Importance Of Different Frames Research Articles

SUM-GAN-GEA: Video Summarization Using GAN with Gaussian Distribution and External Attention

Video summarization aims to generate a sparse subset that is more concise and less redundant than the original video while containing the most informative parts of the video. However, previous works ignore the prior knowledge of the distribution of interestingness of video frames, making it hard for the network to learn the importance of different frames. Furthermore, traditional models alone (such as RNN and LSTM) are not robust enough in capturing global features of the video sequence since the video frames are more in line with non-Euclidean data structure. To this end, we propose a new summarization method based on the graph model concept to learn the feature relationship connections between video frames, which can guide the summary generator to generate a robust global feature representation. Specifically, we propose to use adversarial learning to integrate Gaussian distribution and external attention mechanism (SUM-GAN-GEA). The Gaussian function is a priori mapping function that considers the distribution of the interestingness of actual video frames and the external attention can reduce the inference time of the model. Experimental results on two popular video abstraction datasets (SumMe and TVSum) demonstrate the high superiority and competitiveness of our method in robustness and fast convergence.

Deep learning-based monitoring of surface residual stress and efficient sensing of AE for laser shock peening

• A multi-channel acoustic emission real-time efficient signal detection method and acquisition system. • A novel spatio-temporal complementary model (CNN-LSTM) for fusion of time-varying AE signal. • Dual circulation LSTM explains the decay mechanism of AE using temporal sampling points. • Stronger correlation between information from AE attenuation profile and surface quality. Laser shock peening (LSP) is one of the main anti-fatigue technologies in high-end manufacturing industries. However, guaranteeing its quality consistency is difficult due to its process complexity. Acoustic emission (AE) is a promising solution to accurately monitoring the surface quality of LSP, although, the large scale of monitoring data is still challenging for industrial applications. This paper studied the in-situ evaluation of surface residual compressive stress (SRCS) for 7075 aluminum alloy in LSP and the efficient sensing of AE based on deep learning methods. Firstly, a monitoring system of LSP with four types of AE sensors was developed in order to simultaneously acquire both the ultra-high and ultra-low amplitude of shock wave. The performance of those sensors is further quantitatively evaluated via long-short term memory (LSTM). Then, a new spatio-temporal parallel CNN-LSTM model for SRCS classification was proposed and experimentally validated to outperform CNN and LSTM after parameters optimization. Finally, aiming to efficient sensing of AE, the importance of different frames of AE signal was analyzed by means of the proposed dual circulation LSTM (DC-LSTM) model, which can accurately locate the key frame of time series signal. Besides, the effects of different frames of AE on classification performance was discussed. It was found that the broadband AE sensor without attenuator shows the highest classification accuracy, while the fast decay stage of AE signal has more contribution to the SRCS classification. This paper provides guidance for real-time non-destructive evaluation of residual stress via AE in laser manufacturing.

Application of congestion avoidance mechanism in multimedia transmission over mesh networks

The unreliable nature and shared multi-media of multi-hop communications cause the deployment of multi-media applications in wireless mesh network (WMN) a thorny problem. For instance, video is usually compressed into a group of frames before transmission, resulting in unrecoverable destruction during the display process. The importance of different frames' type is quite different. However, they are considered as same in most existing WMNs. In this paper, we propose a novel Congestion Avoidance Mechanism for multimedia transmission over 802.11e mesh networks. In our mechanism, we added priority for video packets. According to the significance of frames, we proposed an adaptive mechanism involves the mapping of H.264 video packets to appropriate access categories in IEEE 802.11e standard. Simulation results show that our mechanism improves quality of service (QoS) of multimedia transmission.

Video-based person re-identification via spatio-temporal attentional and two-stream fusion convolutional networks

Person re-identification aims at matching the identity of a same person that is captured from non-overlapping cameras. Most of the existing person re-identification methods are still focused on image-based solution. The problem of video-based person re-identification is better handled since video includes spatial and temporal information of pedestrians rather than a separate image. In this paper, we propose a novel approach for video-based person re-identification using spatio-temporal attentional and two-stream fusion convolutional networks, which consist of the two-stream fusion convolutional neural networks (TSF-CNN), the long short-term memory networks (LSTM), the spatial attention subnetwork and the temporal attention subnetwork. Specifically, the TSF-CNN learns the temporal and spatial characteristics simultaneously, and performs two fusions to achieve better feature representation. The spatial attention network is to automatically select the important part of pedestrian image in each frame. The temporal attention model assigns different weights according to the importance of different frames. Experiments on benchmark datasets demonstrate that the proposed approach is superior to existing methods of video-based person re-identification.

GOP-level transmission distortion modeling for mobile streaming video

Unequal loss protection is an effective tool in delivering compressed video streaming over packet-switched networks robustly. A critical component in any unequal-loss-protection scheme is a metric for evaluating the importance of different frames in a Group-Of-Pictures (GOP). In the case of video streaming over 3G mobile networks, packet loss usually corresponds to whole-frame loss due to low bandwidth and small picture size, which results in high error rates and thus most of the existing low-complexity transmission-distortion-estimate models may be ineffective. In this paper, we firstly develop a recursive algorithm to compute the GOP-level transmission distortion at pixel-level precision using pre-computed video information. Based on the study on the propagating behavior of the whole-frame-loss transmission distortion, we then propose a piecewise linear-fitting approach to achieve low-complexity transmission distortion modeling. The simulation results demonstrate that the proposed two models are accurate and robust. The proposed transmission distortion models are fast and accurate importance assessment tools in allocating limited channel resources optimally for the mobile streaming video.

Out-Classed by Our Critics?

The Australian researchers offer one apparently damning criticism of Social Class in Modern Britain. Our treatment of the British survey findings on class identity are 'the height of sociological naivety', since we 'blandly inform readers' that social class identities have retained their salience, 'without any apparent reflection as to [the] veracity' of these data. Our results are merely 'an artefact of the design of [the] survey rather than an accurate reflection of the prevailing patterns of social identities in British society'. An alternative research strategy, 'making discursively available to . . . respondents other sources of identity formation', confirms that, in the Australian context, 'the relative salience of class as a source of social identity is . . . minimal'. In our defence we would submit that nowhere do we claim 'class is . . . the only category of subjective importance for Britons'. We simply maintain that (contrary to the weight of then prevailing academic opinion ) 'people's perceptions of social class are [still] sufficiently concrete to enable them to see this as a possible source of social identity' (Marshall et al. 1988:147). Or, again, that 'class is readily available as a source of social identity to most people' (Marshall et al. 1988:155). Even these more modest conclusions are but cautiously proferred. Thus, we explicitly concede that 'survey research [in general] is not the most appropriate vehicle for investigating the importance of different frames of reference in everyday life', and that our question about reference groups in particular 'is a fairly blunt strategy for unearthing the subtleties of social identities' (Marshall et al. 1988:148-49). Our reflections as to the veracity