Search Results for author:
Found 105 papers, 46 papers with code
Enabling Programming Thinking in Large Language Models Toward Code Generation
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).
Self-Edit: Fault-Aware Code Editor for Code Generation
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.
Towards Enhancing In-Context Learning for Code Generation
In-context learning (ICL) with pre-trained language models (PTLMs) has shown great success in code generation.
Implant Global and Local Hierarchy Information to Sequence based Code Representation Models
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
We construct lattice PUF with a physically obfuscated key and an LWE decryption function block.
Causality Compensated Attention for Contextual Biased Visual Recognition
Visual attention does not always capture the essential object representation desired for robust predictions.
Ranked #1 on
Multi-Label Image Classification
on MSCOCO
Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring
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)
Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering
Recently, self-attention networks achieve impressive performance in point cloud segmentation due to their superiority in modeling long-range dependencies.
Efficient Hierarchical Entropy Model for Learned Point Cloud Compression
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
Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently.
CodePAD: Sequence-based Code Generation with Pushdown Automaton
CodePAD can leverage existing sequence-based models, and we show that it can achieve 100\% grammatical correctness percentage on these benchmark datasets.
Poison Attack and Defense on Deep Source Code Processing Models
The attackers aim to inject insidious backdoors into models by poisoning the training data with poison samples.
CodeEditor: Learning to Edit Source Code with Pre-trained Models
Pre-trained models are first pre-trained with pre-training tasks and fine-tuned with the code editing task.
Frequency-Aware Self-Supervised Monocular Depth Estimation
We present two versatile methods to generally enhance self-supervised monocular depth estimation (MDE) models.
ProDMPs: A Unified Perspective on Dynamic and Probabilistic Movement Primitives
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).
Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem
In this paper, we redesign the patch-based triplet loss in MDE to alleviate the ubiquitous edge-fattening issue.
Ranked #1 on
Unsupervised Monocular Depth Estimation
on Kitti Raw
Antecedent Predictions Are More Important Than You Think: An Effective Method for Tree-Based Code Generation
To evaluate the effectiveness of our proposed loss, we implement and train an Antecedent Prioritized Tree-based code generation model called APT.
Incorporating Domain Knowledge through Task Augmentation for Front-End JavaScript Code Generation
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.
Learning Program Representations with a Tree-Structured Transformer
Learning vector representations for programs is a critical step in applying deep learning techniques for program understanding tasks.
OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms
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.
Salient Object Detection for Point Clouds
This paper researches the unexplored task-point cloud salient object detection (SOD).
What does Transformer learn about source code?
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.
SKFlow: Learning Optical Flow with Super Kernels
In this paper, we propose the Super Kernel Flow Network (SKFlow), a CNN architecture to ameliorate the impacts of occlusions on optical flow estimation.
Nebula-I: A General Framework for Collaboratively Training Deep Learning Models on Low-Bandwidth Cloud Clusters
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
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
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.
Neural Texture Extraction and Distribution for Controllable Person Image Synthesis
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.
Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval
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.
OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression
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
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.
Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019
Code submissions were executed on hidden tasks, with limited time and computational resources, pushing solutions that get results quickly.
Contextual Debiasing for Visual Recognition With Causal Mechanisms
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.
Ranked #9 on
Multi-Label Classification
on MS-COCO
ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
A unified framework named ERNIE 3. 0 was recently proposed for pre-training large-scale knowledge enhanced models and trained a model with 10 billion parameters.
Learning to Share in Multi-Agent Reinforcement Learning
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
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.
Integrating Tree Path in Transformer for Code Representation
Learning distributed representation of source code requires modelling its syntax and semantics.
Precise Learning of Source Code Contextual Semantics via Hierarchical Dependence Structure and Graph Attention Networks
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.
Learning to Disentangle Scenes for Person Re-identification
In this way, the complex scenes in the ReID task are effectively disentangled, and the burden of each branch is relieved.
Ranked #2 on
Person Re-Identification
on P-DukeMTMC-reID
Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives
Background: Electronic Health Records (EHRs) contain rich information of patients' health history, which usually include both structured and unstructured data.
Exploiting Robust Unsupervised Video Person Re-identification
A local-aware module is employed to explore the poentials of local-level feature for unsupervised learning.
Ranked #1 on
Unsupervised Person Re-Identification
on PRID2011
Unsupervised Person Re-Identification
Video-Based Person Re-Identification
PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering
The proposed model can generate photo-realistic portrait images with accurate movements according to intuitive modifications.
Power-Based Attacks on Spatial DNN Accelerators
Spatial accelerators, that parallelize matrix/vector operations, are utilized for enhancing energy efficiency of DNN computation.
Combining Attention with Flow for Person Image Synthesis
Pose-guided person image synthesis aims to synthesize person images by transforming reference images into target poses.
Semantic-guided Pixel Sampling for Cloth-Changing Person Re-identification
The key to this task is to exploit cloth-irrelevant cues.
Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark
We also verified that models pre-trained on LaST can generalize well on existing datasets with short-term and cloth-changing scenarios.
Low Pass Filter for Anti-aliasing in Temporal Action Localization
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.
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Benchmark datasets have a significant impact on accelerating research in programming language tasks.
Ranked #1 on
Cloze Test
on CodeXGLUE - CT-maxmin
Structure-Transformed Texture-Enhanced Network for Person Image Synthesis
Pose-guided virtual try-on task aims to modify the fashion item based on pose transfer task.
SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains
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
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.
Point Cloud Attribute Compression via Successive Subspace Graph Transform
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
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.
Towards Full-line Code Completion with Neural Language Models
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.
Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation
We show that our framework can spatially transform the inputs in an efficient manner.
Toward Zero-Shot Unsupervised Image-to-Image Translation
Recent studies have shown remarkable success in unsupervised image-to-image translation.
A Technical Report for VIPriors Image Classification Challenge
This paper is a brief report to our submission to the VIPriors Image Classification Challenge.
GID-Net: Detecting Human-Object Interaction with Global and Instance Dependency
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.
Deep Image Spatial Transformation for Person Image Generation
Finally, we warp the source features using a content-aware sampling method with the obtained local attention coefficients.
Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree
As far as we have concerned, we are the first to apply graph neural networks on the domain of code clone detection.
NLocalSAT: Boosting Local Search with Solution Prediction
However, in this method, the initialization is assigned in a random manner, which impacts the effectiveness of SLS solvers.
RoIMix: Proposal-Fusion among Multiple Images for Underwater Object Detection
Generic object detection algorithms have proven their excellent performance in recent years.
C3DVQA: Full-Reference Video Quality Assessment with 3D Convolutional Neural Network
However, video quality exhibits different characteristics from static image quality due to the existence of temporal masking effects.
Code Generation as a Dual Task of Code Summarization
Code summarization (CS) and code generation (CG) are two crucial tasks in the field of automatic software development.
Multi-mapping Image-to-Image Translation via Learning Disentanglement
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.
A Self-Attentional Neural Architecture for Code Completion with Multi-Task Learning
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.
C-RPNs: Promoting Object Detection in real world via a Cascade Structure of Region Proposal Networks
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.
StructureFlow: Image Inpainting via Structure-aware Appearance Flow
Image inpainting techniques have shown significant improvements by using deep neural networks recently.
ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network
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
Point cloud is a fundamental 3D representation which is widely used in real world applications such as autonomous driving.
Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection
Remarkably, we obtain the frame-level AUC score of 82. 12% on UCF-Crime.
Anomaly Detection In Surveillance Videos
Multiple Instance Learning
+2
Bi-Skip: A Motion Deblurring Network Using Self-paced Learning
A fast and effective motion deblurring method has great application values in real life.
A Grammar-Based Structural CNN Decoder for Code Generation
In this paper, we propose a grammar-based structural convolutional neural network (CNN) for code generation.
BLP -- Boundary Likelihood Pinpointing Networks for Accurate Temporal Action Localization
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.
SingleGAN: Image-to-Image Translation by a Single-Generator Network using Multiple Generative Adversarial Learning
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.
Mini-batch Serialization: CNN Training with Inter-layer Data Reuse
Training convolutional neural networks (CNNs) requires intense computations and high memory bandwidth.
SEQUENCE MODELLING WITH AUTO-ADDRESSING AND RECURRENT MEMORY INTEGRATING NETWORKS
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
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.
Multi-Mapping Image-to-Image Translation with Central Biasing Normalization
Recent advances in image-to-image translation have seen a rise in approaches generating diverse images through a single network.
Exploiting the Value of the Center-dark Channel Prior for Salient Object Detection
In this paper, we propose a novel salient object detection algorithm for RGB-D images using center-dark channel priors.
Deep Learning in Software Engineering
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
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.
Multimedia
A multilayer backpropagation saliency detection algorithm and its applications
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.
PDNet: Prior-model Guided Depth-enhanced Network for Salient Object Detection
One is the lack of tremendous amount of annotated data to train a network.
Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
This paper addresses the question: Why do neural dialog systems generate short and meaningless replies?
A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement
Inspired by human visual system, we design a multi-exposure fusion framework for low-light image enhancement.
Robust Saliency Detection via Fusing Foreground and Background Priors
Automatic Salient object detection has received tremendous attention from research community and has been an increasingly important tool in many computer vision tasks.
Automatic Salient Object Detection for Panoramic Images Using Region Growing and Fixation Prediction Model
In this paper, we propose a novel bottom-up salient object detection framework for panoramic images.
ORGB: Offset Correction in RGB Color Space for Illumination-Robust Image Processing
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
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.
Compressing Neural Language Models by Sparse Word Representations
Such approaches are time- and memory-intensive because of the large numbers of parameters for word embeddings and the output layer.
Improved Knowledge Base Completion by Path-Augmented TransR Model
Knowledge base completion aims to infer new relations from existing information.
Searching Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking
In this paper, we address the problem of searching action proposals in unconstrained video clips.
Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation
Using neural networks to generate replies in human-computer dialogue systems is attracting increasing attention over the past few years.
How Transferable are Neural Networks in NLP Applications?
Transfer learning is aimed to make use of valuable knowledge in a source domain to help model performance in a target domain.
Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation
However, existing neural networks for relation classification are usually of shallow architectures (e. g., one-layer convolutional neural networks or recurrent networks).
Ranked #2 on
Relation Classification
on SemEval 2010 Task 8
Natural Language Inference by Tree-Based Convolution and Heuristic Matching
In this paper, we propose the TBCNN-pair model to recognize entailment and contradiction between two sentences.
Ranked #88 on
Natural Language Inference
on SNLI
Backward and Forward Language Modeling for Constrained Sentence Generation
Provided a specific word, we use RNNs to generate previous words and future words, either simultaneously or asynchronously, resulting in two model variants.
On End-to-End Program Generation from User Intention by Deep Neural Networks
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
This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP.
Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Path
Relation classification is an important research arena in the field of natural language processing (NLP).
Ranked #4 on
Relation Classification
on SemEval 2010 Task 8
Distilling Word Embeddings: An Encoding Approach
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.
Discriminative Neural Sentence Modeling by Tree-Based Convolution
This paper proposes a tree-based convolutional neural network (TBCNN) for discriminative sentence modeling.
Ranked #6 on
Text Classification
on TREC-6
Convolutional Neural Networks over Tree Structures for Programming Language Processing
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
In this pioneering paper, we propose the "coding criterion" to build program vector representations, which are the premise of deep learning for program analysis.
