arXiv subjects

Jingwen Wang

Publications and source records attributed to Jingwen Wang.

40 records · Page 3Linked to original sources

arXiv2019

Generating an Overview Report over Many Documents

How to efficiently generate an accurate, well-structured overview report (ORPT) over thousands of related documents is challenging. A well-structured ORPT consists of sections of multiple levels (e.g., sections and subsections). None of the existing multi-document summarization (MDS) algorithms is directed toward this task. To overcome this obstacle, we present NDORGS (Numerous Documents' Overview Report Generation Scheme) that integrates text filtering, keyword scoring, single-document summarization (SDS), topic modeling, MDS, and title generation to generate a coherent, well-structured ORPT. We then devise a multi-criteria evaluation method using techniques of text mining and multi-attribute decision making on a combination of human judgments, running time, information coverage, and topic diversity. We evaluate ORPTs generated by NDORGS on two large corpora of documents, where one is classified and the other unclassified. We show that, using Saaty's pairwise comparison 9-point scale and under TOPSIS, the ORPTs generated on SDS's with the length of 20% of the original documents are the best overall on both datasets.

cs.CL↗

arXiv2018

Non-local NetVLAD Encoding for Video Classification

This paper describes our solution for the 2$^\text{nd}$ YouTube-8M video understanding challenge organized by Google AI. Unlike the video recognition benchmarks, such as Kinetics and Moments, the YouTube-8M challenge provides pre-extracted visual and audio features instead of raw videos. In this challenge, the submitted model is restricted to 1GB, which encourages participants focus on constructing one powerful single model rather than incorporating of the results from a bunch of models. Our system fuses six different sub-models into one single computational graph, which are categorized into three families. More specifically, the most effective family is the model with non-local operations following the NetVLAD encoding. The other two family models are Soft-BoF and GRU, respectively. In order to further boost single models performance, the model parameters of different checkpoints are averaged. Experimental results demonstrate that our proposed system can effectively perform the video classification task, achieving 0.88763 on the public test set and 0.88704 on the private set in terms of GAP@20, respectively. We finally ranked at the fourth place in the YouTube-8M video understanding challenge.

cs.CV↗

arXiv2018

A Deep Learning Approach to the Citywide Traffic Accident Risk Prediction

With the rapid development of urbanization, the boom of vehicle numbers has resulted in serious traffic accidents, which led to casualties and huge economic losses. The ability to predict the risk of traffic accident is important in the prevention of the occurrence of accidents and to reduce the damages caused by accidents in a proactive way. However, traffic accident risk prediction with high spatiotemporal resolution is difficult, mainly due to the complex traffic environment, human behavior, and lack of real-time traffic-related data. In this study, we collected big traffic accident data. By analyzing the spatial and temporal patterns of traffic accident frequency, we presented the spatiotemporal correlation of traffic accidents. Based on the patterns we found in analysis, we proposed a high accurate deep learning model based on recurrent neural network toward the prediction of traffic accident risk. The predictive accident risk can be potential applied to the traffic accident warning system. The proposed method can be integrated into an intelligent traffic control system toward a more reasonable traffic prediction and command organization.

cs.CY↗

arXiv2018

Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning

Dense video captioning is a newly emerging task that aims at both localizing and describing all events in a video. We identify and tackle two challenges on this task, namely, (1) how to utilize both past and future contexts for accurate event proposal predictions, and (2) how to construct informative input to the decoder for generating natural event descriptions. First, previous works predominantly generate temporal event proposals in the forward direction, which neglects future video context. We propose a bidirectional proposal method that effectively exploits both past and future contexts to make proposal predictions. Second, different events ending at (nearly) the same time are indistinguishable in the previous works, resulting in the same captions. We solve this problem by representing each event with an attentive fusion of hidden states from the proposal module and video contents (e.g., C3D features). We further propose a novel context gating mechanism to balance the contributions from the current event and its surrounding contexts dynamically. We empirically show that our attentively fused event representation is superior to the proposal hidden states or video contents alone. By coupling proposal and captioning modules into one unified framework, our model outperforms the state-of-the-arts on the ActivityNet Captions dataset with a relative gain of over 100% (Meteor score increases from 4.82 to 9.65).

cs.CV↗