English
Related papers

Related papers: Towards Stable Self-Supervised Object Representati…

200 papers

We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn…

Computer Vision and Pattern Recognition · Computer Science 2023-09-29 Fida Mohammad Thoker , Hazel Doughty , Cees Snoek

We propose GeoNet, a jointly unsupervised learning framework for monocular depth, optical flow and ego-motion estimation from videos. The three components are coupled by the nature of 3D scene geometry, jointly learned by our framework in…

Computer Vision and Pattern Recognition · Computer Science 2018-03-13 Zhichao Yin , Jianping Shi

As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-03-07 John Day , Tushar Arora , Jirui Liu , Li Erran Li , Ming Bo Cai

The emergence of low-cost personal mobiles devices and wearable cameras and the increasing storage capacity of video-sharing websites have pushed forward a growing interest towards first-person videos. Since most of the recorded videos…

Computer Vision and Pattern Recognition · Computer Science 2017-08-17 Michel Melo Silva , Washington Luis Souza Ramos , Joao Pedro Klock Ferreira , Mario Fernando Montenegro Campos , Erickson Rangel Nascimento

In this paper, we consider the task of unsupervised object discovery in videos. Previous works have shown promising results via processing optical flows to segment objects. However, taking flow as input brings about two drawbacks. First,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Shuangrui Ding , Weidi Xie , Yabo Chen , Rui Qian , Xiaopeng Zhang , Hongkai Xiong , Qi Tian

Driven by the increasing demand for applications in augmented and virtual reality, egocentric action recognition has emerged as a prominent research area. It is typically divided into two subtasks: recognizing the performed behavior (i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-08 Huaihai Lyu , Chaofan Chen , Yuheng Ji , Changsheng Xu

The ability to detect and track objects in the visual world is a crucial skill for any intelligent agent, as it is a necessary precursor to any object-level reasoning process. Moreover, it is important that agents learn to track objects…

Machine Learning · Computer Science 2019-11-21 Eric Crawford , Joelle Pineau

We propose a deep video prediction model conditioned on a single image and an action class. To generate future frames, we first detect keypoints of a moving object and predict future motion as a sequence of keypoints. The input image is…

Computer Vision and Pattern Recognition · Computer Science 2019-10-07 Yunji Kim , Seonghyeon Nam , In Cho , Seon Joo Kim

Understanding human actions from videos of first-person view poses significant challenges. Most prior approaches explore representation learning on egocentric videos only, while overlooking the potential benefit of exploiting existing…

Computer Vision and Pattern Recognition · Computer Science 2024-06-21 Jilan Xu , Yifei Huang , Junlin Hou , Guo Chen , Yuejie Zhang , Rui Feng , Weidi Xie

Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of predefined object categories. This closed-set paradigm is…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Mahyar Najibi , Jingwei Ji , Yin Zhou , Charles R. Qi , Xinchen Yan , Scott Ettinger , Dragomir Anguelov

Always-on egocentric cameras are increasingly used as demonstrations for embodied robotics, imitation learning, and assistive AR, but the resulting video streams are dominated by redundant and low-quality frames. Under the storage and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Ajan Subramanian , Sumukh Bettadapura , Rohan Sathish

Natural videos provide rich visual contents for self-supervised learning. Yet most existing approaches for learning spatio-temporal representations rely on manually trimmed videos, leading to limited diversity in visual patterns and limited…

Computer Vision and Pattern Recognition · Computer Science 2022-04-08 Zhiwu Qing , Shiwei Zhang , Ziyuan Huang , Yi Xu , Xiang Wang , Mingqian Tang , Changxin Gao , Rong Jin , Nong Sang

Recent Video Large Language Models (Video-LLMs) have demonstrated strong capabilities in video reasoning through reinforcement learning (RL). However, existing RL pipelines rely heavily on human-annotated tasks and solutions, making them…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Shiqi Huang , Ziyue Wang , Zhongrong Zuo , Han Qiu , Qi She , Bihan Wen

Existing unsupervised video-to-video translation methods fail to produce translated videos which are frame-wise realistic, semantic information preserving and video-level consistent. In this work, we propose UVIT, a novel unsupervised…

Computer Vision and Pattern Recognition · Computer Science 2020-04-15 Kangning Liu , Shuhang Gu , Andres Romero , Radu Timofte

In this paper, we introduce ActBERT for self-supervised learning of joint video-text representations from unlabeled data. First, we leverage global action information to catalyze the mutual interactions between linguistic texts and local…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Linchao Zhu , Yi Yang

Object-centric representations enable autonomous driving algorithms to reason about interactions between many independent agents and scene features. Traditionally these representations have been obtained via supervised learning, but this…

Computer Vision and Pattern Recognition · Computer Science 2023-07-17 Kaylene C. Stocking , Zak Murez , Vijay Badrinarayanan , Jamie Shotton , Alex Kendall , Claire Tomlin , Christopher P. Burgess

The core of video understanding tasks, such as recognition, captioning, and tracking, is to automatically detect objects or actions in a video and analyze their temporal evolution. Despite sharing a common goal, different tasks often rely…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Junke Wang , Dongdong Chen , Chong Luo , Bo He , Lu Yuan , Zuxuan Wu , Yu-Gang Jiang

This technical report describes the SViT approach for the Ego4D Point of No Return (PNR) Temporal Localization Challenge. We propose a learning framework StructureViT (SViT for short), which demonstrates how utilizing the structure of a…

Computer Vision and Pattern Recognition · Computer Science 2022-06-16 Elad Ben-Avraham , Roei Herzig , Karttikeya Mangalam , Amir Bar , Anna Rohrbach , Leonid Karlinsky , Trevor Darrell , Amir Globerson

We study the task of establishing object-level visual correspondence across different viewpoints in videos, focusing on the challenging egocentric-to-exocentric and exocentric-to-egocentric scenarios. We propose a simple yet effective…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Shannan Yan , Leqi Zheng , Keyu Lv , Jingchen Ni , Hongyang Wei , Jiajun Zhang , Guangting Wang , Jing Lyu , Chun Yuan , Fengyun Rao

With the recent successful adaptation of transformers to the vision domain, particularly when trained in a self-supervised fashion, it has been shown that vision transformers can learn impressive object-reasoning-like behaviour and features…

Computer Vision and Pattern Recognition · Computer Science 2022-10-26 Oscar Vikström , Alexander Ilin