In computer vision, tracking humans across camera views
remains challenging, especially for complex scenarios with frequent
occlusions, significant lighting changes and other difficulties. Under
such conditions, most existing appearance and geometric cues are
not reliable enough to distinguish humans across camera views. To
address these challenges, this paper presents a stochastic attribute
grammar model for leveraging complementary and discriminative human
attributes for enhancing cross-view tracking. The key idea of our
method is to introduce a hierarchical representation, parse graph, to
describe a subject and its movement trajectory in both space and time
domains. This results in a hierarchical compositional representation,
comprising trajectory entities of varying level, including human boxes,
3D human boxes, tracklets and trajectories. We use a set of grammar
rules to decompose a graph node (e.g. tracklet) into a set of children
nodes (e.g. 3D human boxes), and augment each node with a set
of attributes, including geometry (e.g., moving speed, direction), accessories
(e.g., bags), and/or activities (e.g., walking, running). These
attributes serve as valuable cues, in addition to appearance features
(e.g., colors), in determining the associations of human detection boxes
across cameras. In particular, the attributes of a parent node are inherited
by its children nodes, resulting in consistency constraints over
the feasible parse graph. Thus, we cast cross-view human tracking as
finding the most discriminative parse graph for each subject in videos.
We develop a learning method to train this attribute grammar model from
weakly supervised training data. To infer the optimal parse graph and its
attributes, we develop an alternative parsing method that employs both
top-down and bottom-up computations to search the optimal solution.
We also explicitly reason the occlusion status of each entity in order
to deal with significant changes of camera viewpoints. We evaluate the
proposed method over public video benchmarks and demonstrate with
extensive experiments that our method clearly outperforms state-of-theart
tracking methods.
more »
« less
Recognizing Part Attributes With Insufficient Data
Recognizing the attributes of objects and their parts is central to many computer vision applications. Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains less applicable since the training data for part attributes recognition is usually scarce especially for internet-scale applications. Furthermore, most existing part attribute recognition methods rely on the part annotations which are more expensive to obtain. In order to solve the data insufficiency problem and get rid of dependence on the part annotation, we introduce a novel Concept Sharing Network (CSN) for part attribute recognition. A great advantage of CSN is its capability of recognizing the part attribute (a combination of part location and appearance pattern) that has insufficient or zero training data, by learning the part location and appearance pattern respectively from the training data that usually mix them in a single label. Extensive experiments on CUB, Celeb A, and a newly proposed human attribute dataset demonstrate the effectiveness of CSN and its advantages over other methods, especially for the attributes with few training samples. Further experiments show that CSN can also perform zero-shot part attribute recognition.
more »
« less
- Award ID(s):
- 1815561
- NSF-PAR ID:
- 10161300
- Date Published:
- Journal Name:
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Page Range / eLocation ID:
- 350 to 360
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Recent studies have revealed that sensitive and private attributes could be decoded from sEMG signals, which incurs significant privacy threats to the users of sEMG applications. Most researches so far focus on improving the accuracy and reliability of sEMG models, but much less attention has been paid to their privacy. To fill this gap, this paper implemented and evaluated a framework to optimize the sEMG-based data-sharing mechanism. Our primary goal is to remove sensitive attributes in the sEMG features before sharing them with primary tasks while maintaining the data utility. We disentangled the identity-invariant task-relevant representations from original sEMG features. We shared it with the downstream pattern recognition tasks to reduce the chance of sensitive attributes being inferred by potential attackers. The proposed method was evaluated on data from twenty subjects, with training and testing data acquired 3-25 days apart. Experimental results show that the disentangled representations significantly lower the success rate of identity inference attacks compared to the original feature and its sparse representations generated by the state-of-the-art feature projection methods. Furthermore, the utility of the disentangled representation is also evaluated in hand gesture recognition tasks, showing superior performance over other methods. This work shows that disentangled representations of sEMG signals are a promising solution for privacy-reserving applications.more » « less
-
null (Ed.)Abstract—The emergence of remote sensing technologies cou- pled with local monitoring workstations enables us the un- precedented ability to monitor the environment in large scale. Information mining from multi-channel geo-spatiotemporal data however poses great challenges to many computational sustainability applications. Most existing approaches adopt various dimensionality reduction techniques without fully taking advantage of the spatiotemporal nature of the data. In addition, the lack of labeled training data raises another challenge for modeling such data. In this work, we propose a novel semi-supervised attention-based deep representation model that learns context-aware spatiotemporal representations for prediction tasks. A combination of convolutional neural networks with a hybrid attention mechanism is adopted to extract spatial and temporal variations in the geo-spatiotemporal data. Recognizing the importance of capturing more complete temporal dependencies, we propose the hybrid attention mechanism which integrates a learnable global query into the classic self-attention mechanism. To overcome the data scarcity issue, sampled spatial and temporal context that naturally reside in the largely-available unlabeled geo-spatiotemporal data are exploited to aid meaningful representation learning. We conduct experiments on a large-scale real-world crop yield prediction task. The results show that our methods significantly outperforms existing state-of-the-art yield prediction methods, especially under the stress of training data scarcity.more » « less
-
Context: Addressing women's under-representation in the soft-ware industry, a widely recognized concern, requires attracting as well as retaining more women. Hearing from women practitioners, particularly those positioned in multi-cultural settings, about their challenges and and adopting their lived experienced solutions can support the design of programs to resolve the under-representation issue. Goal: We investigated the challenges women face in global software development teams, particularly what motivates women to leave their company; how those challenges might break down according to demographics; and strategies to mitigate the identified challenges. Method: To achieve this goal, we conducted an ex-ploratory case study in Ericsson, a global technology company. We surveyed 94 women and employed mixed-methods to analyze the data. Results: Our findings reveal that women face socio-cultural challenges, including work-life balance issues, benevolent and hos-tile sexism, lack of recognition and peer parity, impostor syndrome, glass ceiling bias effects, the prove-it-again phenomenon, and the maternal wall. The participants of our research provided different suggestions to address/mitigate the reported challenges, including sabbatical policies, flexibility of location and time, parenthood support, soft skills training for managers, equality of payment and opportunities between genders, mentoring and role models to sup-port career growth, directives to hire more women, inclusive groups and events, women's empowerment, and recognition for women's success. The framework of challenges and suggestions can inspire further initiatives both in academia and industry to onboard and retain women. Women represent less than 24% of employees in software development industry and experience various types of prejudice and bias. Even in companies that care about Diversity & Inclusion, “untying the mooring ropes” of socio-cultural problems is hard. Hearing from women, especially those working in a multi-cultural organization, about their challenges and adopting their suggestions can be vital to design programs and resolve the under-representation issue. In this work we work closely with a large software development or-ganization which invests and believes in diversity and inclusion. We listened to women and the challenges they face in global soft-ware development teams of this company and what these women suggest reduce the problems and increase retention. Our research showed that women face work-life balance issues and encounter invisible barriers that prevent them from rising to top positions. They also suffer micro-aggression and sexism, need to show com-petence constantly, be supervised in essential tasks, and receive less work after becoming mothers. Moreover, women miss having more female colleagues, lack self-confidence and recognition. The women from the company suggested sabbatical policies, the flexibil-ity of location and time, parenthood support, soft skills training for managers, equality of opportunities, role models to support career growth, directives to hire more women, support groups, and more interaction between women, inclusive groups and events, women's empowerment by publishing their success stories in media and recognizing their achievements. Our results had been shared with the company Human Resources department and management and they considered the diagnosis helpful and will work on actions to mitigate the challenges that women still perceive.more » « less
-
more » « less
Abstract After graphene was first exfoliated in 2004, research worldwide has focused on discovering and exploiting its distinctive electronic, mechanical, and structural properties. Application of the efficacious methodology used to fabricate graphene, mechanical exfoliation followed by optical microscopy inspection, to other analogous bulk materials has resulted in many more two-dimensional (2D) atomic crystals. Despite their fascinating physical properties, manual identification of 2D atomic crystals has the clear drawback of low-throughput and hence is impractical for any scale-up applications of 2D samples. To combat this, recent integration of high-performance machine-learning techniques, usually deep learning algorithms because of their impressive object recognition abilities, with optical microscopy have been used to accelerate and automate this traditional flake identification process. However, deep learning methods require immense datasets and rely on uninterpretable and complicated algorithms for predictions. Conversely, tree-based machine-learning algorithms represent highly transparent and accessible models. We investigate these tree-based algorithms, with features that mimic color contrast, for automating the manual inspection process of exfoliated 2D materials (e.g., MoSe2). We examine their performance in comparison to ResNet, a famous Convolutional Neural Network (CNN), in terms of accuracy and the physical nature of their decision-making process. We find that the decision trees, gradient boosted decision trees, and random forests utilize physical aspects of the images to successfully identify 2D atomic crystals without suffering from extreme overfitting and high training dataset demands. We also employ a post-hoc study that identifies the sub-regions CNNs rely on for classification and find that they regularly utilize physically insignificant image attributes when correctly identifying thin materials.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICCV.2019.00044
