Dacheng Tao

SIR: Self-supervised Image Rectification via Seeing the Same Scene from Multiple Different Lenses

Deep learning has demonstrated its power in image rectification by lever...
11/30/2020 ∙ by Jinlong Fan, et al. ∙ 0 ∙ share

read it
DUT:Learning Video Stabilization by Simply Watching Unstable Videos

We propose a Deep Unsupervised Trajectory-based stabilization framework ...
11/30/2020 ∙ by Yufei Xu, et al. ∙ 0 ∙ share

read it
Inter-layer Transition in Neural Architecture Search

Differential Neural Architecture Search (NAS) methods represent the netw...
11/30/2020 ∙ by Benteng Ma, et al. ∙ 0 ∙ share

read it
Recent Progress in Appearance-based Action Recognition

Action recognition, which is formulated as a task to identify various hu...
11/25/2020 ∙ by Jack Humphreys, et al. ∙ 3 ∙ share

read it
Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things

In the Internet of Things (IoT) era, billions of sensors and devices col...
11/17/2020 ∙ by Jing Zhang, et al. ∙ 41 ∙ share

read it
Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting

Deep learning is often criticized by two serious issues which rarely exi...
11/12/2020 ∙ by Zeke Xie, et al. ∙ 0 ∙ share

read it
Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model

Home-cage social behaviour analysis of mice is an invaluable tool to ass...
11/04/2020 ∙ by Zheheng Jiang, et al. ∙ 0 ∙ share

read it
Context-Aware Cross-Attention for Non-Autoregressive Translation

Non-autoregressive translation (NAT) significantly accelerates the infer...
11/02/2020 ∙ by Liang Ding, et al. ∙ 0 ∙ share

read it
End-to-end Animal Image Matting

Extracting accurate foreground animals from natural animal images benefi...
10/30/2020 ∙ by Jizhizi Li, et al. ∙ 0 ∙ share

read it
Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning

Image-based 3D shape retrieval (IBSR) aims to find the corresponding 3D ...
10/23/2020 ∙ by Huan Fu, et al. ∙ 0 ∙ share

read it
SCOP: Scientific Control for Reliable Neural Network Pruning

This paper proposes a reliable neural network pruning algorithm by setti...
10/21/2020 ∙ by Yehui Tang, et al. ∙ 0 ∙ share

read it
Quantum circuit architecture search: error mitigation and trainability enhancement for variational quantum solvers

Quantum error mitigation techniques are at the heart of quantum computat...
10/20/2020 ∙ by Yuxuan Du, et al. ∙ 0 ∙ share

read it
On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstration

Imitation learning from observation (LfO) is more preferable than imitat...
10/16/2020 ∙ by Zhihao Cheng, et al. ∙ 0 ∙ share

read it
Pretrained Language Models for Dialogue Generation with Multiple Input Sources

Large-scale pretrained language models have achieved outstanding perform...
10/15/2020 ∙ by Yu Cao, et al. ∙ 0 ∙ share

read it
Learning Propagation Rules for Attribution Map Generation

Prior gradient-based attribution-map methods rely on handcrafted propaga...
10/14/2020 ∙ by Yiding Yang, et al. ∙ 0 ∙ share

read it
Experimental Quantum Generative Adversarial Networks for Image Generation

Quantum machine learning is expected to be one of the first practical ap...
10/13/2020 ∙ by He-Liang Huang, et al. ∙ 0 ∙ share

read it
Targeted Attention Attack on Deep Learning Models in Road Sign Recognition

Real world traffic sign recognition is an important step towards buildin...
10/09/2020 ∙ by Xinghao Yang, et al. ∙ 4 ∙ share

read it
Self-supervised Exposure Trajectory Recovery for Dynamic Blur Estimation

Dynamic scene blurring is an important yet challenging topic. Recently, ...
10/06/2020 ∙ by Youjian Zhang, et al. ∙ 0 ∙ share

read it
Open-Set Hypothesis Transfer with Semantic Consistency

Unsupervised open-set domain adaptation (UODA) is a realistic problem wh...
10/01/2020 ∙ by Zeyu Feng, et al. ∙ 4 ∙ share

read it
Batch Coherence-Driven Network for Part-aware Person Re-Identification

Existing part-aware person re-identification methods typically employ tw...
09/21/2020 ∙ by Kan Wang, et al. ∙ 0 ∙ share

read it
3D-FUTURE: 3D Furniture shape with TextURE

The 3D CAD shapes in current 3D benchmarks are mostly collected from onl...
09/21/2020 ∙ by Huan Fu, et al. ∙ 16 ∙ share

read it
AdderSR: Towards Energy Efficient Image Super-Resolution

This paper studies the single image super-resolution problem using adder...
09/18/2020 ∙ by Dehua Song, et al. ∙ 4 ∙ share

read it
Searching for Low-Bit Weights in Quantized Neural Networks

Quantized neural networks with low-bit weights and activations are attra...
09/18/2020 ∙ by Zhaohui Yang, et al. ∙ 7 ∙ share

read it
Heatmap Regression via Randomized Rounding

Heatmap regression has become the mainstream methodology for deep learni...
09/01/2020 ∙ by Baosheng Yu, et al. ∙ 55 ∙ share

read it
Adaptive Context-Aware Multi-Modal Network for Depth Completion

Depth completion aims to recover a dense depth map from the sparse depth...
08/25/2020 ∙ by Shanshan Zhao, et al. ∙ 0 ∙ share

read it
Nighttime Dehazing with a Synthetic Benchmark

Increasing the visibility of nighttime hazy images is challenging becaus...
08/10/2020 ∙ by Jing Zhang, et al. ∙ 11 ∙ share

read it
Recurrent Feature Reasoning for Image Inpainting

Existing inpainting methods have achieved promising performance for reco...
08/09/2020 ∙ by Jingyuan Li, et al. ∙ 20 ∙ share

read it
Polysemy Deciphering Network for Robust Human-Object Interaction Detection

Human-Object Interaction (HOI) detection is important to human-centric s...
08/07/2020 ∙ by Xubin Zhong, et al. ∙ 0 ∙ share

read it
Approximated Bilinear Modules for Temporal Modeling

We consider two less-emphasized temporal properties of video: 1. Tempora...
07/25/2020 ∙ by Xinqi Zhu, et al. ∙ 2 ∙ share

read it
Learning Disentangled Representations with Latent Variation Predictability

Latent traversal is a popular approach to visualize the disentangled lat...
07/25/2020 ∙ by Xinqi Zhu, et al. ∙ 13 ∙ share

read it
Visual Compositional Learning for Human-Object Interaction Detection

Human-Object interaction (HOI) detection aims to localize and infer rela...
07/24/2020 ∙ by Zhi Hou, et al. ∙ 0 ∙ share

read it
Quantum differentially private sparse regression learning

Differentially private (DP) learning, which aims to accurately extract p...
07/23/2020 ∙ by Yuxuan Du, et al. ∙ 0 ∙ share

read it
Symbiotic Adversarial Learning for Attribute-based Person Search

Attribute-based person search is in significant demand for applications ...
07/19/2020 ∙ by Yu-Tong Cao, et al. ∙ 6 ∙ share

read it
Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms

This paper studies the relationship between generalization and privacy p...
07/18/2020 ∙ by Fengxiang He, et al. ∙ 0 ∙ share

read it
Quantum Geometric Machine Learning for Quantum Circuits and Control

The application of machine learning techniques to solve problems in quan...
06/19/2020 ∙ by Elija Perrier, et al. ∙ 0 ∙ share

read it
Parts-dependent Label Noise: Towards Instance-dependent Label Noise

Learning with the instance-dependent label noise is challenging, because...
06/14/2020 ∙ by Xiaobo Xia, et al. ∙ 0 ∙ share

read it
Condensing Two-stage Detection with Automatic Object Key Part Discovery

Modern two-stage object detectors generally require excessively large mo...
06/10/2020 ∙ by Zhe Chen, et al. ∙ 0 ∙ share

read it
Knowledge Distillation: A Survey

In recent years, deep neural networks have been very successful in the f...
06/09/2020 ∙ by Jianping Gou, et al. ∙ 0 ∙ share

read it
Boundary-assisted Region Proposal Networks for Nucleus Segmentation

Nucleus segmentation is an important task in medical image analysis. How...
06/04/2020 ∙ by Shengcong Chen, et al. ∙ 0 ∙ share

read it
DC-NAS: Divide-and-Conquer Neural Architecture Search

Most applications demand high-performance deep neural architectures cost...
05/29/2020 ∙ by Yunhe Wang, et al. ∙ 0 ∙ share

read it
HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens

Neural Architecture Search (NAS) refers to automatically design the arch...
05/29/2020 ∙ by Zhaohui Yang, et al. ∙ 12 ∙ share

read it
Adversarial Attacks for Embodied Agents

Adversarial attacks are valuable for providing insights into the blind-s...
05/19/2020 ∙ by Aishan Liu, et al. ∙ 40 ∙ share

read it
Self-Attention with Cross-Lingual Position Representation

Position encoding (PE), an essential part of self-attention networks (SA...
04/28/2020 ∙ by Liang Ding, et al. ∙ 0 ∙ share

read it
Deep Multimodal Neural Architecture Search

Designing effective neural networks is fundamentally important in deep m...
04/25/2020 ∙ by Zhou Yu, et al. ∙ 17 ∙ share

read it
Repulsive Mixture Models of Exponential Family PCA for Clustering

The mixture extension of exponential family principal component analysis...
04/07/2020 ∙ by Maoying Qiao, et al. ∙ 0 ∙ share

read it
Detecting Communities in Heterogeneous Multi-Relational Networks:A Message Passing based Approach

Community is a common characteristic of networks including social networ...
04/06/2020 ∙ by Maoying Qiao, et al. ∙ 0 ∙ share

read it
Learning Oracle Attention for High-fidelity Face Completion

High-fidelity face completion is a challenging task due to the rich and ...
03/31/2020 ∙ by Tong Zhou, et al. ∙ 0 ∙ share

read it
GPS-Net: Graph Property Sensing Network for Scene Graph Generation

Scene graph generation (SGG) aims to detect objects in an image along wi...
03/29/2020 ∙ by Xin Lin, et al. ∙ 0 ∙ share

read it
Piecewise linear activations substantially shape the loss surfaces of neural networks

Understanding the loss surface of a neural network is fundamentally impo...
03/27/2020 ∙ by Fengxiang He, et al. ∙ 0 ∙ share

read it
Distillating Knowledge from Graph Convolutional Networks

Existing knowledge distillation methods focus on convolutional neural ne...
03/23/2020 ∙ by Yiding Yang, et al. ∙ 70 ∙ share

read it

Dacheng Tao

Featured Co-authors