scholarly journals A magnocellular contribution to conscious perception via temporal object segmentation.

2014 ◽  
Vol 40 (3) ◽  
pp. 948-959 ◽  
Author(s):  
Stephanie C. Goodhew ◽  
Hannah L. Boal ◽  
Mark Edwards
Keyword(s):  
Object Segmentation ◽  
Conscious Perception ◽  
Temporal Object

scholarly journals Motion-Attentive Transition for Zero-Shot Video Object Segmentation

2020 ◽  
Vol 34 (07) ◽  
pp. 13066-13073 ◽  
Author(s):  
Tianfei Zhou ◽  
Shunzhou Wang ◽  
Yi Zhou ◽  
Yazhou Yao ◽  
Jianwu Li ◽  
...  
Keyword(s):  
Object Representation ◽  
Object Segmentation ◽  
Object Motion ◽  
Video Object Segmentation ◽  
Video Object ◽  
The Arts ◽  
Temporal Object ◽  
Multi Level ◽  
Transition Network ◽  
Spatio Temporal

In this paper, we present a novel Motion-Attentive Transition Network (MATNet) for zero-shot video object segmentation, which provides a new way of leveraging motion information to reinforce spatio-temporal object representation. An asymmetric attention block, called Motion-Attentive Transition (MAT), is designed within a two-stream encoder, which transforms appearance features into motion-attentive representations at each convolutional stage. In this way, the encoder becomes deeply interleaved, allowing for closely hierarchical interactions between object motion and appearance. This is superior to the typical two-stream architecture, which treats motion and appearance separately in each stream and often suffers from overfitting to appearance information. Additionally, a bridge network is proposed to obtain a compact, discriminative and scale-sensitive representation for multi-level encoder features, which is further fed into a decoder to achieve segmentation results. Extensive experiments on three challenging public benchmarks (i.e., DAVIS-16, FBMS and Youtube-Objects) show that our model achieves compelling performance against the state-of-the-arts. Code is available at: https://github.com/tfzhou/MATNet.

scholarly journals A magnocellular contribution to conscious object perception via temporal object segmentation

2014 ◽  
Vol 14 (10) ◽  
pp. 1334-1334
Author(s):  
S. C. Goodhew ◽  
H. L. Boal ◽  
M. Edwards
Keyword(s):  
Object Segmentation ◽  
Object Perception ◽  
Temporal Object

scholarly journals Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings

2020 ◽  
Author(s):  
Mennatullah Siam ◽  
Naren Doraiswamy ◽  
Boris N. Oreshkin ◽  
Hengshuai Yao ◽  
Martin Jagersand
Keyword(s):  
Semantic Processing ◽  
Object Segmentation ◽  
State Of The Art ◽  
Video Data ◽  
Modal Interaction ◽  
Shot Segmentation ◽  
Bounding Box ◽  
Segmentation Methods ◽  
Temporal Object ◽  
Weakly Supervised

Significant progress has been made recently in developing few-shot object segmentation methods. Learning is shown to be successful in few-shot segmentation settings, using pixel-level, scribbles and bounding box supervision. This paper takes another approach, i.e., only requiring image-level label for few-shot object segmentation. We propose a novel multi-modal interaction module for few-shot object segmentation that utilizes a co-attention mechanism using both visual and word embedding. Our model using image-level labels achieves 4.8% improvement over previously proposed image-level few-shot object segmentation. It also outperforms state-of-the-art methods that use weak bounding box supervision on PASCAL-5^i. Our results show that few-shot segmentation benefits from utilizing word embeddings, and that we are able to perform few-shot segmentation using stacked joint visual semantic processing with weak image-level labels. We further propose a novel setup, Temporal Object Segmentation for Few-shot Learning (TOSFL) for videos. TOSFL can be used on a variety of public video data such as Youtube-VOS, as demonstrated in both instance-level and category-level TOSFL experiments.

How Socially Relevant Visual Characteristics of Avatars Influence Impression Formation

2010 ◽  
Vol 22 (1) ◽  
pp. 37-43 ◽  
Author(s):  
David Weibel ◽  
Daniel Stricker ◽  
Bartholomäus Wissmath ◽  
Fred W. Mast
Keyword(s):  
Impression Formation ◽  
Pupil Size ◽  
Conscious Perception ◽  
Viewing Angle ◽  
Frontal View ◽  
Computer Mediated ◽  
First Impression ◽  
Visual Characteristics ◽  
Socially Relevant ◽  
Blink Frequency

Like in the real world, the first impression a person leaves in a computer-mediated environment depends on his or her online appearance. The present study manipulates an avatar’s pupil size, eyeblink frequency, and the viewing angle to investigate whether nonverbal visual characteristics are responsible for the impression made. We assessed how participants (N = 56) evaluate these avatars in terms of different attributes. The findings show that avatars with large pupils and slow eye blink frequency are perceived as more sociable and more attractive. Compared to avatars seen in full frontal view or from above, avatars seen from below were rated as most sociable, self-confident, and attractive. Moreover, avatars’ pupil size and eyeblink frequency escape the viewer’s conscious perception but still influence how people evaluate them. The findings have wide-ranging applied implications for avatar design.

IMPROVED OBJECT SEGMENTATION USING MULTI SCALE SALIENCY APPROACH

2018 ◽  
Vol 6 (4) ◽  
pp. 161-167
Author(s):  
S. Thilagamani ◽  
◽  
◽  
V. Manochitra
Keyword(s):  
Object Segmentation ◽  
Multi Scale
Sign in / Sign up

Export Citation Format

Share Document