اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدProgression Modelling for Online and Early Gesture Detection
63
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Online and Early detection of gestures is crucial for building touchless gesture based interfaces. These interfaces should operate on a stream of video frames instead of the complete video and detect the presence of gestures at an earlier stage than post-completion for providing real time user experience. To achieve this, it is important to recognize the progression of the gesture across different stages so that appropriate responses can be triggered on reaching the desired execution stage. To address this, we propose a simple yet effective multi-task learning framework which models the progression of the gesture along with frame level recognition. The proposed framework recognizes the gestures at an early stage with high precision and also achieves state-of-the-art recognition accuracy of 87.8% which is closer to human accuracy of 88.4% on the NVIDIA gesture dataset in the offline configuration and advances the state-of-the-art by more than 4%. We also introduce tightly segmented annotations for the NVIDIA gesture dataset and setup a strong baseline for gesture localization for this dataset. We also evaluate our framework on the Montalbano dataset and report competitive results.
قيم البحث
اقرأ أيضاً
Online action detection is a task with the aim of identifying ongoing actions from streaming videos without any side information or access to future frames. Recent methods proposed to aggregate fixed temporal ranges of invisible but anticipated futur
e frames representations as supplementary features and achieved promising performance. They are based on the observation that human beings often detect ongoing actions by contemplating the future vision simultaneously. However, we observed that at different action progressions, the optimal supplementary features should be obtained from distinct temporal ranges instead of simply fixed future temporal ranges. To this end, we introduce an adaptive features sampling strategy to overcome the mentioned variable-ranges of optimal supplementary features. Specifically, in this paper, we propose a novel Learning Action Progression Network termed LAP-Net, which integrates an adaptive features sampling strategy. At each time step, this sampling strategy first estimates current action progression and then decide what temporal ranges should be used to aggregate the optimal supplementary features. We evaluated our LAP-Net on three benchmark datasets, TVSeries, THUMOS-14 and HDD. The extensive experiments demonstrate that with our adaptive feature sampling strategy, the proposed LAP-Net can significantly outperform current state-of-the-art methods with a large margin.
This paper presents an evaluation of deep neural networks for recognition of digits entered by users on a smartphone touchscreen. A new large dataset of Arabic numerals was collected for training and evaluation of the network. The dataset consists of
spatial and temporal touch data recorded for 80 digits entered by 260 users. Two neural network models were investigated. The first model was a 2D convolutional neural (ConvNet) network applied to bitmaps of the glpyhs created by interpolation of the sensed screen touches and its topology is similar to that of previously published models for offline handwriting recognition from scanned images. The second model used a 1D ConvNet architecture but was applied to the sequence of polar vectors connecting the touch points. The models were found to provide accuracies of 98.50% and 95.86%, respectively. The second model was much simpler, providing a reduction in the number of parameters from 1,663,370 to 287,690. The dataset has been made available to the community as an open source resource.
Most work on temporal action detection is formulated as an offline problem, in which the start and end times of actions are determined after the entire video is fully observed. However, important real-time applications including surveillance and driv
er assistance systems require identifying actions as soon as each video frame arrives, based only on current and historical observations. In this paper, we propose a novel framework, Temporal Recurrent Network (TRN), to model greater temporal context of a video frame by simultaneously performing online action detection and anticipation of the immediate future. At each moment in time, our approach makes use of both accumulated historical evidence and predicted future information to better recognize the action that is currently occurring, and integrates both of these into a unified end-to-end architecture. We evaluate our approach on two popular online action detection datasets, HDD and TVSeries, as well as another widely used dataset, THUMOS14. The results show that TRN significantly outperforms the state-of-the-art.
Gesture recognition and hand motion tracking are important tasks in advanced gesture based interaction systems. In this paper, we propose to apply a sliding windows filtering approach to sample the incoming streams of data from data gloves and a deci
sion tree model to recognize the gestures in real time for a manual grafting operation of a vegetable seedling propagation facility. The sequence of these recognized gestures defines the tasks that are taking place, which helps to evaluate individuals performances and to identify any bottlenecks in real time. In this work, two pairs of data gloves are utilized, which reports the location of the fingers, hands, and wrists wirelessly (i.e., via Bluetooth). To evaluate the performance of the proposed framework, a preliminary experiment was conducted in multiple lab settings of tomato grafting operations, where multiple subjects wear the data gloves while performing different tasks. Our results show an accuracy of 91% on average, in terms of gesture recognition in real time by employing our proposed framework.
Recognition of surgical gesture is crucial for surgical skill assessment and efficient surgery training. Prior works on this task are based on either variant graphical models such as HMMs and CRFs, or deep learning models such as Recurrent Neural Net
works and Temporal Convolutional Networks. Most of the current approaches usually suffer from over-segmentation and therefore low segment-level edit scores. In contrast, we present an essentially different methodology by modeling the task as a sequential decision-making process. An intelligent agent is trained using reinforcement learning with hierarchical features from a deep model. Temporal consistency is integrated into our action design and reward mechanism to reduce over-segmentation errors. Experiments on JIGSAWS dataset demonstrate that the proposed method performs better than state-of-the-art methods in terms of the edit score and on par in frame-wise accuracy. Our code will be released later.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
