325 citations · 720 across the 24 of their papers we have counts for
24 papers
Thinking with Anchors: Grounded and Efficient Document Reasoning
Sichen Zhu, Yuchen Zhu, Wenzhuo Xu +13
Existing document understanding benchmarks have largely focused on locating page elements, yet real-world document intelligence requires models to reason jointly about region seman…
MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic Video Segmentation
Najmeh Sadoughi, Xinyu Li, Avijit Vajpayee +5
Previous research has studied the task of segmenting cinematic videos into scenes and into narrative acts. However, these studies have overlooked the essential task of multimodal a…
Large Scale Real-World Multi-Person Tracking
Bing Shuai, Alessandro Bergamo, Uta Buechler +3
This paper presents a new large scale multi-person tracking dataset -- \texttt{PersonPath22}, which is over an order of magnitude larger than currently available high quality multi…
An In-depth Study of Stochastic Backpropagation
Jun Fang, Mingze Xu, Hao Chen +3
In this paper, we provide an in-depth study of Stochastic Backpropagation (SBP) when training deep neural networks for standard image classification and object detection tasks. Dur…
Transfer of Representations to Video Label Propagation: Implementation Factors Matter
Daniel McKee, Zitong Zhan, Bing Shuai +3
This work studies feature representations for dense label propagation in video, with a focus on recently proposed methods that learn video correspondence using self-supervised sign…
Multi-Object Tracking with Hallucinated and Unlabeled Videos
Daniel McKee, Bing Shuai, Andrew Berneshawi +4
In this paper, we explore learning end-to-end deep neural trackers without tracking annotations. This is important as large-scale training data is essential for training deep neura…
SiamMOT: Siamese Multi-Object Tracking
Bing Shuai, Andrew Berneshawi, Xinyu Li +2
In this paper, we focus on improving online multi-object tracking (MOT). In particular, we introduce a region-based Siamese Multi-Object Tracking network, which we name SiamMOT. Si…
VidTr: Video Transformer Without Convolutions
Yanyi Zhang, Xinyu Li, Chunhui Liu +6
We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal infor…
NUTA: Non-uniform Temporal Aggregation for Action Recognition
Xinyu Li, Chunhui Liu, Bing Shuai +3
In the world of action recognition research, one primary focus has been on how to construct and train networks to model the spatial-temporal volume of an input video. These methods…
Directional Temporal Modeling for Action Recognition
Xinyu Li, Bing Shuai, Joseph Tighe
Many current activity recognition models use 3D convolutional neural networks (e.g. I3D, I3D-NL) to generate local spatial-temporal features. However, such features do not encode c…
Multi-Object Tracking with Siamese Track-RCNN
Bing Shuai, Andrew G. Berneshawi, Davide Modolo +1
Multi-object tracking systems often consist of a combination of a detector, a short term linker, a re-identification feature extractor and a solver that takes the output from these…
Understanding the impact of mistakes on background regions in crowd counting
Davide Modolo, Bing Shuai, Rahul Rama Varior +1
Every crowd counting researcher has likely observed their model output wrong positive predictions on image regions not containing any person. But how often do these mistakes happen…
Semantic Correlation Promoted Shape-Variant Context for Segmentation
Henghui Ding, Xudong Jiang, Bing Shuai +2
Context is essential for semantic segmentation. Due to the diverse shapes of objects and their complex layout in various scene images, the spatial scales and shapes of contexts for…
Multi-Scale Attention Network for Crowd Counting
Rahul Rama Varior, Bing Shuai, Joseph Tighe +1
In crowd counting datasets, people appear at different scales, depending on their distance from the camera. To address this issue, we propose a novel multi-branch scale-aware atten…
Improving Fast Segmentation With Teacher-student Learning
Jiafeng Xie, Bing Shuai, Jian-Fang Hu +2
Recently, segmentation neural networks have been significantly improved by demonstrating very promising accuracies on public benchmarks. However, these models are very heavy and ge…
Multimodal Recurrent Neural Networks with Information Transfer Layers for Indoor Scene Labeling
Abrar H. Abdulnabi, Bing Shuai, Zhen Zuo +2
This paper proposes a new method called Multimodal RNNs for RGB-D scene semantic segmentation. It is optimized to classify image pixels given two input sources: RGB color channels…
Improving Fully Convolution Network for Semantic Segmentation
Bing Shuai, Ting Liu, Gang Wang
Fully Convolution Networks (FCN) have achieved great success in dense prediction tasks including semantic segmentation. In this paper, we start from discussing FCN by understanding…
A Siamese Long Short-Term Memory Architecture for Human Re-Identification
Rahul Rama Varior, Bing Shuai, Jiwen Lu +2
Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance. In the existing works concen…
Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association
Bing Wang, Li Wang, Bing Shuai +4
In this paper, we study the challenging problem of multi-object tracking in a complex scene captured by a single camera. Different from the existing tracklet association-based trac…
Scene Parsing with Integration of Parametric and Non-parametric Models
Bing Shuai, Zhen Zuo, Gang Wang +1
We adopt Convolutional Neural Networks (CNNs) to be our parametric model to learn discriminative features and classifiers for local patch classification. Based on the occurrence fr…
Recent Advances in Convolutional Neural Networks
Jiuxiang Gu, Zhenhua Wang, Jason Kuen +9
In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing. Amon…
Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks
Zhen Zuo, Bing Shuai, Gang Wang +3
Existing deep convolutional neural networks (CNNs) have shown their great success on image classification. CNNs mainly consist of convolutional and pooling layers, both of which ar…
DAG-Recurrent Neural Networks For Scene Labeling
Bing Shuai, Zhen Zuo, Gang Wang +1
In image labeling, local representations for image units are usually generated from their surrounding image patches, thus long-range contextual information is not effectively encod…
Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification
Zhen Zuo, Gang Wang, Bing Shuai +2
In order to encode the class correlation and class specific information in image representation, we propose a new local feature learning approach named Deep Discriminative and Shar…