English
Related papers

Related papers: E2E-LOAD: End-to-End Long-form Online Action Detec…

200 papers

We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that reduces contextual bandit learning with general reward function approximation to offline regression. The framework allows near-optimal regret for contextual…

Machine Learning · Computer Science 2026-02-11 Hao Qin , Chicheng Zhang

Estimating abnormal posture based on 3D pose is vital in human pose analysis, yet it presents challenges, especially when reconstructing 3D human poses from monocular datasets with occlusions. Accurate reconstructions enable the restoration…

Computer Vision and Pattern Recognition · Computer Science 2024-07-25 Su Li , Wang Liang , Jianye Wang , Ziheng Zhang , Lei Zhang

End-to-end (E2E) neural modeling has emerged as one predominant school of thought to develop computer-assisted language training (CAPT) systems, showing competitive performance to conventional pronunciation-scoring based methods. However,…

Computation and Language · Computer Science 2022-02-23 Hsin-Wei Wang , Bi-Cheng Yan , Hsuan-Sheng Chiu , Yung-Chang Hsu , Berlin Chen

In voice-enabled applications, a predetermined hotword isusually used to activate a device in order to attend to the query.However, speaking queries followed by a hotword each timeintroduces a cognitive burden in continued conversations.…

Computation and Language · Computer Science 2022-08-30 Shuo-yiin Chang , Guru Prakash , Zelin Wu , Qiao Liang , Tara N. Sainath , Bo Li , Adam Stambler , Shyam Upadhyay , Manaal Faruqui , Trevor Strohman

Recently, there has been a strong push to transition from hybrid models to end-to-end (E2E) models for automatic speech recognition. Currently, there are three promising E2E methods: recurrent neural network transducer (RNN-T), RNN…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-31 Jinyu Li , Yu Wu , Yashesh Gaur , Chengyi Wang , Rui Zhao , Shujie Liu

Fast and accurate video object recognition, which relies on frame-by-frame video analytics, remains a challenge for resource-constrained devices such as traffic cameras. Recent advances in mobile edge computing have made it possible to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Kun Guo , Yun Shen , Xijun Wang , Chaoqun You , Yun Rui , Tony Q. S. Quek

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…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Xiaoyu Li , Peidong Li , Xian Wu , Long Shi , Dedong Liu , Yitao Wu , Jiajia Fu , Dixiao Cui , Lijun Zhao , Lining Sun

Most existing Multi-Object Tracking (MOT) approaches follow the Tracking-by-Detection paradigm and the data association framework where objects are firstly detected and then associated. Although deep-learning based method can noticeably…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Xingyu Wan , Jiakai Cao , Sanping Zhou , Jinjun Wang

End-to-end (E2E) models fold the acoustic, pronunciation and language models of a conventional speech recognition model into one neural network with a much smaller number of parameters than a conventional ASR system, thus making it suitable…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-14 Bo Li , Shuo-yiin Chang , Tara N. Sainath , Ruoming Pang , Yanzhang He , Trevor Strohman , Yonghui Wu

We present an online approach to efficiently and simultaneously detect and track the 2D pose of multiple people in a video sequence. We build upon Part Affinity Field (PAF) representation designed for static images, and propose an…

Computer Vision and Pattern Recognition · Computer Science 2019-06-14 Yaadhav Raaj , Haroon Idrees , Gines Hidalgo , Yaser Sheikh

Spatio-temporal action detection (STAD) aims to classify the actions present in a video and localize them in space and time. It has become a particularly active area of research in computer vision because of its explosively emerging…

Computer Vision and Pattern Recognition · Computer Science 2023-08-04 Peng Wang , Fanwei Zeng , Yuntao Qian

Dominant approaches to action detection can only provide sub-optimal solutions to the problem, as they rely on seeking frame-level detections, to later compose them into "action tubes" in a post-processing step. With this paper we radically…

Computer Vision and Pattern Recognition · Computer Science 2017-08-08 Suman Saha , Gurkirt Singh , Fabio Cuzzolin

Most recent approaches for online action detection tend to apply Recurrent Neural Network (RNN) to capture long-range temporal structure. However, RNN suffers from non-parallelism and gradient vanishing, hence it is hard to be optimized. In…

Computer Vision and Pattern Recognition · Computer Science 2021-06-22 Xiang Wang , Shiwei Zhang , Zhiwu Qing , Yuanjie Shao , Zhengrong Zuo , Changxin Gao , Nong Sang

Designing a real-time framework for the spatio-temporal action detection task is still a challenge. In this paper, we propose a novel real-time action detection framework, YOWOv2. In this new framework, YOWOv2 takes advantage of both the 3D…

Computer Vision and Pattern Recognition · Computer Science 2023-06-09 Jianhua Yang , Kun Dai

In online action detection, the goal is to detect the start of an action in a video stream as soon as it happens. For instance, if a child is chasing a ball, an autonomous car should recognize what is going on and respond immediately. This…

Computer Vision and Pattern Recognition · Computer Science 2016-08-31 Roeland De Geest , Efstratios Gavves , Amir Ghodrati , Zhenyang Li , Cees Snoek , Tinne Tuytelaars

In this paper, we propose Two-Stream AMTnet, which leverages recent advances in video-based action representation[1] and incremental action tube generation[2]. Majority of the present action detectors follow a frame-based representation, a…

Computer Vision and Pattern Recognition · Computer Science 2020-04-06 Suman Saha , Gurkirt Singh , Fabio Cuzzolin

Different from traditional action recognition based on video segments, online action recognition aims to recognize actions from unsegmented streams of data in a continuous manner. One way for online recognition is based on the evidence…

Computer Vision and Pattern Recognition · Computer Science 2017-07-07 Chang Tang , Pichao Wang , Wanqing Li

The requirements for many applications of state-of-the-art speech recognition systems include not only low word error rate (WER) but also low latency. Specifically, for many use-cases, the system must be able to decode utterances in a…

End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present numerous challenges: In order to be truly useful, such models…

Expandable networks have demonstrated their advantages in dealing with catastrophic forgetting problem in incremental learning. Considering that different tasks may need different structures, recent methods design dynamic structures adapted…

Computer Vision and Pattern Recognition · Computer Science 2022-07-15 Guimei Cao , Zhanzhan Cheng , Yunlu Xu , Duo Li , Shiliang Pu , Yi Niu , Fei Wu