Search Results for author: Dong Li

Found 90 papers, 19 papers with code

ProgressFace: Scale-Aware Progressive Learning for Face Detection

no code implementations ECCV 2020 Jiashu Zhu, Dong Li, Tiantian Han, Lu Tian, Yi Shan

In this work, we propose a novel scale-aware progressive training mechanism to address large scale variations across faces.

Face Detection

MEMO : Accelerating Transformers with Memoization on Big Memory Systems

no code implementations23 Jan 2023 Yuan Feng, Hyeran Jeon, Filip Blagojevic, Cyril Guyot, Qing Li, Dong Li

However, the transformer is computation-intensive, causing a long inference time.

Generation-Augmented Query Expansion For Code Retrieval

no code implementations20 Dec 2022 Dong Li, Yelong Shen, Ruoming Jin, Yi Mao, Kuan Wang, Weizhu Chen

Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code snippet.

Association Code Generation +1

Towards Reliable Item Sampling for Recommendation Evaluation

no code implementations28 Nov 2022 Dong Li, Ruoming Jin, Zhenming Liu, Bin Ren, Jing Gao, Zhi Liu

Since Rendle and Krichene argued that commonly used sampling-based evaluation metrics are ``inconsistent'' with respect to the global metrics (even in expectation), there have been a few studies on the sampling-based recommender system evaluation.

Recommendation Systems

State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning

no code implementations28 Nov 2022 Chen Chen, Hongyao Tang, Yi Ma, Chao Wang, Qianli Shen, Dong Li, Jianye Hao

The key idea of SA-PP is leveraging discounted stationary state distribution ratios between the learning policy and the offline dataset to modulate the degree of behavior regularization in a state-wise manner, so that pessimism can be implemented in a more appropriate way.

Offline RL Q-Learning +2

Prototypical context-aware dynamics generalization for high-dimensional model-based reinforcement learning

no code implementations23 Nov 2022 Junjie Wang, Yao Mu, Dong Li, Qichao Zhang, Dongbin Zhao, Yuzheng Zhuang, Ping Luo, Bin Wang, Jianye Hao

The latent world model provides a promising way to learn policies in a compact latent space for tasks with high-dimensional observations, however, its generalization across diverse environments with unseen dynamics remains challenging.

Model-based Reinforcement Learning reinforcement-learning +1

Linear Video Transformer with Feature Fixation

no code implementations15 Oct 2022 Kaiyue Lu, Zexiang Liu, Jianyuan Wang, Weixuan Sun, Zhen Qin, Dong Li, Xuyang Shen, Hui Deng, Xiaodong Han, Yuchao Dai, Yiran Zhong

Therefore, we propose a feature fixation module to reweight the feature importance of the query and key before computing linear attention.

Association Feature Importance +1

On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies

no code implementations21 Sep 2022 Haozhi Wang, Qing Wang, Yunfeng Shao, Dong Li, Jianye Hao, Yinchuan Li

Modern meta-reinforcement learning (Meta-RL) methods are mainly developed based on model-agnostic meta-learning, which performs policy gradient steps across tasks to maximize policy performance.

Continuous Control Meta-Learning +3

Multi-Document Scientific Summarization from a Knowledge Graph-Centric View

1 code implementation COLING 2022 Pancheng Wang, Shasha Li, Kunyuan Pang, Liangliang He, Dong Li, Jintao Tang, Ting Wang

Multi-Document Scientific Summarization (MDSS) aims to produce coherent and concise summaries for clusters of topic-relevant scientific papers.

Knowledge Graphs

Coarse-to-Fine Knowledge-Enhanced Multi-Interest Learning Framework for Multi-Behavior Recommendation

no code implementations3 Aug 2022 Chang Meng, Ziqi Zhao, Wei Guo, Yingxue Zhang, Haolun Wu, Chen Gao, Dong Li, Xiu Li, Ruiming Tang

More specifically, we propose a novel Coarse-to-fine Knowledge-enhanced Multi-interest Learning (CKML) framework to learn shared and behavior-specific interests for different behaviors.

Neural Architecture Search on Efficient Transformers and Beyond

no code implementations28 Jul 2022 Zexiang Liu, Dong Li, Kaiyue Lu, Zhen Qin, Weixuan Sun, Jiacheng Xu, Yiran Zhong

To address this issue, we propose a new framework to find optimal architectures for efficient Transformers with the neural architecture search (NAS) technique.

Image Classification Machine Translation +1

Auto Machine Learning for Medical Image Analysis by Unifying the Search on Data Augmentation and Neural Architecture

no code implementations21 Jul 2022 Jianwei Zhang, Dong Li, Lituan Wang, Lei Zhang

To address the problem, an improved augmentation search strategy, named Augmented Density Matching, was proposed by randomly sampling policies from a prior distribution for training.

AutoML Data Augmentation

Pushing the Limit of Phase Shift Feedback Compression for Intelligent Reflecting Surface-Assisted Wireless Systems by Exploiting Global Attention

no code implementations5 Jul 2022 Xianhua Yu, Dong Li

However, most of existing works on IRS focus on how to compute the phase shift for performance enhancement, and the problem on how to obtain the computed phase shift at the IRS side is generally neglected.

SEREN: Knowing When to Explore and When to Exploit

no code implementations30 May 2022 Changmin Yu, David Mguni, Dong Li, Aivar Sootla, Jun Wang, Neil Burgess

Efficient reinforcement learning (RL) involves a trade-off between "exploitative" actions that maximise expected reward and "explorative'" ones that sample unvisited states.

Rethinking Reinforcement Learning based Logic Synthesis

no code implementations16 May 2022 Chao Wang, Chen Chen, Dong Li, Bin Wang

Recently, reinforcement learning has been used to address logic synthesis by formulating the operator sequence optimization problem as a Markov decision process.

reinforcement-learning reinforcement Learning

Dynamic Sparse R-CNN

no code implementations CVPR 2022 Qinghang Hong, Fengming Liu, Dong Li, Ji Liu, Lu Tian, Yi Shan

Sparse R-CNN is a recent strong object detection baseline by set prediction on sparse, learnable proposal boxes and proposal features.

object-detection Object Detection

Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification

no code implementations CVPR 2022 Haowei Zhu, Wenjing Ke, Dong Li, Ji Liu, Lu Tian, Yi Shan

First, we propose global-local cross-attention (GLCA) to enhance the interactions between global images and local high-response regions, which can help reinforce the spatial-wise discriminative clues for recognition.

Fine-Grained Image Classification Fine-Grained Visual Categorization

Compare learning: bi-attention network for few-shot learning

no code implementations25 Mar 2022 Li Ke, Meng Pan, Weigao Wen, Dong Li

Learning with few labeled data is a key challenge for visual recognition, as deep neural networks tend to overfit using a few samples only.

Few-Shot Learning Metric Learning

Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework

no code implementations10 Mar 2022 Xiaotian Hao, Hangyu Mao, Weixun Wang, Yaodong Yang, Dong Li, Yan Zheng, Zhen Wang, Jianye Hao

To break this curse, we propose a unified agent permutation framework that exploits the permutation invariance (PI) and permutation equivariance (PE) inductive biases to reduce the multiagent state space.

Data Augmentation reinforcement Learning +1

Who Should Review Your Proposal? Interdisciplinary Topic Path Detection for Research Proposals

no code implementations7 Mar 2022 Meng Xiao, Ziyue Qiao, Yanjie Fu, Hao Dong, Yi Du, Pengyang Wang, Dong Li, Yuanchun Zhou

After extracting the semantic and interdisciplinary knowledge, we design a level-wise prediction component to fuse the two types of knowledge representations and detect interdisciplinary topic paths for each proposal.

Representing Videos as Discriminative Sub-graphs for Action Recognition

no code implementations CVPR 2021 Dong Li, Zhaofan Qiu, Yingwei Pan, Ting Yao, Houqiang Li, Tao Mei

For each action category, we execute online clustering to decompose the graph into sub-graphs on each scale through learning Gaussian Mixture Layer and select the discriminative sub-graphs as action prototypes for recognition.

Action Recognition Graph Learning +1

Scalable Deep Graph Clustering with Random-walk based Self-supervised Learning

no code implementations31 Dec 2021 Xiang Li, Dong Li, Ruoming Jin, Gagan Agrawal, Rajiv Ramnath

Though other methods (particularly those based on Laplacian Smoothing) have reported better accuracy, a fundamental limitation of all the work is a lack of scalability.

Deep Clustering Graph Clustering +2

A Survey on Interpretable Reinforcement Learning

no code implementations24 Dec 2021 Claire Glanois, Paul Weng, Matthieu Zimmer, Dong Li, Tianpei Yang, Jianye Hao, Wulong Liu

To that aim, we distinguish interpretability (as a property of a model) and explainability (as a post-hoc operation, with the intervention of a proxy) and discuss them in the context of RL with an emphasis on the former notion.

Autonomous Driving Decision Making +2

Learning State Representations via Retracing in Reinforcement Learning

1 code implementation ICLR 2022 Changmin Yu, Dong Li, Jianye Hao, Jun Wang, Neil Burgess

We propose learning via retracing, a novel self-supervised approach for learning the state representation (and the associated dynamics model) for reinforcement learning tasks.

Continuous Control Model-based Reinforcement Learning +3

SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition

no code implementations17 Nov 2021 Hangyu Mao, Chao Wang, Xiaotian Hao, Yihuan Mao, Yiming Lu, Chengjie WU, Jianye Hao, Dong Li, Pingzhong Tang

The MineRL competition is designed for the development of reinforcement learning and imitation learning algorithms that can efficiently leverage human demonstrations to drastically reduce the number of environment interactions needed to solve the complex \emph{ObtainDiamond} task with sparse rewards.

Imitation Learning reinforcement-learning +1

Generalizable Cross-Graph Embedding for GNN-based Congestion Prediction

no code implementations10 Nov 2021 Amur Ghose, Vincent Zhang, Yingxue Zhang, Dong Li, Wulong Liu, Mark Coates

To address this limitation, we propose a framework that can directly learn embeddings for the given netlist to enhance the quality of our node features.

Graph Embedding

Convolutional Autoencoder-Based Phase Shift Feedback Compression for Intelligent Reflecting Surface-Assisted Wireless Systems

1 code implementation24 Oct 2021 Xianhua Yu, Dong Li, Yongjun Xu, Ying-Chang Liang

To this end, it is crucial to adjust the phases of reflecting elements of the IRS, and most of the research works focus on how to optimize/quantize the phase for different optimization objectives.


Ranking Cost: Building An Efficient and Scalable Circuit Routing Planner with Evolution-Based Optimization

1 code implementation8 Oct 2021 Shiyu Huang, Bin Wang, Dong Li, Jianye Hao, Ting Chen, Jun Zhu

In this work, we propose a new algorithm for circuit routing, named Ranking Cost, which innovatively combines search-based methods (i. e., A* algorithm) and learning-based methods (i. e., Evolution Strategies) to form an efficient and trainable router.

Learning Explicit Credit Assignment for Multi-agent Joint Q-learning

no code implementations29 Sep 2021 Hangyu Mao, Jianye Hao, Dong Li, Jun Wang, Weixun Wang, Xiaotian Hao, Bin Wang, Kun Shao, Zhen Xiao, Wulong Liu

In contrast, we formulate an \emph{explicit} credit assignment problem where each agent gives its suggestion about how to weight individual Q-values to explicitly maximize the joint Q-value, besides guaranteeing the Bellman optimality of the joint Q-value.


On the regularization landscape for the linear recommendation models

no code implementations29 Sep 2021 Dong Li, Zhenming Liu, Ruoming Jin, Zhi Liu, Jing Gao, Bin Ren

Recently, a wide range of recommendation algorithms inspired by deep learning techniques have emerged as the performance leaders several standard recommendation benchmarks.

Learning Pseudometric-based Action Representations for Offline Reinforcement Learning

no code implementations29 Sep 2021 Pengjie Gu, Mengchen Zhao, Chen Chen, Dong Li, Jianye Hao, Bo An

Offline reinforcement learning is a promising approach for practical applications since it does not require interactions with real-world environments.

Offline RL Recommendation Systems +3

CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation

1 code implementation24 Aug 2021 Xidong Feng, Chen Chen, Dong Li, Mengchen Zhao, Jianye Hao, Jun Wang

Meta learning, especially gradient based one, can be adopted to tackle this problem by learning initial parameters of the model and thus allowing fast adaptation to a specific task from limited data examples.

Meta-Learning Recommendation Systems

On Sampling Top-K Recommendation Evaluation

no code implementations20 Jun 2021 Dong Li, Ruoming Jin, Jing Gao, Zhi Liu

Recently, Rendle has warned that the use of sampling-based top-$k$ metrics might not suffice.

RankDetNet: Delving Into Ranking Constraints for Object Detection

no code implementations CVPR 2021 Ji Liu, Dong Li, Rongzhang Zheng, Lu Tian, Yi Shan

To this end, we comprehensively investigate three types of ranking constraints, i. e., global ranking, class-specific ranking and IoU-guided ranking losses.

3D Object Detection Classification +2

Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment

no code implementations1 Jun 2021 Tianze Zhou, Fubiao Zhang, Kun Shao, Kai Li, Wenhan Huang, Jun Luo, Weixun Wang, Yaodong Yang, Hangyu Mao, Bin Wang, Dong Li, Wulong Liu, Jianye Hao

In addition, we use a novel agent network named Population Invariant agent with Transformer (PIT) to realize the coordination transfer in more varieties of scenarios.

Management Multi-agent Reinforcement Learning +3

Towards a Better Understanding of Linear Models for Recommendation

no code implementations27 May 2021 Ruoming Jin, Dong Li, Jing Gao, Zhi Liu, Li Chen, Yang Zhou

Through the derivation and analysis of the closed-form solutions for two basic regression and matrix factorization approaches, we found these two approaches are indeed inherently related but also diverge in how they "scale-down" the singular values of the original user-item interaction matrix.


Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving

no code implementations21 Mar 2021 Li Wang, Dong Li, Han Liu, Jinzhang Peng, Lu Tian, Yi Shan

Our goal is to train a unified model for improving the performance in each dataset by leveraging information from all the datasets.

3D Semantic Segmentation Autonomous Driving +2

Learning Symbolic Rules for Interpretable Deep Reinforcement Learning

no code implementations15 Mar 2021 Zhihao Ma, Yuzheng Zhuang, Paul Weng, Hankz Hankui Zhuo, Dong Li, Wulong Liu, Jianye Hao

To address this challenge and improve the transparency, we propose a Neural Symbolic Reinforcement Learning framework by introducing symbolic logic into DRL.

reinforcement-learning reinforcement Learning

On Estimating Recommendation Evaluation Metrics under Sampling

no code implementations2 Mar 2021 Ruoming Jin, Dong Li, Benjamin Mudrak, Jing Gao, Zhi Liu

The proposed approaches either are rather uninformative (linking sampling to metric evaluation) or can only work on simple metrics, such as Recall/Precision (Krichene and Rendle 2020; Li et al. 2020).

Excess-noise suppression for a squeezed state propagating through random amplifying media via wave-front shaping

no code implementations4 Feb 2021 Dong Li, Song Sun, Yao Yao

After propagating through a random amplifying medium, a squeezed state commonly shows excess noise above the shot-noise level.

Quantum Physics

Diagnosing a Solar Flaring Core with Bidirectional Quasi-Periodic Fast Propagating Magnetoacoustic Waves

no code implementations29 Jan 2021 Yuhu Miao, Dong Li, Ding Yuan, Chaowei Jiang, Abouazza Elmhamdi, Mingyu Zhao, Sergey Anfinogentov

Quasi-periodic fast propagating (QFP) waves are often excited by solar flares, and could be trapped in the coronal structure with low Alfv\'en speed, so they could be used as a diagnosing tool for both the flaring core and magnetic waveguide.

Solar and Stellar Astrophysics

ZeRO-Offload: Democratizing Billion-Scale Model Training

3 code implementations18 Jan 2021 Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, Yuxiong He

By combining compute and memory efficiency with ease-of-use, ZeRO-Offload democratizes large-scale model training making it accessible to even data scientists with access to just a single GPU.

Robust Multi-Agent Reinforcement Learning Driven by Correlated Equilibrium

no code implementations1 Jan 2021 Yizheng Hu, Kun Shao, Dong Li, Jianye Hao, Wulong Liu, Yaodong Yang, Jun Wang, Zhanxing Zhu

Therefore, to achieve robust CMARL, we introduce novel strategies to encourage agents to learn correlated equilibrium while maximally preserving the convenience of the decentralized execution.

Adversarial Robustness reinforcement-learning +2

Meta-Learning with Implicit Processes

no code implementations1 Jan 2021 Yizhou Chen, Dong Li, Na Li, TONG LIANG, Shizhuo Zhang, Bryan Kian Hsiang Low

This paper presents a novel implicit process-based meta-learning (IPML) algorithm that, in contrast to existing works, explicitly represents each task as a continuous latent vector and models its probabilistic belief within the highly expressive IP framework.


Approximating Pareto Frontier through Bayesian-optimization-directed Robust Multi-objective Reinforcement Learning

no code implementations1 Jan 2021 Xiangkun He, Jianye Hao, Dong Li, Bin Wang, Wulong Liu

Thirdly, the agent’s learning process is regarded as a black-box, and the comprehensive metric we proposed is computed after each episode of training, then a Bayesian optimization (BO) algorithm is adopted to guide the agent to evolve towards improving the quality of the approximated Pareto frontier.

reinforcement-learning reinforcement Learning

Ranking Cost: One-Stage Circuit Routing by Directly Optimizing Global Objective Function

no code implementations1 Jan 2021 Shiyu Huang, Bin Wang, Dong Li, Jianye Hao, Jun Zhu, Ting Chen

In our method, we introduce a new set of variables called cost maps, which can help the A* router to find out proper paths to achieve the global object.

Improving Low-Precision Network Quantization via Bin Regularization

no code implementations ICCV 2021 Tiantian Han, Dong Li, Ji Liu, Lu Tian, Yi Shan

Such bin regularization (BR) mechanism encourages the weight distribution of each quantization bin to be sharp and approximate to a Dirac delta distribution ideally.


Strong but Simple Baseline with Dual-Granularity Triplet Loss for Visible-Thermal Person Re-Identification

1 code implementation9 Dec 2020 Haijun Liu, Yanxia Chai, Xiaoheng Tan, Dong Li, Xichuan Zhou

In this letter, we propose a conceptually simple and effective dual-granularity triplet loss for visible-thermal person re-identification (VT-ReID).

Cross-Modal Person Re-Identification

Towards Better Object Detection in Scale Variation with Adaptive Feature Selection

1 code implementation6 Dec 2020 Zehui Gong, Dong Li

It is a common practice to exploit pyramidal feature representation to tackle the problem of scale variation in object instances.

object-detection Object Detection

HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory

no code implementations NeurIPS 2020 Jie Ren, Minjia Zhang, Dong Li

The emergence of heterogeneous memory (HM) brings a solution to significantly increase memory capacity and break the above tradeoff: Using HM, billions of data points can be placed in the main memory on a single machine without using any data compression.

Data Compression Quantization

What About Inputing Policy in Value Function: Policy Representation and Policy-extended Value Function Approximator

no code implementations NeurIPS 2021 Hongyao Tang, Zhaopeng Meng, Jianye Hao, Chen Chen, Daniel Graves, Dong Li, Changmin Yu, Hangyu Mao, Wulong Liu, Yaodong Yang, Wenyuan Tao, Li Wang

We study Policy-extended Value Function Approximator (PeVFA) in Reinforcement Learning (RL), which extends conventional value function approximator (VFA) to take as input not only the state (and action) but also an explicit policy representation.

Continuous Control Contrastive Learning +2

Towards Optimal Filter Pruning with Balanced Performance and Pruning Speed

1 code implementation14 Oct 2020 Dong Li, Sitong Chen, Xudong Liu, YunDa Sun, Li Zhang

In this paper, we propose a balanced filter pruning method for both performance and pruning speed.

Transfer among Agents: An Efficient Multiagent Transfer Learning Framework

no code implementations28 Sep 2020 Tianpei Yang, Jianye Hao, Weixun Wang, Hongyao Tang, Zhaopeng Meng, Hangyu Mao, Dong Li, Wulong Liu, Yujing Hu, Yingfeng Chen, Changjie Fan

In many cases, each agent's experience is inconsistent with each other which causes the option-value estimation to oscillate and to become inaccurate.

Transfer Learning

Smart-PGSim: Using Neural Network to Accelerate AC-OPF Power Grid Simulation

no code implementations26 Aug 2020 Wenqian Dong, Zhen Xie, Gokcen Kestor, Dong Li

In this paper, we develop a neural network approach to the problem of accelerating the current optimal power flow (AC-OPF) by generating an intelligent initial solution.


Adaptive Neural Network-Based Approximation to Accelerate Eulerian Fluid Simulation

no code implementations26 Aug 2020 Wenqian Dong, Jie Liu, Zhen Xie, Dong Li

Evaluating with 20, 480 input problems, we show that Smartfluidnet achieves 1. 46x and 590x speedup comparing with a state-of-the-art neural network model and the original fluid simulation respectively on an NVIDIA Titan X Pascal GPU, while providing better simulation quality than the state-of-the-art model.

Long Short-Term Relation Networks for Video Action Detection

no code implementations31 Mar 2020 Dong Li, Ting Yao, Zhaofan Qiu, Houqiang Li, Tao Mei

It has been well recognized that modeling human-object or object-object relations would be helpful for detection task.

Action Detection Region Proposal

Feedback Graph Convolutional Network for Skeleton-based Action Recognition

no code implementations17 Mar 2020 Hao Yang, Dan Yan, Li Zhang, Dong Li, YunDa Sun, ShaoDi You, Stephen J. Maybank

It transmits the high-level semantic features to the low-level layers and flows temporal information stage by stage to progressively model global spatial-temporal features for action recognition; (3) The FGCN model provides early predictions.

Action Recognition Skeleton Based Action Recognition

FLAME: A Self-Adaptive Auto-labeling System for Heterogeneous Mobile Processors

no code implementations3 Mar 2020 Jie Liu, Jiawen Liu, Zhen Xie, Dong Li

How to accurately and efficiently label data on a mobile device is critical for the success of training machine learning models on mobile devices.

Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning

no code implementations3 Dec 2019 Hangyu Mao, Wulong Liu, Jianye Hao, Jun Luo, Dong Li, Zhengchao Zhang, Jun Wang, Zhen Xiao

Social psychology and real experiences show that cognitive consistency plays an important role to keep human society in order: if people have a more consistent cognition about their environments, they are more likely to achieve better cooperation.

Multi-agent Reinforcement Learning Q-Learning +2

Spam Review Detection with Graph Convolutional Networks

3 code implementations22 Aug 2019 Ao Li, Zhou Qin, Runshi Liu, Yiqun Yang, Dong Li

Furthermore, we deploy our system to process million-scale data daily at Xianyu.

MVB: A Large-Scale Dataset for Baggage Re-Identification and Merged Siamese Networks

2 code implementations26 Jul 2019 Zhulin Zhang, Dong Li, Jinhua Wu, YunDa Sun, Li Zhang

Second, all baggage images are captured by specially-designed multi-view camera system to handle pose variation and occlusion, in order to obtain the 3D information of baggage surface as complete as possible.

Combining Q&A Pair Quality and Question Relevance Features on Community-based Question Retrieval

no code implementations3 Jul 2019 Dong Li, Lin Li

The Q&A community has become an important way for people to access knowledge and information from the Internet.

Retrieval Translation

Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019

no code implementations14 Jun 2019 Zhaofan Qiu, Dong Li, Yehao Li, Qi Cai, Yingwei Pan, Ting Yao

This notebook paper presents an overview and comparative analysis of our systems designed for the following three tasks in ActivityNet Challenge 2019: trimmed action recognition, dense-captioning events in videos, and spatio-temporal action localization.

Action Recognition Dense Captioning +1

Performance Analysis and Characterization of Training Deep Learning Models on Mobile Devices

no code implementations10 Jun 2019 Jie Liu, Jiawen Liu, Wan Du, Dong Li

In this paper, we perform a variety of experiments on a representative mobile device (the NVIDIA TX2) to study the performance of training deep learning models.

Graph Attention Memory for Visual Navigation

no code implementations11 May 2019 Dong Li, Qichao Zhang, Dongbin Zhao, Yuzheng Zhuang, Bin Wang, Wulong Liu, Rasul Tutunov, Jun Wang

To address the long-term memory issue, this paper proposes a graph attention memory (GAM) architecture consisting of memory construction module, graph attention module and control module.

Graph Attention reinforcement Learning +1

A Preliminary Study of Neural Network-based Approximation for HPC Applications

1 code implementation18 Dec 2018 Wenqian Dong, Anzheng Guolu, Dong Li

Machine learning, as a tool to learn and model complicated (non)linear relationships between input and output data sets, has shown preliminary success in some HPC problems.

BIG-bench Machine Learning

Enhanced Expressive Power and Fast Training of Neural Networks by Random Projections

1 code implementation22 Nov 2018 Jian-Feng Cai, Dong Li, Jiaze Sun, Ke Wang

The key in our proof is that random projections embed stably the set of sparse vectors or a low-dimensional smooth manifold into a low-dimensional subspace.

Dimensionality Reduction

Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Driving

1 code implementation30 Oct 2018 Dong Li, Dongbin Zhao, Qichao Zhang, Yaran Chen

The control module which is based on reinforcement learning then makes a control decision based on these features.

Autonomous Driving Multi-Task Learning +2

Runtime Concurrency Control and Operation Scheduling for High Performance Neural Network Training

no code implementations21 Oct 2018 Jiawen Liu, Dong Li, Gokcen Kestor, Jeffrey Vetter

These frameworks employ a dataflow model where the NN training is modeled as a directed graph composed of a set of nodes.

BIG-bench Machine Learning Scheduling

Recurrent Tubelet Proposal and Recognition Networks for Action Detection

no code implementations ECCV 2018 Dong Li, Zhaofan Qiu, Qi Dai, Ting Yao, Tao Mei

The RTP initializes action proposals of the start frame through a Region Proposal Network and then estimates the movements of proposals in next frame in a recurrent manner.

Action Detection Region Proposal

Baidu Apollo EM Motion Planner

1 code implementation20 Jul 2018 Haoyang Fan, Fan Zhu, Changchun Liu, Liangliang Zhang, Li Zhuang, Dong Li, Weicheng Zhu, Jiangtao Hu, Hongye Li, Qi Kong

In this manuscript, we introduce a real-time motion planning system based on the Baidu Apollo (open source) autonomous driving platform.

Autonomous Driving Motion Planning

Progressive Representation Adaptation for Weakly Supervised Object Localization

1 code implementation12 Oct 2017 Dong Li, Jia-Bin Huang, Ya-Li Li, Shengjin Wang, Ming-Hsuan Yang

In classification adaptation, we transfer a pre-trained network to a multi-label classification task for recognizing the presence of a certain object in an image.

Classification General Classification +3

Joint Maximum Purity Forest with Application to Image Super-Resolution

1 code implementation30 Aug 2017 Hailiang Li, Kin-Man Lam, Dong Li

In the JMPF scheme, the original feature space is transformed into a compactly pre-clustered feature space, via a trained rotation matrix.

General Classification Image Super-Resolution +2

Learning Structured Semantic Embeddings for Visual Recognition

no code implementations5 Jun 2017 Dong Li, Hsin-Ying Lee, Jia-Bin Huang, Shengjin Wang, Ming-Hsuan Yang

First, we exploit the discriminative constraints to capture the intra- and inter-class relationships of image embeddings.

General Classification Multi-Label Classification +2

Weakly Supervised Object Localization With Progressive Domain Adaptation

no code implementations CVPR 2016 Dong Li, Jia-Bin Huang, Ya-Li Li, Shengjin Wang, Ming-Hsuan Yang

In this paper, we address this problem by progressive domain adaptation with two main steps: classification adaptation and detection adaptation.

Classification Domain Adaptation +4

Cannot find the paper you are looking for? You can Submit a new open access paper.