1.8k citations · 2.4k across the 36 of their papers we have counts for
36 papers
OccNet: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions
Miao Fan, Mingrui Chen, Chen Hu +1
Image matching is a fundamental and critical task in various visual applications, such as Simultaneous Localization and Mapping (SLAM) and image retrieval, which require accurate p…
Proximal Policy Optimization Actual Combat: Manipulating Output Tokenizer Length
Miao Fan, Chen Hu, Shuchang Zhou
The Reinforcement Learning from Human Feedback (RLHF) plays a pivotal role in shaping the impact of large language models (LLMs), contributing significantly to controlling output t…
A Dynamic Multi-Scale Voxel Flow Network for Video Prediction
Xiaotao Hu, Zhewei Huang, Ailin Huang +2
The performance of video prediction has been greatly boosted by advanced deep neural networks. However, most of the current methods suffer from large model sizes and require extra…
Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning
Yun-Hao Cao, Peiqin Sun, Shuchang Zhou
We propose universally slimmable self-supervised learning (dubbed as US3L) to achieve better accuracy-efficiency trade-offs for deploying self-supervised models across different de…
OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
Ruihang Miao, Weizhou Liu, Mingrui Chen +4
3D Semantic Scene Completion (SSC) can provide dense geometric and semantic scene representations, which can be applied in the field of autonomous driving and robotic systems. It i…
A Survey on Human Action Recognition
Zhou Shuchang
Human Action Recognition (HAR), one of the most important tasks in computer vision, has developed rapidly in the past decade and has a wide range of applications in health monitori…
One is All: Bridging the Gap Between Neural Radiance Fields Architectures with Progressive Volume Distillation
Shuangkang Fang, Weixin Xu, Heng Wang +3
Neural Radiance Fields (NeRF) methods have proved effective as compact, high-quality and versatile representations for 3D scenes, and enable downstream tasks such as editing, retri…
Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer
Ailin Huang, Zhewei Huang, Shuchang Zhou
This paper reports our solution for ACM Multimedia ViCo 2022 Conversational Head Generation Challenge, which aims to generate vivid face-to-face conversation videos based on audio…
Synergistic Self-supervised and Quantization Learning
Yun-Hao Cao, Peiqin Sun, Yechang Huang +2
With the success of self-supervised learning (SSL), it has become a mainstream paradigm to fine-tune from self-supervised pretrained models to boost the performance on downstream t…
Collaborative Neural Rendering using Anime Character Sheets
Zuzeng Lin, Ailin Huang, Zhewei Huang
Drawing images of characters with desired poses is an essential but laborious task in anime production. Assisting artists to create is a research hotspot in recent years. In this p…
The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights
Maxime Gasse, Quentin Cappart, Jonas Charfreitag +38
Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused on solving problem instances in isolatio…
ML4CO-KIDA: Knowledge Inheritance in Dataset Aggregation
Zixuan Cao, Yang Xu, Zhewei Huang +1
The Machine Learning for Combinatorial Optimization (ML4CO) NeurIPS 2021 competition aims to improve state-of-the-art combinatorial optimization solvers by replacing key heuristic…
FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
Yang Lin, Tianyu Zhang, Peiqin Sun +2
Network quantization significantly reduces model inference complexity and has been widely used in real-world deployments. However, most existing quantization methods have been deve…
Arch-Net: Model Distillation for Architecture Agnostic Model Deployment
Weixin Xu, Zipeng Feng, Shuangkang Fang +3
Vast requirement of computation power of Deep Neural Networks is a major hurdle to their real world applications. Many recent Application Specific Integrated Circuit (ASIC) chips f…
Optimal Quantization for Batch Normalization in Neural Network Deployments and Beyond
Dachao Lin, Peiqin Sun, Guangzeng Xie +2
Quantized Neural Networks (QNNs) use low bit-width fixed-point numbers for representing weight parameters and activations, and are often used in real-world applications due to thei…
Are L2 adversarial examples intrinsically different?
Mingxuan Li, Jingyuan Wang, Yufan Wu
Deep Neural Network (DDN) has achieved notable success in various tasks, including many security concerning scenarios. However, a considerable amount of work has proved its vulnera…
Learning to Paint With Model-based Deep Reinforcement Learning
Zhewei Huang, Wen Heng, Shuchang Zhou
We show how to teach machines to paint like human painters, who can use a small number of strokes to create fantastic paintings. By employing a neural renderer in model-based Deep…
Harmonic Adversarial Attack Method
Wen Heng, Shuchang Zhou, Tingting Jiang
Adversarial attacks find perturbations that can fool models into misclassifying images. Previous works had successes in generating noisy/edge-rich adversarial perturbations, at the…
Stroke-based Character Reconstruction
Zhewei Huang, Wen Heng, Yuanzheng Tao +1
Background elimination for noisy character images or character images from real scene is still a challenging problem, due to the bewildering backgrounds, uneven illumination, low r…
Interpolatron: Interpolation or Extrapolation Schemes to Accelerate Optimization for Deep Neural Networks
Guangzeng Xie, Yitan Wang, Shuchang Zhou +1
In this paper we explore acceleration techniques for large scale nonconvex optimization problems with special focuses on deep neural networks. The extrapolation scheme is a classic…
Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments
Łukasz Kidziński, Sharada Prasanna Mohanty, Carmichael Ong +26
In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle c…
Learning to Run with Actor-Critic Ensemble
Zhewei Huang, Shuchang Zhou, BoEr Zhuang +1
We introduce an Actor-Critic Ensemble(ACE) method for improving the performance of Deep Deterministic Policy Gradient(DDPG) algorithm. At inference time, our method uses a critic e…
Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks
Shuchang Zhou, Yuzhi Wang, He Wen +2
Quantized Neural Networks (QNNs), which use low bitwidth numbers for representing parameters and performing computations, have been proposed to reduce the computation complexity, s…
GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
Shuchang Zhou, Taihong Xiao, Yi Yang +3
Object Transfiguration replaces an object in an image with another object from a second image. For example it can perform tasks like "putting exactly those eyeglasses from image A…