Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDetecting natural disasters, damage, and incidents in the wild
296
0
0.0
(
0
)
Added by
Ethan Weber
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Responding to natural disasters, such as earthquakes, floods, and wildfires, is a laborious task performed by on-the-ground emergency responders and analysts. Social media has emerged as a low-latency data source to quickly understand disaster situations. While most studies on social media are limited to text, images offer more information for understanding disaster and incident scenes. However, no large-scale image datasets for incident detection exists. In this work, we present the Incidents Dataset, which contains 446,684 images annotated by humans that cover 43 incidents across a variety of scenes. We employ a baseline classification model that mitigates false-positive errors and we perform image filtering experiments on millions of social media images from Flickr and Twitter. Through these experiments, we show how the Incidents Dataset can be used to detect images with incidents in the wild. Code, data, and models are available online at http://incidentsdataset.csail.mit.edu.
rate research
Read More
We investigate a new problem of detecting hands and recognizing their physical contact state in unconstrained conditions. This is a challenging inference task given the need to reason beyond the local appearance of hands. The lack of training annotations indicating which object or parts of an object the hand is in contact with further complicates the task. We propose a novel convolutional network based on Mask-RCNN that can jointly learn to localize hands and predict their physical contact to address this problem. The network uses outputs from another object detector to obtain locations of objects present in the scene. It uses these outputs and hand locations to recognize the hands contact state using two attention mechanisms. The first attention mechanism is based on the hand and a regions affinity, enclosing the hand and the object, and densely pools features from this region to the hand region. The second attention module adaptively selects salient features from this plausible region of contact. To develop and evaluate our methods performance, we introduce a large-scale dataset called ContactHands, containing unconstrained images annotated with hand locations and contact states. The proposed network, including the parameters of attention modules, is end-to-end trainable. This network achieves approximately 7% relative improvement over a baseline network that was built on the vanilla Mask-RCNN architecture and trained for recognizing hand contact states.
We provide, and perform a risk theoretic statistical analysis of, a dataset that is 75 percent larger than the previous best dataset on nuclear incidents and accidents, comparing three measures of severity: INES (International Nuclear Event Scale), radiation released, and damage dollar losses. The annual rate of nuclear accidents, with size above 20 Million US$, per plant, decreased from the 1950s until dropping significantly after Chernobyl (April, 1986). The rate is now roughly stable at 0.002 to 0.003, i.e., around 1 event per year across the current fleet. The distribution of damage values changed after Three Mile Island (TMI; March, 1979), where moderate damages were suppressed but the tail became very heavy, being described by a Pareto distribution with tail index 0.55. Further, there is a runaway disaster regime, associated with the dragon-king phenomenon, amplifying the risk of extreme damage. In fact, the damage of the largest event (Fukushima; March, 2011) is equal to 60 percent of the total damage of all 174 accidents in our database since 1946. In dollar losses we compute a 50% chance that (i) a Fukushima event (or larger) occurs in the next 50 years, (ii) a Chernobyl event (or larger) occurs in the next 27 years and (iii) a TMI event (or larger) occurs in the next 10 years. Finally, we find that the INES scale is inconsistent. To be consistent with damage, the Fukushima disaster would need to have an INES level of 11, rather than the maximum of 7.
Detecting customized moments and highlights from videos given natural language (NL) user queries is an important but under-studied topic. One of the challenges in pursuing this direction is the lack of annotated data. To address this issue, we present the Query-based Video Highlights (QVHighlights) dataset. It consists of over 10,000 YouTube videos, covering a wide range of topics, from everyday activities and travel in lifestyle vlog videos to social and political activities in news videos. Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w.r.t. the query, and (3) five-point scale saliency scores for all query-relevant clips. This comprehensive annotation enables us to develop and evaluate systems that detect relevant moments as well as salient highlights for diverse, flexible user queries. We also present a strong baseline for this task, Moment-DETR, a transformer encoder-decoder model that views moment retrieval as a direct set prediction problem, taking extracted video and query representations as inputs and predicting moment coordinates and saliency scores end-to-end. While our model does not utilize any human prior, we show that it performs competitively when compared to well-engineered architectures. With weakly supervised pretraining using ASR captions, Moment-DETR substantially outperforms previous methods. Lastly, we present several ablations and visualizations of Moment-DETR. Data and code is publicly available at https://github.com/jayleicn/moment_detr
We study collective attention paid towards hurricanes through the lens of $n$-grams on Twitter, a social media platform with global reach. Using hurricane name mentions as a proxy for awareness, we find that the exogenous temporal dynamics are remarkably similar across storms, but that overall collective attention varies widely even among storms causing comparable deaths and damage. We construct `hurricane attention maps and observe that hurricanes causing deaths on (or economic damage to) the continental United States generate substantially more attention in English language tweets than those that do not. We find that a hurricanes Saffir-Simpson wind scale category assignment is strongly associated with the amount of attention it receives. Higher category storms receive higher proportional increases of attention per proportional increases in number of deaths or dollars of damage, than lower category storms. The most damaging and deadly storms of the 2010s, Hurricanes Harvey and Maria, generated the most attention and were remembered the longest, respectively. On average, a category 5 storm receives 4.6 times more attention than a category 1 storm causing the same number of deaths and economic damage.
We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image. The CTPN detects a text line in a sequence of fine-scale text proposals directly in convolutional feature maps. We develop a vertical anchor mechanism that jointly predicts location and text/non-text score of each fixed-width proposal, considerably improving localization accuracy. The sequential proposals are naturally connected by a recurrent neural network, which is seamlessly incorporated into the convolutional network, resulting in an end-to-end trainable model. This allows the CTPN to explore rich context information of image, making it powerful to detect extremely ambiguous text. The CTPN works reliably on multi-scale and multi- language text without further post-processing, departing from previous bottom-up methods requiring multi-step post-processing. It achieves 0.88 and 0.61 F-measure on the ICDAR 2013 and 2015 benchmarks, surpass- ing recent results [8, 35] by a large margin. The CTPN is computationally efficient with 0:14s/image, by using the very deep VGG16 model [27]. Online demo is available at: http://textdet.com/.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
