kong , Jie Yang

Self-supervised learning of image representations by predicting future frames is a promising direction but still remains a challenge. This is because of the under-determined nature of frame prediction; multiple potential futures can arise…

计算机视觉与模式识别 · 计算机科学 2024-08-12 Huiwon Jang , Dongyoung Kim , Junsu Kim , Jinwoo Shin , Pieter Abbeel , Younggyo Seo

Human motion prediction is consisting in forecasting future body poses from historically observed sequences. It is a longstanding challenge due to motion's complex dynamics and uncertainty. Existing methods focus on building up complicated…

计算机视觉与模式识别 · 计算机科学 2024-03-22 Zhihao Wang , Yulin Zhou , Ningyu Zhang , Xiaosong Yang , Jun Xiao , Zhao Wang

We present a generative approach to forecast long-term future human behavior in 3D, requiring only weak supervision from readily available 2D human action data. This is a fundamental task enabling many downstream applications. The required…

计算机视觉与模式识别 · 计算机科学 2024-05-20 Christian Diller , Thomas Funkhouser , Angela Dai

We present a solution for the goal of extracting a video from a single motion blurred image to sequentially reconstruct the clear views of a scene as beheld by the camera during the time of exposure. We first learn motion representation…

计算机视觉与模式识别 · 计算机科学 2022-01-31 Kuldeep Purohit , Anshul Shah , A. N. Rajagopalan

Understanding and predicting video content is essential for planning and reasoning in dynamic environments. Despite advancements, unsupervised learning of object representations and dynamics remains challenging. We present VideoPCDNet, an…

计算机视觉与模式识别 · 计算机科学 2025-06-25 Noel José Rodrigues Vicente , Enrique Lehner , Angel Villar-Corrales , Jan Nogga , Sven Behnke

We propose a novel neural representation for videos (NeRV) which encodes videos in neural networks. Unlike conventional representations that treat videos as frame sequences, we represent videos as neural networks taking frame index as…

计算机视觉与模式识别 · 计算机科学 2021-10-27 Hao Chen , Bo He , Hanyu Wang , Yixuan Ren , Ser-Nam Lim , Abhinav Shrivastava