English
Related papers

Related papers: Moving Off-the-Grid: Scene-Grounded Video Represen…

200 papers

Perceptual understanding of the scene and the relationship between its different components is important for successful completion of robotic tasks. Representation learning has been shown to be a powerful technique for this, but most of the…

With the explosive growth of video data in real-world applications, a comprehensive representation of videos becomes increasingly important. In this paper, we address the problem of video scene recognition, whose goal is to learn a…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Xuzheng Yu , Chen Jiang , Wei Zhang , Tian Gan , Linlin Chao , Jianan Zhao , Yuan Cheng , Qingpei Guo , Wei Chu

Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Maryam Haghighat , Peyman Moghadam , Shaheer Mohamed , Piotr Koniusz

In a Massive Open Online Course (MOOC), predictive models of student behavior can support multiple aspects of learning, including instructor feedback and timely intervention. Ongoing courses, when the student outcomes are yet unknown, must…

Machine Learning · Computer Science 2018-12-19 Mucong Ding , Yanbang Wang , Erik Hemberg , Una-May O'Reilly

Learning semantically meaningful image transformations (i.e. rotation, thickness, blur) directly from examples can be a challenging task. Recently, the Manifold Autoencoder (MAE) proposed using a set of Lie group operators to learn image…

Image and Video Processing · Electrical Eng. & Systems 2025-04-22 Brighton Ancelin , Yenho Chen , Peimeng Guan , Chiraag Kaushik , Belen Martin-Urcelay , Alex Saad-Falcon , Nakul Singh

This paper presents an end-to-end approach for tracking static and dynamic objects for an autonomous vehicle driving through crowded urban environments. Unlike traditional approaches to tracking, this method is learned end-to-end, and is…

Computer Vision and Pattern Recognition · Computer Science 2017-04-20 Julie Dequaire , Dushyant Rao , Peter Ondruska , Dominic Wang , Ingmar Posner

Current state-of-the-art video models process a video clip as a long sequence of spatio-temporal tokens. However, they do not explicitly model objects, their interactions across the video, and instead process all the tokens in the video. In…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Xingyi Zhou , Anurag Arnab , Chen Sun , Cordelia Schmid

The recent success in deep learning has lead to various effective representation learning methods for videos. However, the current approaches for video representation require large amount of human labeled datasets for effective learning. We…

Computer Vision and Pattern Recognition · Computer Science 2018-11-30 Shruti Vyas , Yogesh S Rawat , Mubarak Shah

Recent years have witnessed a surge of interest in machine learning on graphs and networks with applications ranging from vehicular network design to IoT traffic management to social network recommendations. Supervised machine learning…

Social and Information Networks · Computer Science 2019-08-23 Manoj Reddy Dareddy , Mahashweta Das , Hao Yang

Dynamic Scene Graph Generation (DSGG) focuses on identifying visual relationships within the spatial-temporal domain of videos. Conventional approaches often employ multi-stage pipelines, which typically consist of object detection,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Guan Wang , Zhimin Li , Qingchao Chen , Yang Liu

Learning visual representations with self-supervised learning has become popular in computer vision. The idea is to design auxiliary tasks where labels are free to obtain. Most of these tasks end up providing data to learn specific kinds of…

Computer Vision and Pattern Recognition · Computer Science 2017-08-16 Xiaolong Wang , Kaiming He , Abhinav Gupta

Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks. This work aims to assess how well these features preserve information…

Computer Vision and Pattern Recognition · Computer Science 2022-12-21 Monika Wysoczańska , Tom Monnier , Tomasz Trzciński , David Picard

Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Martina G. Vilas , Timothy Schaumlöffel , Gemma Roig

Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Ziyu Zhu , Xilin Wang , Yixuan Li , Zhuofan Zhang , Xiaojian Ma , Yixin Chen , Baoxiong Jia , Wei Liang , Qian Yu , Zhidong Deng , Siyuan Huang , Qing Li

Moving Object Detection (MOD) is a fundamental step for many computer vision applications. MOD becomes very challenging when a video sequence captured from a static or moving camera suffers from the challenges: camouflage, shadow, dynamic…

Computer Vision and Pattern Recognition · Computer Science 2022-07-15 Jhony H. Giraldo , Sajid Javed , Naoufel Werghi , Thierry Bouwmans

We develop new representations and algorithms for three-dimensional (3D) object detection and spatial layout prediction in cluttered indoor scenes. We first propose a clouds of oriented gradient (COG) descriptor that links the 2D appearance…

Computer Vision and Pattern Recognition · Computer Science 2019-06-12 Zhile Ren , Erik B. Sudderth

Representation learning in dynamic graphs is a challenging problem because the topology of graph and node features vary at different time. This requires the model to be able to effectively capture both graph topology information and…

Machine Learning · Computer Science 2021-11-16 Xintao Xiang , Tiancheng Huang , Donglin Wang

We present a novel method for generating, predicting, and using Spatiotemporal Occupancy Grid Maps (SOGM), which embed future information of dynamic scenes. Our automated generation process creates groundtruth SOGMs from previous navigation…

Robotics · Computer Science 2021-09-17 Hugues Thomas , Matthieu Gallet de Saint Aurin , Jian Zhang , Timothy D. Barfoot

This paper proposes a novel memory-based online video representation that is efficient, accurate and predictive. This is in contrast to prior works that often rely on computationally heavy 3D convolutions, ignore actual motion when aligning…

Computer Vision and Pattern Recognition · Computer Science 2018-03-30 Tuan-Hung Vu , Wongun Choi , Samuel Schulter , Manmohan Chandraker

We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call "percepts" using Gated-Recurrent-Unit Recurrent Networks (GRUs).Our method relies on percepts that are extracted from all…

Computer Vision and Pattern Recognition · Computer Science 2016-03-02 Nicolas Ballas , Li Yao , Chris Pal , Aaron Courville