中文
相关论文

相关论文: Jointly Modeling Spatio-Temporal Features of Tacti…

200 篇论文

We introduce Activity Graph Transformer, an end-to-end learnable model for temporal action localization, that receives a video as input and directly predicts a set of action instances that appear in the video. Detecting and localizing…

计算机视觉与模式识别 · 计算机科学 2021-01-29 Megha Nawhal , Greg Mori

Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot…

计算机视觉与模式识别 · 计算机科学 2023-11-08 Thinh Phan , Khoa Vo , Duy Le , Gianfranco Doretto , Donald Adjeroh , Ngan Le

Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant…

计算机视觉与模式识别 · 计算机科学 2018-09-12 Xiaolin Song , Cuiling Lan , Wenjun Zeng , Junliang Xing , Jingyu Yang , Xiaoyan Sun

Gesture recognition is essential for the interaction of autonomous vehicles with humans. While the current approaches focus on combining several modalities like image features, keypoints and bone vectors, we present neural network…

计算机视觉与模式识别 · 计算机科学 2022-08-19 Adrian Holzbock , Alexander Tsaregorodtsev , Youssef Dawoud , Klaus Dietmayer , Vasileios Belagiannis

Human mobility patterns have shown significant applications in policy-decision scenarios and economic behavior researches. The human mobility simulation task aims to generate human mobility trajectories given a small set of trajectory data,…

机器学习 · 计算机科学 2024-06-07 Yu Wang , Tongya Zheng , Shunyu Liu , Zunlei Feng , Kaixuan Chen , Yunzhi Hao , Mingli Song

Video-Action Models (VAMs) have emerged as a promising framework for embodied intelligence, learning implicit world dynamics from raw video streams to produce temporally consistent action predictions. Although such models demonstrate strong…

Continuous collection of physiological data from wearable sensors enables temporal characterization of individual behaviors. Understanding the relation between an individual's behavioral patterns and psychological states can help identify…

The past decade has witnessed significant advances in time series modeling with deep learning. While achieving state-of-the-art results, the best-performing architectures vary highly across applications and domains. Meanwhile, for natural…

机器学习 · 计算机科学 2024-04-03 Defu Cao , Furong Jia , Sercan O Arik , Tomas Pfister , Yixiang Zheng , Wen Ye , Yan Liu

Deep spatiotemporal models are used in a variety of computer vision tasks, such as action recognition and video object segmentation. Currently, there is a limited understanding of what information is captured by these models in their…

计算机视觉与模式识别 · 计算机科学 2022-06-08 Matthew Kowal , Mennatullah Siam , Md Amirul Islam , Neil D. B. Bruce , Richard P. Wildes , Konstantinos G. Derpanis

In this paper, we address the challenging problem of action recognition, using event-based cameras. To recognise most gestural actions, often higher temporal precision is required for sampling visual information. Actions are defined by…

计算机视觉与模式识别 · 计算机科学 2019-03-19 Rohan Ghosh , Anupam Gupta , Andrei Nakagawa , Alcimar Soares , Nitish Thakor

Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To overcome this challenge, one recent work builds an…

计算机视觉与模式识别 · 计算机科学 2021-11-25 Le Yang , Junwei Han , Tao Zhao , Tianwei Lin , Dingwen Zhang , Jianxin Chen

In this paper, we newly introduce the concept of temporal attention filters, and describe how they can be used for human activity recognition from videos. Many high-level activities are often composed of multiple temporal parts (e.g.,…

计算机视觉与模式识别 · 计算机科学 2016-12-28 AJ Piergiovanni , Chenyou Fan , Michael S. Ryoo

Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online using unlabeled…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Zishu Zhou , Zaipeng Xie , Xuanyao Jie

Recent research has achieved impressive progress in the session-based recommendation. However, information such as item knowledge and click time interval, which could be potentially utilized to improve the performance, remains largely…

信息检索 · 计算机科学 2021-12-17 Rongzhi Zhang , Yulong Gu , Xiaoyu Shen , Hui Su

Robotic manipulation requires both rich multimodal perception and effective learning frameworks to handle complex real-world tasks. See-through-skin (STS) sensors, which combine tactile and visual perception, offer promising sensing…

机器人学 · 计算机科学 2026-02-10 Yuyang Li , Yinghan Chen , Zihang Zhao , Puhao Li , Tengyu Liu , Siyuan Huang , Yixin Zhu

Temporal action localization plays an important role in video analysis, which aims to localize and classify actions in untrimmed videos. The previous methods often predict actions on a feature space of a single-temporal scale. However, the…

计算机视觉与模式识别 · 计算机科学 2022-08-17 Zan Gao , Xinglei Cui , Tao Zhuo , Zhiyong Cheng , An-An Liu , Meng Wang , Shenyong Chen

This paper addresses spatio-temporal localization of human actions in video. In order to localize actions in time, we propose a recurrent localization network (RecLNet) designed to model the temporal structure of actions on the level of…

计算机视觉与模式识别 · 计算机科学 2018-06-29 Guilhem Chéron , Anton Osokin , Ivan Laptev , Cordelia Schmid

Research in action detection has grown in the recentyears, as it plays a key role in video understanding. Modelling the interactions (either spatial or temporal) between actors and their context has proven to be essential for this task.…

计算机视觉与模式识别 · 计算机科学 2021-06-30 Manuel Sarmiento Calderó , David Varas , Elisenda Bou-Balust

Tactile sensing is a crucial perception mode for robots and human amputees in need of controlling a prosthetic device. Today robotic and prosthetic systems are still missing the important feature of accurate tactile sensing. This lack is…

机器人学 · 计算机科学 2022-03-30 Xiaying Wang , Fabian Geiger , Vlad Niculescu , Michele Magno , Luca Benini

Spatio-temporal alignment is crucial for temporal modeling of end-to-end (E2E) perception in autonomous driving (AD), providing valuable structural and textural prior information. Existing methods typically rely on the attention mechanism…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Xiaoyu Li , Peidong Li , Xian Wu , Long Shi , Dedong Liu , Yitao Wu , Jiajia Fu , Dixiao Cui , Lijun Zhao , Lining Sun