Combining multiple sources of knowledge in deep CNNs for action recognition

Park, Eunbyung; Han, Xufeng; Berg, Tamara L.; Berg, Alexander C.

doi:10.1109/wacv.2016.7477589

Cited by 144 publications

(114 citation statements)

References 14 publications

Supporting

Mentioning

111

Contrasting

Order By: Relevance

“…In addition to content and network signals, we incorporate other linguistic cues into our networks. For this we rely on the "late fusion" approach that has been shown to be effective in vision tasks (Karpathy et al, 2014;Park et al, 2016). "Fusion" allows for a network to learn a combined representation of multiple input streams.…”

Section: Datamentioning

confidence: 99%

Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter

Volkova

Shaffer

Jang

et al. 2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 2: Short Papers)

273

172

View full text Add to dashboard Cite

Pew research polls report 62 percent of U.S. adults get news on social media (Gottfried and Shearer, 2016). In a December poll, 64 percent of U.S. adults said that "made-up news" has caused a "great deal of confusion" about the facts of current events (Barthel et al., 2016). Fabricated stories in social media, ranging from deliberate propaganda to hoaxes and satire, contributes to this confusion in addition to having serious effects on global stability.In this work we build predictive models to classify 130 thousand news posts as suspicious or verified, and predict four subtypes of suspicious news -satire, hoaxes, clickbait and propaganda. We show that neural network models trained on tweet content and social network interactions outperform lexical models. Unlike previous work on deception detection, we find that adding syntax and grammar features to our models does not improve performance. Incorporating linguistic features improves classification results, however, social interaction features are most informative for finer-grained separation between four types of suspicious news posts.

show abstract

Section: Datamentioning

confidence: 99%

Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter

Volkova

Shaffer

Jang

et al. 2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 2: Short Papers)

273

172

View full text Add to dashboard Cite

show abstract

“…This will add a geometrical "shape" information to the RGB reflectance values. There are several ways of combining these inputs such as presented in (Park et al, 2016). A first method would consist in merging the inputs and training the network with four channels.…”

Section: Resultsmentioning

confidence: 99%

Manhole Cover Localization in Aerial Images With a Deep Learning Approach

Commandré

En-Nejjary

Pibre

et al. 2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Urban growth is an ongoing trend and one of its direct consequences is the development of buried utility networks. Locating these networks is becoming a challenging task. While the labeling of large objects in aerial images is extensively studied in Geosciences, the localization of small objects (smaller than a building) is in counter part less studied and very challenging due to the variance of object colors, cluttered neighborhood, non-uniform background, shadows and aspect ratios. In this paper, we put forward a method for the automatic detection and localization of manhole covers in Very High Resolution (VHR) aerial and remotely sensed images using a Convolutional Neural Network (CNN). Compared to other detection/localization methods for small objects, the proposed approach is more comprehensive as the entire image is processed without prior segmentation. The first experiments using the Prades-Le-Lez and Gigean datasets show that our method is indeed effective as more than 49% of the ground truth database is detected with a precision of 75%. New improvement possibilities are being explored such as using information on the shape of the detected objects and increasing the types of objects to be detected, thus enabling the extraction of more object specific features.

show abstract

“…For image processing, the Scale-Invariant Feature Transform (SIFT) [11] is a well-known image feature matching algorithm. Another method based on Deep Learning [12] can be used for object recognition, and has many other applications such as human action analysis [13]. Moreover, Deep Learning can be applied to some unlearned objects.…”

Section: Detection Of Neighboring Objects and Interobjectmentioning

confidence: 99%

Visual support system for remote control by adaptive ROI selection of monitoring robot

2018

View full text Add to dashboard Cite

A visual assistance system has become attractive as a technique to improve the efficiency and stability of remote control. While an operator controls a working robot, another autonomous monitoring robot evaluates a suitable viewpoint to observe the work site, and dynamically moves to the optimal viewpoint for monitoring. Choosing the observation region (ROI: region of interest) is equivalent to deciding the action of the following autonomous monitoring system. Therefore, we focus on ROI detection in our visual support system. We propose an ROI selection method to identify the most suitable observation point and interobject relations. The monitoring robot detects a gestalt of the scene in order to identify the relations between objects. Such an adaptive ROI in real time improves the efficiency of the remote control. The experimental results indicate the effectiveness of the proposed system in terms of execution time and number of errors.

show abstract

Combining multiple sources of knowledge in deep CNNs for action recognition

Cited by 144 publications

References 14 publications

Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter

Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter

Manhole Cover Localization in Aerial Images With a Deep Learning Approach

Visual support system for remote control by adaptive ROI selection of monitoring robot

Contact Info

Product

Resources

About