481 citations · 1.3k across the 30 of their papers we have counts for
30 papers
Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition
Dongqi Cai, Yangyuxuan Kang, Anbang Yao +1
This paper presents Ske2Grid, a new representation learning framework for improved skeleton-based action recognition. In Ske2Grid, we define a regular convolution operation upon a…
ECT: Fine-grained Edge Detection with Learned Cause Tokens
Shaocong Xu, Xiaoxue Chen, Yuhang Zheng +4
In this study, we tackle the challenging fine-grained edge detection task, which refers to predicting specific edges caused by reflectance, illumination, normal, and depth changes,…
CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large Input
Senmao Tian, Ming Lu, Jiaming Liu +3
With the development of high-definition display devices, the practical scenario of Super-Resolution (SR) usually needs to super-resolve large input like 2K to higher resolution (4K…
From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds
Huan-ang Gao, Beiwen Tian, Pengfei Li +5
Room layout estimation is a long-existing robotic vision task that benefits both environment sensing and motion planning. However, layout estimation using point clouds (PCs) still…
Efficient Meta-Tuning for Content-aware Neural Video Delivery
Xiaoqi Li, Jiaming Liu, Shizun Wang +6
Recently, Deep Neural Networks (DNNs) are utilized to reduce the bandwidth and improve the quality of Internet video delivery. Existing methods train corresponding content-aware su…
Transferable End-to-end Room Layout Estimation via Implicit Encoding
Hao Zhao, Rene Ranftl, Yurong Chen +1
We study the problem of estimating room layouts from a single panorama image. Most former works have two stages: feature extraction and parametric model fitting. Here we propose an…
Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation
Jiaming Liu, Ming Lu, Kaixin Chen +7
Internet video delivery has undergone a tremendous explosion of growth over the past few years. However, the quality of video delivery system greatly depends on the Internet bandwi…
AccSS3D: Accelerator for Spatially Sparse 3D DNNs
Om Ji Omer, Prashant Laddha, Gurpreet S Kalsi +6
Semantic understanding and completion of real world scenes is a foundational primitive of 3D Visual perception widely used in high-level applications such as robotics, medical imag…
LID 2020: The Learning from Imperfect Data Challenge Results
Yunchao Wei, Shuai Zheng, Ming-Ming Cheng +32
Learning from imperfect data becomes an issue in many industrial applications after the research community has made profound progress in supervised learning from perfectly annotate…
CASNet: Common Attribute Support Network for image instance and panoptic segmentation
Xiaolong Liu, Yuqing Hou, Anbang Yao +2
Instance segmentation and panoptic segmentation is being paid more and more attention in recent years. In comparison with bounding box based object detection and semantic segmentat…
On Connections between Regularizations for Improving DNN Robustness
Yiwen Guo, Long Chen, Yurong Chen +1
This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view. Specifically,…
Learning Two-View Correspondences and Geometry Using Order-Aware Network
Jiahui Zhang, Dawei Sun, Zixin Luo +6
Establishing correspondences between two images requires both local and global spatial context. Given putative correspondences of feature points in two views, in this paper, we pro…
Efficient Semantic Scene Completion Network with Spatial Group Convolution
Jiahui Zhang, Hao Zhao, Anbang Yao +3
We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks. SGC is orthogonal to group convolution, which works on spatial dimension…
A Closed-form Solution to Universal Style Transfer
Ming Lu, Hao Zhao, Anbang Yao +3
Universal style transfer tries to explicitly minimize the losses in feature space, thus it does not require training on any pre-defined styles. It usually uses different layers of…
Deep Likelihood Network for Image Restoration with Multiple Degradation Levels
Yiwen Guo, Ming Lu, Wangmeng Zuo +2
Convolutional neural networks have been proven effective in a variety of image restoration tasks. Most state-of-the-art solutions, however, are trained using images with a single p…
Sparse DNNs with Improved Adversarial Robustness
Yiwen Guo, Chao Zhang, Changshui Zhang +1
Deep neural networks (DNNs) are computationally/memory-intensive and vulnerable to adversarial attacks, making them prohibitive in some real-world applications. By converting dense…
Object Detection from Scratch with Deep Supervision
Zhiqiang Shen, Zhuang Liu, Jianguo Li +3
We propose Deeply Supervised Object Detectors (DSOD), an object detection framework that can be trained from scratch. Recent advances in object detection heavily depend on the off-…
Network Decoupling: From Regular to Depthwise Separable Convolutions
Jianbo Guo, Yuxi Li, Weiyao Lin +2
Depthwise separable convolution has shown great efficiency in network design, but requires time-consuming training procedure with full training-set available. This paper first anal…
Learning Visual Knowledge Memory Networks for Visual Question Answering
Zhou Su, Chen Zhu, Yinpeng Dong +3
Visual question answering (VQA) requires joint comprehension of images and natural language questions, where many questions can't be directly or clearly answered from visual conten…
Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization
Yinpeng Dong, Renkun Ni, Jianguo Li +3
Low-bit deep neural networks (DNNs) become critical for embedded applications due to their low storage requirement and computing efficiency. However, they suffer much from the non-…
DSOD: Learning Deeply Supervised Object Detectors from Scratch
Zhiqiang Shen, Zhuang Liu, Jianguo Li +3
We present Deeply Supervised Object Detector (DSOD), a framework that can learn object detectors from scratch. State-of-the-art object objectors rely heavily on the off-the-shelf n…
RON: Reverse Connection with Objectness Prior Networks for Object Detection
Tao Kong, Fuchun Sun, Anbang Yao +3
We present RON, an efficient and effective framework for generic object detection. Our motivation is to smartly associate the best of the region-based (e.g., Faster R-CNN) and regi…
Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation
Hao Zhao, Ming Lu, Anbang Yao +3
In this paper, we propose an alternative method to estimate room layouts of cluttered indoor scenes. This method enjoys the benefits of two novel techniques. The first one is seman…
Network Sketching: Exploiting Binary Structure in Deep CNNs
Yiwen Guo, Anbang Yao, Hao Zhao +1
Convolutional neural networks (CNNs) with deep architectures have substantially advanced the state-of-the-art in computer vision tasks. However, deep networks are typically resourc…