Search Results for author:
Found 83 papers, 23 papers with code
Learning Progressive Joint Propagation for Human Motion Prediction
Last, in order to incorporate a general motion space for high-quality prediction, we build a memory-based dictionary, which aims to preserve the global motion patterns in training data to guide the predictions.
Deep Transferring Quantization
Specifically, we propose a method named deep transferring quantization (DTQ) to effectively exploit the knowledge in a pre-trained full-precision model.
Exploiting Spatial-Temporal Semantic Consistency for Video Scene Parsing
Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction.
PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval
Recently, dense passage retrieval has become a mainstream approach to finding relevant information in various natural language processing tasks.
Elastic Architecture Search for Diverse Tasks with Different Resources
To this end, we first propose to effectively train the over-parameterized network via a task dropout strategy to disentangle the tasks during training.
DuReader\_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications
Machine reading comprehension (MRC) is a crucial task in natural language processing and has achieved remarkable advancements.
Resisting Out-of-Distribution Data Problem in Perturbation of XAI
Besides, our solution also resolves a fundamental problem with the faithfulness indicator, a commonly used evaluation metric of XAI algorithms that appears to be sensitive to the OoD issue.
HANet: Hierarchical Alignment Networks for Video-Text Retrieval
Based on these, we naturally construct hierarchical representations in the individual-local-global manner, where the individual level focuses on the alignment between frame and word, local level focuses on the alignment between video clip and textual context, and global level focuses on the alignment between the whole video and text.
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation
In this paper, we propose an Omni-perception Pre-Trainer (OPT) for cross-modal understanding and generation, by jointly modeling visual, text and audio resources.
Tensor networks for unsupervised machine learning
Modeling the joint distribution of high-dimensional data is a central task in unsupervised machine learning.
Exploiting Large-scale Teacher-Student Training for On-device Acoustic Models
We present results from Alexa speech teams on semi-supervised learning (SSL) of acoustic models (AM) with experiments spanning over 3000 hours of GPU time, making our study one of the largest of its kind.
Measuring Conversational Uptake: A Case Study on Student-Teacher Interactions
In conversation, uptake happens when a speaker builds on the contribution of their interlocutor by, for example, acknowledging, repeating or reformulating what they have said.
Large-Scale Data-Driven Airline Market Influence Maximization
On top of the prediction models, we define a budget-constrained flight frequency optimization problem to maximize the market influence over 2, 262 routes.
Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information
Many deep learning based video compression artifact removal algorithms have been proposed to recover high-quality videos from low-quality compressed videos.
Less is More: Pay Less Attention in Vision Transformers
Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision.
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
AAformer: Auto-Aligned Transformer for Person Re-Identification
In this paper, we introduce an alignment scheme in Transformer architecture for the first time and propose the Auto-Aligned Transformer (AAformer) to automatically locate both the human parts and non-human ones at patch-level.
Scalable Vision Transformers with Hierarchical Pooling
However, the routine of the current ViT model is to maintain a full-length patch sequence during inference, which is redundant and lacks hierarchical representation.
Ranked #346 on
Image Classification
on ImageNet
Temporal Memory Attention for Video Semantic Segmentation
Video semantic segmentation requires to utilize the complex temporal relations between frames of the video sequence.
Ranked #1 on
Video Semantic Segmentation
on Cityscapes val
CPTR: Full Transformer Network for Image Captioning
Besides, we provide detailed visualizations of the self-attention between patches in the encoder and the "words-to-patches" attention in the decoder thanks to the full Transformer architecture.
Global-Local Propagation Network for RGB-D Semantic Segmentation
Depth information matters in RGB-D semantic segmentation task for providing additional geometric information to color images.
Fast Sequence Generation with Multi-Agent Reinforcement Learning
These models are autoregressive in that they generate each word by conditioning on previously generated words, which leads to heavy latency during inference.
LBS: Loss-aware Bit Sharing for Automatic Model Compression
Low-bitwidth model compression is an effective method to reduce the model size and computational overhead.
Magnetic field and gravitational waves from the first-order Phase Transition
We perform the three dimensional lattice simulation of the magnetic field and gravitational wave productions from bubble collisions during the first-order electroweak phase transition.
Cosmology and Nongalactic Astrophysics High Energy Physics - Lattice High Energy Physics - Phenomenology
AutoCaption: Image Captioning with Neural Architecture Search
In particular, RNN is equivalent to a subset of our search space.
DS-Net: Dynamic Spatiotemporal Network for Video Salient Object Detection
In this paper, we investigate the complimentary roles of spatial and temporal information and propose a novel dynamic spatiotemporal network (DS-Net) for more effective fusion of spatiotemporal information.
RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
In open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers.
Ranked #2 on
Passage Retrieval
on Natural Questions
Conditional Automated Channel Pruning for Deep Neural Networks
To address this issue, given a target compression rate for the whole model, one can search for the optimal compression rate for each layer.
Robust Mean Estimation in High Dimensions via $\ell_0$ Minimization
We study the robust mean estimation problem in high dimensions, where $\alpha <0. 5$ fraction of the data points can be arbitrarily corrupted.
Scene Segmentation with Dual Relation-aware Attention Network
We conduct extensive experiments to validate the effectiveness of our network and achieve new state-of-the-art segmentation performance on four challenging scene segmentation data sets, i. e., Cityscapes, ADE20K, PASCAL Context, and COCO Stuff data sets.
Ranked #3 on
Semantic Segmentation
on COCO-Stuff test
AQD: Towards Accurate Quantized Object Detection
Network quantization allows inference to be conducted using low-precision arithmetic for improved inference efficiency of deep neural networks on edge devices.
Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision
Violence detection has been studied in computer vision for years.
NROWAN-DQN: A Stable Noisy Network with Noise Reduction and Online Weight Adjustment for Exploration
Effective exploration for noisy networks is one of the most important issues in deep reinforcement learning.
Non-Autoregressive Image Captioning with Counterfactuals-Critical Multi-Agent Learning
In this paper, we propose a Non-Autoregressive Image Captioning (NAIC) model with a novel training paradigm: Counterfactuals-critical Multi-Agent Learning (CMAL).
NTIRE 2020 Challenge on NonHomogeneous Dehazing
We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset consisting of 55 pairs of real haze free and nonhomogeneous hazy images recorded outdoor.
NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results
For track 2, some existing methods are evaluated, showing promising solutions to the weakly-supervised video quality mapping problem.
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications
Machine reading comprehension (MRC) is a crucial task in natural language processing and has achieved remarkable advancements.
Gumbel-softmax-based Optimization: A Simple General Framework for Optimization Problems on Graphs
In computer science, there exist a large number of optimization problems defined on graphs, that is to find a best node state configuration or a network structure such that the designed objective function is optimized under some constraints.
Normalized and Geometry-Aware Self-Attention Network for Image Captioning
First, we propose Normalized Self-Attention (NSA), a reparameterization of SA that brings the benefits of normalization inside SA.
Minor Constraint Disturbances for Deep Semi-supervised Learning
The semi-supervised strategy based on the KL divergence of the MCD significantly reduces the reliance on the labels and improves the stability of the semi-supervised feature learning in high-dimensional space simultaneously.
Generative Low-bitwidth Data Free Quantization
More critically, our method achieves much higher accuracy on 4-bit quantization than the existing data free quantization method.
Learn to Generate Time Series Conditioned Graphs with Generative Adversarial Nets
Differently, in this paper, we are interested in a novel problem named Time Series Conditioned Graph Generation: given an input multivariate time series, we aim to infer a target relation graph modeling the underlying interrelationships between time series with each node corresponding to each time series.
Discrimination-aware Network Pruning for Deep Model Compression
In this paper, we propose a simple-yet-effective method called discrimination-aware channel pruning (DCP) to choose the channels that actually contribute to the discriminative power.
Semantic-Aware Label Placement for Augmented Reality in Street View
Our solution encodes the constraints for placing labels in an optimization problem to obtain the final label layout, and the labels will be placed in appropriate positions to reduce the chances of overlaying important real-world objects in street view AR scenarios.
CoKE: Contextualized Knowledge Graph Embedding
This work presents Contextualized Knowledge Graph Embedding (CoKE), a novel paradigm that takes into account such contextual nature, and learns dynamic, flexible, and fully contextualized entity and relation embeddings.
Adaptive Context Network for Scene Parsing
Recent works attempt to improve scene parsing performance by exploring different levels of contexts, and typically train a well-designed convolutional network to exploit useful contexts across all pixels equally.
Ranked #29 on
Semantic Segmentation
on ADE20K val
D-NET: A Pre-Training and Fine-Tuning Framework for Improving the Generalization of Machine Reading Comprehension
In this paper, we introduce a simple system Baidu submitted for MRQA (Machine Reading for Question Answering) 2019 Shared Task that focused on generalization of machine reading comprehension (MRC) models.
Flash X-ray diffraction imaging in 3D: a proposed analysis pipeline
Modern Flash X-ray diffraction Imaging (FXI) acquires diffraction signals from single biomolecules at a high repetition rate from X-ray Free Electron Lasers (XFELs), easily obtaining millions of 2D diffraction patterns from a single experiment.
Vatex Video Captioning Challenge 2020: Multi-View Features and Hybrid Reward Strategies for Video Captioning
This report describes our solution for the VATEX Captioning Challenge 2020, which requires generating descriptions for the videos in both English and Chinese languages.
Gumbel-softmax Optimization: A Simple General Framework for Combinatorial Optimization Problems on Graphs
Many problems in real life can be converted to combinatorial optimization problems (COPs) on graphs, that is to find a best node state configuration or a network structure such that the designed objective function is optimized under some constraints.
Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations
Furthermore, we propose a second progressive quantization scheme which gradually decreases the bit-width from high-precision to low-precision during training.
Aligning Linguistic Words and Visual Semantic Units for Image Captioning
Image captioning attempts to generate a sentence composed of several linguistic words, which are used to describe objects, attributes, and interactions in an image, denoted as visual semantic units in this paper.
Quantum Fisher information matrix and multiparameter estimation
Quantum Fisher information matrix (QFIM) is a core concept in theoretical quantum metrology due to the significant importance of quantum Cram\'{e}r-Rao bound in quantum parameter estimation.
Quantum Physics
Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension
In this work, we investigate the potential of leveraging external knowledge bases (KBs) to further improve BERT for MRC.
UCRDNet: Unsupervised Collaborative Representation Deep Network for Clustering
Furthermore, the proposed UCRDNet shows more excellent collaborative representation capabilities than the CDL deep collaborative networks for unsupervised clustering.
Solving Large-Scale 0-1 Knapsack Problems and its Application to Point Cloud Resampling
0-1 knapsack is of fundamental importance in computer science, business, operations research, etc.
Towards Time-Aware Distant Supervision for Relation Extraction
Time-DS is composed of a time series instance-popularity and two strategies.
A General Deep Learning Framework for Network Reconstruction and Dynamics Learning
We exhibit the universality of our framework on different kinds of time-series data: with the same structure, our model can be trained to accurately recover the network structure and predict future states on continuous, discrete, and binary dynamics, and outperforms competing network reconstruction methods.
Unsupervised Feature Learning Architecture with Multi-clustering Integration RBM
In this paper, we present a novel unsupervised feature learning architecture, which consists of a multi-clustering integration module and a variant of RBM termed multi-clustering integration RBM (MIRBM).
Discrimination-aware Channel Pruning for Deep Neural Networks
Channel pruning is one of the predominant approaches for deep model compression.
Supervised Classification Methods for Flash X-ray single particle diffraction Imaging
It is also straightforward to parallelize them so as to fully match the XFEL repetition rate, thereby enabling processing at site.
Aggregated Semantic Matching for Short Text Entity Linking
The task of entity linking aims to identify concepts mentioned in a text fragments and link them to a reference knowledge base.
Answer-focused and Position-aware Neural Question Generation
(2) The model copies the context words that are far from and irrelevant to the answer, instead of the words that are close and relevant to the answer.
Dual Attention Network for Scene Segmentation
Specifically, we append two types of attention modules on top of traditional dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respectively.
Ranked #7 on
Semantic Segmentation
on COCO-Stuff test
Neural Math Word Problem Solver with Reinforcement Learning
Experimental results show that (1) The copy and alignment mechanism is effective to address the two issues; (2) Reinforcement learning leads to better performance than maximum likelihood on this task; (3) Our neural model is complementary to the feature-based model and their combination significantly outperforms the state-of-the-art results.
Adaptations of ROUGE and BLEU to Better Evaluate Machine Reading Comprehension Task
Current evaluation metrics to question answering based machine reading comprehension (MRC) systems generally focus on the lexical overlap between the candidate and reference answers, such as ROUGE and BLEU.
Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification
Machine reading comprehension (MRC) on real web data usually requires the machine to answer a question by analyzing multiple passages retrieved by search engine.
Ranked #3 on
Question Answering
on MS MARCO
DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
Experiments show that human performance is well above current state-of-the-art baseline systems, leaving plenty of room for the community to make improvements.
A Statistical Framework for Product Description Generation
We present in this paper a statistical framework that generates accurate and fluent product description from product attributes.
Stacked Deconvolutional Network for Semantic Segmentation
In SDN, multiple shallow deconvolutional networks, which are called as SDN units, are stacked one by one to integrate contextual information and guarantee the fine recovery of localization information.
Ranked #11 on
Semantic Segmentation
on PASCAL VOC 2012 test
Long-term Blood Pressure Prediction with Deep Recurrent Neural Networks
Existing methods for arterial blood pressure (BP) estimation directly map the input physiological signals to output BP values without explicitly modeling the underlying temporal dependencies in BP dynamics.
Ranked #1 on
Blood pressure estimation
on MIMIC-III
A-Lamp: Adaptive Layout-Aware Multi-Patch Deep Convolutional Neural Network for Photo Aesthetic Assessment
However, the performance of these deep CNN methods is often compromised by the constraint that the neural network only takes the fixed-size input.
Ranked #2 on
Aesthetics Quality Assessment
on AVA
Assessing Uncertainties in X-ray Single-particle Three-dimensional reconstructions
These two-dimensional diffraction patterns can be practically reconstructed and retrieved down to a resolution of a few \angstrom.
Machine learning for ultrafast X-ray diffraction patterns on large-scale GPU clusters
With the expected enormous amount of diffraction data to be produced in the foreseeable future, this is the required scale to approach real time processing of data at the beam site.
Weakly-Supervised Dual Clustering for Image Semantic Segmentation
In this paper, we propose a novel Weakly-Supervised Dual Clustering (WSDC) approach for image semantic segmentation with image-level labels, i. e., collaboratively performing image segmentation and tag alignment with those regions.