Understanding temporal structure for video captioning

2019 ◽  
Vol 23 (1) ◽  
pp. 147-159
Author(s):  
Shagan Sah ◽  
Thang Nguyen ◽  
Ray Ptucha
Keyword(s):  
Temporal Structure ◽  
Video Captioning

scholarly journals Video Captioning Based on Channel Soft Attention and Semantic Reconstructor

2021 ◽  
Vol 13 (2) ◽  
pp. 55
Author(s):  
Zhou Lei ◽  
Yiyong Huang
Keyword(s):  
Temporal Structure ◽  
Video Content ◽  
Global Features ◽  
Time Step ◽  
Video Captioning ◽  
3 Dimensional ◽  
Spatial Features ◽  
Video Feature ◽  
Fully Connected

Video captioning is a popular task which automatically generates a natural-language sentence to describe video content. Previous video captioning works mainly use the encoder–decoder framework and exploit special techniques such as attention mechanisms to improve the quality of generated sentences. In addition, most attention mechanisms focus on global features and spatial features. However, global features are usually fully connected features. Recurrent convolution networks (RCNs) receive 3-dimensional features as input at each time step, but the temporal structure of each channel at each time step has been ignored, which provide temporal relation information of each channel. In this paper, a video captioning model based on channel soft attention and semantic reconstructor is proposed, which considers the global information for each channel. In a video feature map sequence, the same channel of every time step is generated by the same convolutional kernel. We selectively collect the features generated by each convolutional kernel and then input the weighted sum of each channel to RCN at each time step to encode video representation. Furthermore, a semantic reconstructor is proposed to rebuild semantic vectors to ensure the integrity of semantic information in the training process, which takes advantage of both forward (semantic to sentence) and backward (sentence to semantic) flows. Experimental results on popular datasets MSVD and MSR-VTT demonstrate the effectiveness and feasibility of our model.

scholarly journals Correction to: Attention based video captioning framework for Hindi

2021 ◽  
Author(s):  
Alok Singh ◽  
Thoudam Doren Singh ◽  
Sivaji Bandyopadhyay
Keyword(s):  
Video Captioning

scholarly journals Agency and the Successive Structure of Time-Consciousness

Erkenntnis ◽  
2021 ◽  
Author(s):  
Camden Alexander McKenna
Keyword(s):  
Temporal Structure ◽  
Basic Structure ◽  
The Self ◽  
Necessary Condition ◽  
Epistemic Status ◽  
Mental Attitude ◽  
Time Consciousness ◽  
Possibility Space ◽  
The Right ◽  
Wrong Sort

AbstractI argue for constraining the nomological possibility space of temporal experiences and endorsing the Succession Requirement for agents. The Succession Requirement holds that the basic structure of temporal experience must be successive for agentive subjects, at least in worlds that are law-like in the same way as ours. I aim to establish the Succession Requirement by showing non-successively experiencing agents are not possible for three main reasons, namely that they (1) fail to stand in the right sort of causal relationship to the outcomes of their actions, (2) exhibit the wrong sort of epistemic status for agency, and (3) lack the requisite agentive mental attitude of intentionality. I conclude that agency is incompatible with non-successive experience and therefore we should view the successive temporal structure of experience as a necessary condition for agency. I also suggest that the Succession Requirement may actually extend beyond my main focus on agency, offering preliminary considerations in favor of seeing successive experience as a precondition for selfhood as well. The consequences of the Succession Requirement are wide-ranging, and I discuss various implications for our understanding of agency, the self, time consciousness, and theology, among other things.

Syntax-guided Hierarchical Attention Network for Video Captioning

2021 ◽  
pp. 1-1
Author(s):  
Jincan Deng ◽  
Liang Li ◽  
Beichen Zhang ◽  
Shuhui Wang ◽  
Zhengjun Zha ◽  
...  
Keyword(s):  
Attention Network ◽  
Video Captioning

scholarly journals High-frequency burst spiking in layer 5 thick-tufted pyramids of rat primary somatosensory cortex encodes exploratory touch

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Christiaan P. J. de Kock ◽  
Jean Pie ◽  
Anton W. Pieneman ◽  
Rebecca A. Mease ◽  
Arco Bast ◽  
...  
Keyword(s):  
Somatosensory Cortex ◽  
Information Content ◽  
High Frequency ◽  
Temporal Structure ◽  
Cell Types ◽  
Primary Somatosensory Cortex ◽  
Excitatory Cell ◽  
Cortical Microcircuit ◽  
Subcortical Regions ◽  
Frequency Burst

AbstractDiversity of cell-types that collectively shape the cortical microcircuit ensures the necessary computational richness to orchestrate a wide variety of behaviors. The information content embedded in spiking activity of identified cell-types remain unclear to a large extent. Here, we recorded spike responses upon whisker touch of anatomically identified excitatory cell-types in primary somatosensory cortex in naive, untrained rats. We find major differences across layers and cell-types. The temporal structure of spontaneous spiking contains high-frequency bursts (≥100 Hz) in all morphological cell-types but a significant increase upon whisker touch is restricted to layer L5 thick-tufted pyramids (L5tts) and thus provides a distinct neurophysiological signature. We find that whisker touch can also be decoded from L5tt bursting, but not from other cell-types. We observed high-frequency bursts in L5tts projecting to different subcortical regions, including thalamus, midbrain and brainstem. We conclude that bursts in L5tts allow accurate coding and decoding of exploratory whisker touch.

scholarly journals Gender Differences in Neuromuscular, Haematological and Urinary Responses during Padel Matches

2021 ◽  
Vol 18 (11) ◽  
pp. 5864
Author(s):  
Francisco Pradas ◽  
Alejandro García-Giménez ◽  
Víctor Toro-Román ◽  
Nicolae Ochiana ◽  
Carlos Castellar
Keyword(s):  
Gender Differences ◽  
Red Blood Cells ◽  
Grip Strength ◽  
Blood Cells ◽  
Temporal Structure ◽  
Hand Grip Strength ◽  
Squat Jump ◽  
Hand Grip ◽  
Before And After ◽  
High Level

Research on the acute physiological response to a padel match is limited. The present study aimed to: (a) evaluate neuromuscular, urinary, and hematological responses after simulated padel competition (SC) and (b) analyze possible gender differences. In this study, 28 high-level padel players participated (men = 13, age = 26.83 ± 6.57 years; women = 15, age = 30.07 ± 4.36 years). The following parameters were analyzed before and after SC: neuromuscular (hand grip strength, squat jump (SJ), countermovement jump (CMJ), and Abalakov jump (ABK)), hematological (red blood cells, hemoglobin, and hematocrit), and urinary (pH, specific gravity, microalbuminuria, and red blood cells). Significant gender differences were found in neuromuscular and hematological responses, with men obtaining higher values (p < 0.05). For the SC influence, changes were noted in ABK and microalbuminuria (p < 0.05). The percentages of change in hand grip strength, SJ (height and watts), CMJ (height), and ABK (height) were higher for men than women (p < 0.05). SC negatively influenced the neuromuscular parameters to a greater extent in women. Our results could be related to gender differences in game actions, the temporal structure, and anthropometric and physiological characteristics. Game dynamics and a different organic response between male and female padel playing were confirmed.

Sign in / Sign up

Export Citation Format

Share Document