中文
相关论文

相关论文: Leveraging Next-Active Objects for Context-Aware A…

200 篇论文

The rapid advancement of sensor technologies and artificial intelligence are creating new opportunities for traffic safety enhancement. Dashboard cameras (dashcams) have been widely deployed on both human driving vehicles and automated…

计算机视觉与模式识别 · 计算机科学 2021-12-22 Muhammad Monjurul Karim , Yu Li , Ruwen Qin , Zhaozheng Yin

In this paper, we present a method to detect the hand-object interaction from an egocentric perspective. In contrast to massive data-driven discriminator based method like \cite{Shan20}, we propose a novel workflow that utilises the cues of…

计算机视觉与模式识别 · 计算机科学 2021-10-01 Yao Lu , Walterio W. Mayol-Cuevas

Accurately detecting active objects undergoing state changes is essential for comprehending human interactions and facilitating decision-making. The existing methods for active object detection (AOD) primarily rely on visual appearance of…

计算机视觉与模式识别 · 计算机科学 2024-05-22 Dejie Yang , Yang Liu

Learning how to interact with objects is an important step towards embodied visual intelligence, but existing techniques suffer from heavy supervision or sensing requirements. We propose an approach to learn human-object interaction…

计算机视觉与模式识别 · 计算机科学 2019-04-04 Tushar Nagarajan , Christoph Feichtenhofer , Kristen Grauman

Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized…

计算机视觉与模式识别 · 计算机科学 2021-10-28 Saurabh Sahu , Palash Goyal

Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens. Consequently, they lack an inherent incentive to compress history into compact latent states with…

Recently, video transformers have shown great success in video understanding, exceeding CNN performance; yet existing video transformer models do not explicitly model objects, although objects can be essential for recognizing actions. In…

计算机视觉与模式识别 · 计算机科学 2022-06-13 Roei Herzig , Elad Ben-Avraham , Karttikeya Mangalam , Amir Bar , Gal Chechik , Anna Rohrbach , Trevor Darrell , Amir Globerson

Forecasting long-term 3D human motion is challenging: the stochasticity of human behavior makes it hard to generate realistic human motion from the input sequence alone. Information on the scene environment and the motion of nearby people…

计算机视觉与模式识别 · 计算机科学 2024-09-19 Felix B Mueller , Julian Tanke , Juergen Gall

Predicting the future interaction of objects when they come into contact with their environment is key for autonomous agents to take intelligent and anticipatory actions. This paper presents a perception framework that fuses visual and…

机器学习 · 计算机科学 2021-01-21 Sahand Rezaei-Shoshtari , Francois Robert Hogan , Michael Jenkin , David Meger , Gregory Dudek

We envision that in the near future, humanoid robots would share home space and assist us in our daily and routine activities through object manipulations. One of the fundamental technologies that need to be developed for robots is to…

计算机视觉与模式识别 · 计算机科学 2020-02-11 Sayantan Chatterjee , Faheem H. Zunjani , Souvik Sen , Gora C. Nandi

Close human-robot cooperation is a key enabler for new developments in advanced manufacturing and assistive applications. Close cooperation require robots that can predict human actions and intent, and understand human non-verbal cues.…

人机交互 · 计算机科学 2019-02-19 Paul Schydlo , Mirko Rakovic , Lorenzo Jamone , José Santos-Victor

Predictive Process Monitoring focuses on predicting future states of ongoing process executions, such as forecasting the remaining time. Recent developments in Object-Centric Process Mining have enriched event data with objects and their…

机器学习 · 计算机科学 2024-04-17 Tim K. Smit , Hajo A. Reijers , Xixi Lu

In video analysis, understanding the temporal context is crucial for recognizing object interactions, event patterns, and contextual changes over time. The proposed model leverages adjacency and semantic similarities between objects from…

计算机视觉与模式识别 · 计算机科学 2024-08-26 Ahnaf Farhan , M. Shahriar Hossain

Egocentric videos can bring a lot of information about how humans perceive the world and interact with the environment, which can be beneficial for the analysis of human behaviour. The research in egocentric video analysis is developing…

计算机视觉与模式识别 · 计算机科学 2021-07-29 Ivan Rodin , Antonino Furnari , Dimitrios Mavroedis , Giovanni Maria Farinella

Humans possess the innate ability to extract latent visuo-lingual cues to infer context through human interaction. During collaboration, this enables proactive prediction of the underlying intention of a series of tasks. In contrast,…

机器人学 · 计算机科学 2023-10-05 Pranay Mathur

Recent approaches have successfully focused on the segmentation of static reconstructions, thereby equipping downstream applications with semantic 3D understanding. However, the world in which we live is dynamic, characterized by numerous…

机器人学 · 计算机科学 2025-03-12 Tjark Behrens , René Zurbrügg , Marc Pollefeys , Zuria Bauer , Hermann Blum

We consider the problem of predicting the future trajectory of scene agents from egocentric views obtained from a moving platform. This problem is important in a variety of domains, particularly for autonomous systems making reactive or…

计算机视觉与模式识别 · 计算机科学 2020-08-10 Srikanth Malla , Behzad Dariush , Chiho Choi

Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional modules to capture…

计算机视觉与模式识别 · 计算机科学 2025-03-19 Haoxing Chen , Zizheng Huang , Yan Hong , Yanshuo Wang , Zhongcai Lyu , Zhuoer Xu , Jun Lan , Zhangxuan Gu

Anticipating actions before they occur is a core challenge in action understanding research. While conventional methods rely on extracting and aggregating temporal information from videos, as humans we can often predict upcoming actions by…

Robust multi-object tracking (MOT) is a prerequisite fora safe deployment of self-driving cars. Tracking objects, however, remains a highly challenging problem, especially in cluttered autonomous driving scenes in which objects tend to…

计算机视觉与模式识别 · 计算机科学 2020-08-20 Wei-Chih Hung , Henrik Kretzschmar , Tsung-Yi Lin , Yuning Chai , Ruichi Yu , Ming-Hsuan Yang , Dragomir Anguelov