Search Results for author: Ge Li

Found 105 papers, 46 papers with code

Enabling Programming Thinking in Large Language Models Toward Code Generation

no code implementations11 May 2023 Jia Li, Ge Li, Yongmin Li, Zhi Jin

A large-scale study released that writing programs requires programming thinking, i. e., analyzing and implementing requirements in programming logic (e. g., sequence, branch, loop).

Code Generation

Self-Edit: Fault-Aware Code Editor for Code Generation

no code implementations6 May 2023 Kechi Zhang, Zhuo Li, Jia Li, Ge Li, Zhi Jin

Inspired by the process of human programming, we propose a generate-and-edit approach named Self-Edit that utilizes execution results of the generated code from LLMs to improve the code quality on the competitive programming task.

Code Generation

Towards Enhancing In-Context Learning for Code Generation

no code implementations31 Mar 2023 Jia Li, YunFei Zhao, Yongmin Li, Ge Li, Zhi Jin

In-context learning (ICL) with pre-trained language models (PTLMs) has shown great success in code generation.

Code Generation Retrieval +1

Implant Global and Local Hierarchy Information to Sequence based Code Representation Models

1 code implementation14 Mar 2023 Kechi Zhang, Zhuo Li, Zhi Jin, Ge Li

Furthermore, we propose the Hierarchy Transformer (HiT), a simple but effective sequence model to incorporate the complete hierarchical embeddings of source code into a Transformer model.

A Provably Secure Strong PUF based on LWE: Construction and Implementation

no code implementations5 Mar 2023 Xiaodan Xi, Ge Li, Ye Wang, Yeonsoo Jeon, Michael Orshansky

We construct lattice PUF with a physically obfuscated key and an LWE decryption function block.

Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring

1 code implementation CVPR 2023 Ruyang Liu, Jingjia Huang, Ge Li, Jiashi Feng, Xinglong Wu, Thomas H. Li

In this paper, based on the CLIP model, we revisit temporal modeling in the context of image-to-video knowledge transferring, which is the key point for extending image-text pretrained models to the video domain.

Ranked #5 on Video Retrieval on MSR-VTT-1kA (using extra training data)

Representation Learning Retrieval +3

Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering

no code implementations CVPR 2023 Nan Zhang, Zhiyi Pan, Thomas H. Li, Wei Gao, Ge Li

Recently, self-attention networks achieve impressive performance in point cloud segmentation due to their superiority in modeling long-range dependencies.

Point Cloud Segmentation

Efficient Hierarchical Entropy Model for Learned Point Cloud Compression

no code implementations CVPR 2023 Rui Song, Chunyang Fu, Shan Liu, Ge Li

Learning an accurate entropy model is a fundamental way to remove the redundancy in point cloud compression.

Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively

1 code implementation3 Nov 2022 Haojie Zhang, Ge Li, Jia Li, Zhongjin Zhang, Yuqi Zhu, Zhi Jin

Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently.

Language Modelling

CodePAD: Sequence-based Code Generation with Pushdown Automaton

no code implementations2 Nov 2022 Yihong Dong, Xue Jiang, Yuchen Liu, Ge Li, Zhi Jin

CodePAD can leverage existing sequence-based models, and we show that it can achieve 100\% grammatical correctness percentage on these benchmark datasets.

Code Generation Text Generation

Poison Attack and Defense on Deep Source Code Processing Models

no code implementations31 Oct 2022 Jia Li, Zhuo Li, Huangzhao Zhang, Ge Li, Zhi Jin, Xing Hu, Xin Xia

The attackers aim to inject insidious backdoors into models by poisoning the training data with poison samples.

Clone Detection Code Repair +1

CodeEditor: Learning to Edit Source Code with Pre-trained Models

no code implementations31 Oct 2022 Jia Li, Ge Li, Zhuo Li, Zhi Jin, Xing Hu, Kechi Zhang, Zhiyi Fu

Pre-trained models are first pre-trained with pre-training tasks and fine-tuned with the code editing task.

Language Modelling Masked Language Modeling

Frequency-Aware Self-Supervised Monocular Depth Estimation

1 code implementation11 Oct 2022 Xingyu Chen, Thomas H. Li, Ruonan Zhang, Ge Li

We present two versatile methods to generally enhance self-supervised monocular depth estimation (MDE) models.

Depth Prediction Monocular Depth Estimation +1

ProDMPs: A Unified Perspective on Dynamic and Probabilistic Movement Primitives

no code implementations4 Oct 2022 Ge Li, Zeqi Jin, Michael Volpp, Fabian Otto, Rudolf Lioutikov, Gerhard Neumann

MPs can be broadly categorized into two types: (a) dynamics-based approaches that generate smooth trajectories from any initial state, e. g., Dynamic Movement Primitives (DMPs), and (b) probabilistic approaches that capture higher-order statistics of the motion, e. g., Probabilistic Movement Primitives (ProMPs).

Numerical Integration

Antecedent Predictions Are More Important Than You Think: An Effective Method for Tree-Based Code Generation

no code implementations22 Aug 2022 Yihong Dong, Ge Li, Zhi Jin

To evaluate the effectiveness of our proposed loss, we implement and train an Antecedent Prioritized Tree-based code generation model called APT.

Code Generation

Incorporating Domain Knowledge through Task Augmentation for Front-End JavaScript Code Generation

no code implementations22 Aug 2022 Sijie Shen, Xiang Zhu, Yihong Dong, Qizhi Guo, Yankun Zhen, Ge Li

However, in some domain-specific scenarios, building such a large paired corpus for code generation is difficult because there is no directly available pairing data, and a lot of effort is required to manually write the code descriptions to construct a high-quality training dataset.

Code Generation

Learning Program Representations with a Tree-Structured Transformer

no code implementations18 Aug 2022 Wenhan Wang, Kechi Zhang, Ge Li, Shangqing Liu, Anran Li, Zhi Jin, Yang Liu

Learning vector representations for programs is a critical step in applying deep learning techniques for program understanding tasks.

Representation Learning

OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms

no code implementations11 Aug 2022 Jia-Xin Zhuang, Xiansong Huang, Yang Yang, Jiancong Chen, Yue Yu, Wei Gao, Ge Li, Jie Chen, Tong Zhang

In this paper, we present OpenMedIA, an open-source toolbox library containing a rich set of deep learning methods for medical image analysis under heterogeneous Artificial Intelligence (AI) computing platforms.

Image Classification Medical Image Classification +2

Salient Object Detection for Point Clouds

1 code implementation25 Jul 2022 Songlin Fan, Wei Gao, Ge Li

This paper researches the unexplored task-point cloud salient object detection (SOD).

object-detection Object Detection +1

What does Transformer learn about source code?

no code implementations18 Jul 2022 Kechi Zhang, Ge Li, Zhi Jin

In the field of source code processing, the transformer-based representation models have shown great powerfulness and have achieved state-of-the-art (SOTA) performance in many tasks.

Variable misuse

SKFlow: Learning Optical Flow with Super Kernels

1 code implementation29 May 2022 Shangkun Sun, Yuanqi Chen, Yu Zhu, Guodong Guo, Ge Li

In this paper, we propose the Super Kernel Flow Network (SKFlow), a CNN architecture to ameliorate the impacts of occlusions on optical flow estimation.

Optical Flow Estimation

Nebula-I: A General Framework for Collaboratively Training Deep Learning Models on Low-Bandwidth Cloud Clusters

1 code implementation19 May 2022 Yang Xiang, Zhihua Wu, Weibao Gong, Siyu Ding, Xianjie Mo, Yuang Liu, Shuohuan Wang, Peng Liu, Yongshuai Hou, Long Li, Bin Wang, Shaohuai Shi, Yaqian Han, Yue Yu, Ge Li, Yu Sun, Yanjun Ma, dianhai yu

We took natural language processing (NLP) as an example to show how Nebula-I works in different training phases that include: a) pre-training a multilingual language model using two remote clusters; and b) fine-tuning a machine translation model using knowledge distilled from pre-trained models, which run through the most popular paradigm of recent deep learning.

Cross-Lingual Natural Language Inference Distributed Computing +2

Deep Geometry Post-Processing for Decompressed Point Clouds

1 code implementation29 Apr 2022 Xiaoqing Fan, Ge Li, Dingquan Li, Yurui Ren, Wei Gao, Thomas H. Li

Point cloud compression plays a crucial role in reducing the huge cost of data storage and transmission.


Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation

1 code implementation CVPR 2022 Wenbo Zhao, Xianming Liu, Zhiwei Zhong, Junjun Jiang, Wei Gao, Ge Li, Xiangyang Ji

Most existing methods either take the end-to-end supervised learning based manner, where large amounts of pairs of sparse input and dense ground-truth are exploited as supervision information; or treat up-scaling of different scale factors as independent tasks, and have to build multiple networks to handle upsampling with varying factors.

Self-Supervised Learning

Neural Texture Extraction and Distribution for Controllable Person Image Synthesis

1 code implementation CVPR 2022 Yurui Ren, Xiaoqing Fan, Ge Li, Shan Liu, Thomas H. Li

Our model is trained to predict human images in arbitrary poses, which encourages it to extract disentangled and expressive neural textures representing the appearance of different semantic entities.

Image Generation

Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval

1 code implementation12 Feb 2022 Xianghao Zang, Ge Li, Wei Gao

To fuse multi-scale feature representation, this paper presents a pyramid structure containing global-level information and many pieces of local-level information from different scales.

Person Re-Identification Retrieval

OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression

1 code implementation12 Feb 2022 Chunyang Fu, Ge Li, Rui Song, Wei Gao, Shan Liu

In point cloud compression, sufficient contexts are significant for modeling the point cloud distribution.

Multimodal data matters: language model pre-training over structured and unstructured electronic health records

1 code implementation25 Jan 2022 Sicen Liu, Xiaolong Wang, Yongshuai Hou, Ge Li, Hui Wang, Hui Xu, Yang Xiang, Buzhou Tang

As two important textual modalities in electronic health records (EHR), both structured data (clinical codes) and unstructured data (clinical narratives) have recently been increasingly applied to the healthcare domain.

Decision Making Language Modelling +1

Contextual Debiasing for Visual Recognition With Causal Mechanisms

no code implementations CVPR 2022 Ruyang Liu, Hao liu, Ge Li, Haodi Hou, TingHao Yu, Tao Yang

As a common problem in the visual world, contextual bias means the recognition may depend on the co-occurrence context rather than the objects themselves, which is even more severe in multi-label tasks due to multiple targets and the absence of location.

Causal Inference Multi-Label Classification

Learning to Share in Multi-Agent Reinforcement Learning

2 code implementations16 Dec 2021 Yuxuan Yi, Ge Li, YaoWei Wang, Zongqing Lu

Inspired by the fact that sharing plays a key role in human's learning of cooperation, we propose LToS, a hierarchically decentralized MARL framework that enables agents to learn to dynamically share reward with neighbors so as to encourage agents to cooperate on the global objective through collectives.

Multi-agent Reinforcement Learning reinforcement-learning +1

Specializing Versatile Skill Libraries using Local Mixture of Experts

1 code implementation8 Dec 2021 Onur Celik, Dongzhuoran Zhou, Ge Li, Philipp Becker, Gerhard Neumann

This local and incremental learning results in a modular MoE model of high accuracy and versatility, where both properties can be scaled by adding more components on the fly.

Incremental Learning Reinforcement Learning (RL)

Precise Learning of Source Code Contextual Semantics via Hierarchical Dependence Structure and Graph Attention Networks

no code implementations20 Nov 2021 Zhehao Zhao, Bo Yang, Ge Li, Huai Liu, Zhi Jin

Based on that, we also designed a neural network that depends on the graph attention mechanism. Specifically, we introduced the syntactic structural of the basic block, i. e., its corresponding AST, in source code model to provide sufficient information and fill the gap.

Feature Engineering Graph Attention

Learning to Disentangle Scenes for Person Re-identification

1 code implementation10 Nov 2021 Xianghao Zang, Ge Li, Wei Gao, Xiujun Shu

In this way, the complex scenes in the ReID task are effectively disentangled, and the burden of each branch is relieved.

Person Re-Identification

Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives

no code implementations9 Nov 2021 Ziyi Liu, JiaQi Zhang, Yongshuai Hou, Xinran Zhang, Ge Li, Yang Xiang

Background: Electronic Health Records (EHRs) contain rich information of patients' health history, which usually include both structured and unstructured data.

BIG-bench Machine Learning

PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering

1 code implementation ICCV 2021 Yurui Ren, Ge Li, Yuanqi Chen, Thomas H. Li, Shan Liu

The proposed model can generate photo-realistic portrait images with accurate movements according to intuitive modifications.

Image Generation Neural Rendering

Power-Based Attacks on Spatial DNN Accelerators

no code implementations28 Aug 2021 Ge Li, Mohit Tiwari, Michael Orshansky

Spatial accelerators, that parallelize matrix/vector operations, are utilized for enhancing energy efficiency of DNN computation.

Model extraction

Combining Attention with Flow for Person Image Synthesis

no code implementations4 Aug 2021 Yurui Ren, Yubo Wu, Thomas H. Li, Shan Liu, Ge Li

Pose-guided person image synthesis aims to synthesize person images by transforming reference images into target poses.

Image Generation

Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark

1 code implementation31 May 2021 Xiujun Shu, Xiao Wang, Xianghao Zang, Shiliang Zhang, Yuanqi Chen, Ge Li, Qi Tian

We also verified that models pre-trained on LaST can generalize well on existing datasets with short-term and cloth-changing scenarios.

Person Re-Identification

Low Pass Filter for Anti-aliasing in Temporal Action Localization

no code implementations23 Apr 2021 Cece Jin, Yuanqi Chen, Ge Li, Tao Zhang, Thomas Li

This paper aims to verify the existence of aliasing in TAL methods and investigate utilizing low pass filters to solve this problem by inhibiting the high-frequency band.

Temporal Action Localization

SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains

1 code implementation10 Dec 2020 Yuanqi Chen, Ge Li, Cece Jin, Shan Liu, Thomas Li

This issue makes the generator lack the incentive from the discriminator to learn high-frequency content of data, resulting in a significant spectrum discrepancy between generated images and real images.

Learning to Represent Programs with Heterogeneous Graphs

no code implementations8 Dec 2020 Kechi Zhang, Wenhan Wang, Huangzhao Zhang, Ge Li, Zhi Jin

To address the information of node and edge types, we bring the idea of heterogeneous graphs to learning on source code and present a new formula of building heterogeneous program graphs from ASTs with additional type information for nodes and edges.

Code Comment Generation Comment Generation

Point Cloud Attribute Compression via Successive Subspace Graph Transform

no code implementations29 Oct 2020 Yueru Chen, Yiting shao, Jing Wang, Ge Li, C. -C. Jay Kuo

Inspired by the recently proposed successive subspace learning (SSL) principles, we develop a successive subspace graph transform (SSGT) to address point cloud attribute compression in this work.

Retrieve and Refine: Exemplar-based Neural Comment Generation

1 code implementation9 Oct 2020 Bolin Wei, Yongmin Li, Ge Li, Xin Xia, Zhi Jin

Inspired by the IR-based and template-based approaches, in this paper, we propose a neural comment generation approach where we use the existing comments of similar code snippets as exemplars to guide comment generation.

Code Comment Generation Comment Generation +4

Towards Full-line Code Completion with Neural Language Models

no code implementations18 Sep 2020 Wenhan Wang, Sijie Shen, Ge Li, Zhi Jin

In this paper, we take a further step and discuss the probability of directly completing a whole line of code instead of a single token.

Code Completion

A Technical Report for VIPriors Image Classification Challenge

no code implementations17 Jul 2020 Zhipeng Luo, Ge Li, Zhiguang Zhang

This paper is a brief report to our submission to the VIPriors Image Classification Challenge.

Classification Ensemble Learning +3

GID-Net: Detecting Human-Object Interaction with Global and Instance Dependency

no code implementations11 Mar 2020 Dongming Yang, Yuexian Zou, Jian Zhang, Ge Li

GID block breaks through the local neighborhoods and captures long-range dependency of pixels both in global-level and instance-level from the scene to help detecting interactions between instances.

Human-Object Interaction Detection

Deep Image Spatial Transformation for Person Image Generation

2 code implementations CVPR 2020 Yurui Ren, Xiaoming Yu, Junming Chen, Thomas H. Li, Ge Li

Finally, we warp the source features using a content-aware sampling method with the obtained local attention coefficients.

Image Generation

Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree

1 code implementation20 Feb 2020 Wenhan Wang, Ge Li, Bo Ma, Xin Xia, Zhi Jin

As far as we have concerned, we are the first to apply graph neural networks on the domain of code clone detection.

Clone Detection

NLocalSAT: Boosting Local Search with Solution Prediction

1 code implementation26 Jan 2020 Wenjie Zhang, Zeyu Sun, Qihao Zhu, Ge Li, Shaowei Cai, Yingfei Xiong, Lu Zhang

However, in this method, the initialization is assigned in a random manner, which impacts the effectiveness of SLS solvers.

C3DVQA: Full-Reference Video Quality Assessment with 3D Convolutional Neural Network

no code implementations30 Oct 2019 Munan Xu, Junming Chen, Haiqiang Wang, Shan Liu, Ge Li, Zhiqiang Bai

However, video quality exhibits different characteristics from static image quality due to the existence of temporal masking effects.

Video Quality Assessment Visual Question Answering (VQA)

Code Generation as a Dual Task of Code Summarization

2 code implementations NeurIPS 2019 Bolin Wei, Ge Li, Xin Xia, Zhiyi Fu, Zhi Jin

Code summarization (CS) and code generation (CG) are two crucial tasks in the field of automatic software development.

Code Generation Code Summarization +1

Multi-mapping Image-to-Image Translation via Learning Disentanglement

1 code implementation NeurIPS 2019 Xiaoming Yu, Yuanqi Chen, Thomas Li, Shan Liu, Ge Li

Recent advances of image-to-image translation focus on learning the one-to-many mapping from two aspects: multi-modal translation and multi-domain translation.

Disentanglement Image-to-Image Translation +1

A Self-Attentional Neural Architecture for Code Completion with Multi-Task Learning

no code implementations16 Sep 2019 Fang Liu, Ge Li, Bolin Wei, Xin Xia, Zhiyi Fu, Zhi Jin

To enable the knowledge sharing between related tasks, we creatively propose a Multi-Task Learning (MTL) framework to learn two related tasks in code completion jointly.

Code Completion Language Modelling +1

C-RPNs: Promoting Object Detection in real world via a Cascade Structure of Region Proposal Networks

no code implementations19 Aug 2019 Dongming Yang, Yuexian Zou, Jian Zhang, Ge Li

Although two-stage detectors like Faster R-CNN achieved big successes in object detection due to the strategy of extracting region proposals by region proposal network, they show their poor adaption in real-world object detection as a result of without considering mining hard samples during extracting region proposals.

object-detection Object Detection +1

ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network

1 code implementation28 Jun 2019 Zhangheng Li, Jia-Xing Zhong, Jingjia Huang, Tao Zhang, Thomas Li, Ge Li

In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks.

Deep AutoEncoder-based Lossy Geometry Compression for Point Clouds

no code implementations18 Apr 2019 Wei Yan, Yiting shao, Shan Liu, Thomas H. Li, Zhu Li, Ge Li

Point cloud is a fundamental 3D representation which is widely used in real world applications such as autonomous driving.

Autonomous Driving Image Compression

Bi-Skip: A Motion Deblurring Network Using Self-paced Learning

no code implementations24 Feb 2019 Yiwei Zhang, Chunbiao Zhu, Ge Li, Yuan Zhao, Haifeng Shen

A fast and effective motion deblurring method has great application values in real life.


A Grammar-Based Structural CNN Decoder for Code Generation

1 code implementation14 Nov 2018 Zeyu Sun, Qihao Zhu, Lili Mou, Yingfei Xiong, Ge Li, Lu Zhang

In this paper, we propose a grammar-based structural convolutional neural network (CNN) for code generation.

Code Generation Semantic Parsing

BLP -- Boundary Likelihood Pinpointing Networks for Accurate Temporal Action Localization

no code implementations6 Nov 2018 Weijie Kong, Nannan Li, Shan Liu, Thomas Li, Ge Li

Despite tremendous progress achieved in temporal action detection, state-of-the-art methods still suffer from the sharp performance deterioration when localizing the starting and ending temporal action boundaries.

Action Detection regression +1

SingleGAN: Image-to-Image Translation by a Single-Generator Network using Multiple Generative Adversarial Learning

1 code implementation11 Oct 2018 Xiaoming Yu, Xing Cai, Zhenqiang Ying, Thomas Li, Ge Li

Besides, we explore variants of SingleGAN for different tasks, including one-to-many domain translation, many-to-many domain translation and one-to-one domain translation with multimodality.

Image-to-Image Translation Translation

Mini-batch Serialization: CNN Training with Inter-layer Data Reuse

1 code implementation30 Sep 2018 Sangkug Lym, Armand Behroozi, Wei Wen, Ge Li, Yongkee Kwon, Mattan Erez

Training convolutional neural networks (CNNs) requires intense computations and high memory bandwidth.


no code implementations27 Sep 2018 Zhangheng Li, Jia-Xing Zhong, Jingjia Huang, Tao Zhang, Thomas Li, Ge Li

Processing sequential data with long term dependencies and learn complex transitions are two major challenges in many deep learning applications.

Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector

no code implementations9 Jul 2018 Jia-Xing Zhong, Nannan Li, Weijie Kong, Tao Zhang, Thomas H. Li, Ge Li

Weakly supervised temporal action detection is a Herculean task in understanding untrimmed videos, since no supervisory signal except the video-level category label is available on training data.

Action Detection Temporal Localization

Multi-Mapping Image-to-Image Translation with Central Biasing Normalization

no code implementations26 Jun 2018 Xiaoming Yu, Zhenqiang Ying, Thomas Li, Shan Liu, Ge Li

Recent advances in image-to-image translation have seen a rise in approaches generating diverse images through a single network.

Image-to-Image Translation Translation

Exploiting the Value of the Center-dark Channel Prior for Salient Object Detection

no code implementations14 May 2018 Chunbiao Zhu, Wen-Hao Zhang, Thomas H. Li, Ge Li

In this paper, we propose a novel salient object detection algorithm for RGB-D images using center-dark channel priors.

object-detection RGB Salient Object Detection +2

Deep Learning in Software Engineering

no code implementations13 May 2018 Xiaochen Li, He Jiang, Zhilei Ren, Ge Li, Jing-Xuan Zhang

To answer these questions, we conduct a bibliography analysis on 98 research papers in SE that use deep learning techniques.

Software Engineering

Hybrid Point Cloud Attribute Compression Using Slice-based Layered Structure and Block-based Intra Prediction

no code implementations28 Apr 2018 Yiting Shao, Qi Zhang, Ge Li, Zhu Li

In intra-frame compression of point cloud color attributes, results demonstrate that our method performs better than the state-of-the-art region-adaptive hierarchical transform (RAHT) system, and on average a 29. 37$\%$ BD-rate gain is achieved.


A multilayer backpropagation saliency detection algorithm and its applications

no code implementations26 Mar 2018 Chunbiao Zhu, Ge Li

In this paper, we propose a multilayer backpropagation saliency detection algorithm based on depth mining by which we exploit depth cue from three different layers of images.

Algorithm object-detection +2

A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement

no code implementations2 Nov 2017 Zhenqiang Ying, Ge Li, Wen Gao

Inspired by human visual system, we design a multi-exposure fusion framework for low-light image enhancement.

Low-Light Image Enhancement

Robust Saliency Detection via Fusing Foreground and Background Priors

no code implementations1 Nov 2017 Kan Huang, Chunbiao Zhu, Ge Li

Automatic Salient object detection has received tremendous attention from research community and has been an increasingly important tool in many computer vision tasks.

object-detection RGB Salient Object Detection +2

ORGB: Offset Correction in RGB Color Space for Illumination-Robust Image Processing

no code implementations3 Aug 2017 Zhenqiang Ying, Ge Li, Sixin Wen, Guozhen Tan

This paper is concerned with the detection and correction of the offset between the intersection and origin.

A Self-Adaptive Proposal Model for Temporal Action Detection based on Reinforcement Learning

1 code implementation22 Jun 2017 Jingjia Huang, Nannan Li, Tao Zhang, Ge Li

Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.

Action Detection Q-Learning +1

Compressing Neural Language Models by Sparse Word Representations

1 code implementation ACL 2016 Yunchuan Chen, Lili Mou, Yan Xu, Ge Li, Zhi Jin

Such approaches are time- and memory-intensive because of the large numbers of parameters for word embeddings and the output layer.

Language Modelling Word Embeddings

Searching Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking

no code implementations23 Aug 2016 Nannan Li, Dan Xu, Zhenqiang Ying, Zhihao LI, Ge Li

In this paper, we address the problem of searching action proposals in unconstrained video clips.

How Transferable are Neural Networks in NLP Applications?

no code implementations EMNLP 2016 Lili Mou, Zhao Meng, Rui Yan, Ge Li, Yan Xu, Lu Zhang, Zhi Jin

Transfer learning is aimed to make use of valuable knowledge in a source domain to help model performance in a target domain.

Transfer Learning

Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation

no code implementations COLING 2016 Yan Xu, Ran Jia, Lili Mou, Ge Li, Yunchuan Chen, Yangyang Lu, Zhi Jin

However, existing neural networks for relation classification are usually of shallow architectures (e. g., one-layer convolutional neural networks or recurrent networks).

Classification Data Augmentation +2

Backward and Forward Language Modeling for Constrained Sentence Generation

no code implementations21 Dec 2015 Lili Mou, Rui Yan, Ge Li, Lu Zhang, Zhi Jin

Provided a specific word, we use RNNs to generate previous words and future words, either simultaneously or asynchronously, resulting in two model variants.

Language Modelling Machine Translation +3

On End-to-End Program Generation from User Intention by Deep Neural Networks

no code implementations25 Oct 2015 Lili Mou, Rui Men, Ge Li, Lu Zhang, Zhi Jin

This paper envisions an end-to-end program generation scenario using recurrent neural networks (RNNs): Users can express their intention in natural language; an RNN then automatically generates corresponding code in a characterby-by-character fashion.

A Comparative Study on Regularization Strategies for Embedding-based Neural Networks

no code implementations EMNLP 2015 Hao Peng, Lili Mou, Ge Li, Yunchuan Chen, Yangyang Lu, Zhi Jin

This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP.

Distilling Word Embeddings: An Encoding Approach

no code implementations15 Jun 2015 Lili Mou, Ran Jia, Yan Xu, Ge Li, Lu Zhang, Zhi Jin

Distilling knowledge from a well-trained cumbersome network to a small one has recently become a new research topic, as lightweight neural networks with high performance are particularly in need in various resource-restricted systems.

Word Embeddings

Convolutional Neural Networks over Tree Structures for Programming Language Processing

7 code implementations18 Sep 2014 Lili Mou, Ge Li, Lu Zhang, Tao Wang, Zhi Jin

Programming language processing (similar to natural language processing) is a hot research topic in the field of software engineering; it has also aroused growing interest in the artificial intelligence community.

Building Program Vector Representations for Deep Learning

1 code implementation11 Sep 2014 Lili Mou, Ge Li, Yuxuan Liu, Hao Peng, Zhi Jin, Yan Xu, Lu Zhang

In this pioneering paper, we propose the "coding criterion" to build program vector representations, which are the premise of deep learning for program analysis.

Representation Learning

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