Search Results for author:
Found 243 papers, 89 papers with code
A Copy-Augmented Generative Model for Open-Domain Question Answering
Open-domain question answering is a challenging task with a wide variety of practical applications.
Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text
Recently, Transformer-based text detection techniques have sought to predict polygons by encoding the coordinates of individual boundary vertices using distinct query features.
Leveraging the Power of Data Augmentation for Transformer-based Tracking
Due to long-distance correlation and powerful pretrained models, transformer-based methods have initiated a breakthrough in visual object tracking performance.
BERT4CTR: An Efficient Framework to Combine Pre-trained Language Model with Non-textual Features for CTR Prediction
Although deep pre-trained language models have shown promising benefit in a large set of industrial scenarios, including Click-Through-Rate (CTR) prediction, how to integrate pre-trained language models that handle only textual signals into a prediction pipeline with non-textual features is challenging.
Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking
The Bridge Module incorporates the high-level information of deep features into the shallow large-resolution features.
Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking
Furthermore, our method shows strong generalization for diverse trackers and scenarios in a plug-and-play and training-free manner.
Tracking Anything in High Quality
To further improve the quality of tracking masks, a pretrained MR model is employed to refine the tracking results.
Ranked #4 on
Semi-Supervised Video Object Segmentation
on YouTube-VOS 2019
(using extra training data)
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+2
Topology-Preserving Automatic Labeling of Coronary Arteries via Anatomy-aware Connection Classifier
Automatic labeling of coronary arteries is an essential task in the practical diagnosis process of cardiovascular diseases.
Cross-Element Combinatorial Selection for Multi-Element Creative in Display Advertising
The effectiveness of ad creatives is greatly influenced by their visual appearance.
A Collaborative Transfer Learning Framework for Cross-domain Recommendation
The disadvantage of the former is that the data from other domains is not utilized by a single domain model, while the latter leverage all the data from different domains, but the fine-tuned model of transfer learning may trap the model in a local optimum of the source domain, making it difficult to fit the target domain.
HSR-Diff:Hyperspectral Image Super-Resolution via Conditional Diffusion Models
Despite the proven significance of hyperspectral images (HSIs) in performing various computer vision tasks, its potential is adversely affected by the low-resolution (LR) property in the spatial domain, resulting from multiple physical factors.
Boosting Breast Ultrasound Video Classification by the Guidance of Keyframe Feature Centers
The coherence loss uses the feature centers generated by the static images to guide the frame attention in the video model.
Graph Based Long-Term And Short-Term Interest Model for Click-Through Rate Prediction
It consists of a multi-interest graph structure for capturing long-term user behavior, a multi-scenario heterogeneous sequence model for modeling short-term information, then an adaptive fusion mechanism to fused information from long-term and short-term behaviors.
Safe Offline Reinforcement Learning with Real-Time Budget Constraints
Aiming at promoting the safe real-world deployment of Reinforcement Learning (RL), research on safe RL has made significant progress in recent years.
Mining Negative Temporal Contexts For False Positive Suppression In Real-Time Ultrasound Lesion Detection
To address this issue, we propose to extract contexts from previous frames, including NTC, with the guidance of inverse optical flow.
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
Specifically, we propose Multi-Task Diffusion Model (\textsc{MTDiff}), a diffusion-based method that incorporates Transformer backbones and prompt learning for generative planning and data synthesis in multi-task offline settings.
Cross-Domain Policy Adaptation via Value-Guided Data Filtering
Specifically, we present the Value-Guided Data Filtering (VGDF) algorithm, which selectively shares transitions from the source domain based on the proximity of paired value targets across the two domains.
Spot keywords from very noisy and mixed speech
We propose a novel Mix Training (MT) strategy that encourages the model to discover low-energy keywords from noisy and mixed speech.
Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning
With emerging online topics as a source for numerous new events, detecting unseen / rare event types presents an elusive challenge for existing event detection methods, where only limited data access is provided for training.
CN-Celeb-AV: A Multi-Genre Audio-Visual Dataset for Person Recognition
A comprehensive study was conducted to compare CN-Celeb-AV with two popular public AVPR benchmark datasets, and the results demonstrated that CN-Celeb-AV is more in line with real-world scenarios and can be regarded as a new benchmark dataset for AVPR research.
Ordered and Binary Speaker Embedding
Modern speaker recognition systems represent utterances by embedding vectors.
Neural Image Re-Exposure
In this work, we aim to re-expose the captured photo in post-processing to provide a more flexible way of addressing those issues within a unified framework.
Ranked #4 on
Deblurring
on GoPro
(using extra training data)
MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta Learning
As such, MetaAdapt can learn how to adapt the misinformation detection model and exploit the source data for improved performance in the target domain.
Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks
First, to benchmark attack naturalness, we contribute the first Physical Attack Naturalness (PAN) dataset with human rating and gaze.
Representing Input Transformations by Low-Dimensional Parameter Subspaces
Deep models lack robustness to simple input transformations such as rotation, scaling, and translation, unless they feature a particular invariant architecture or undergo specific training, e. g., learning the desired robustness from data augmentations.
SeqTrack: Sequence to Sequence Learning for Visual Object Tracking
In this paper, we present a new sequence-to-sequence learning framework for visual tracking, dubbed SeqTrack.
Ranked #2 on
Visual Object Tracking
on TNL2K
Label-free timing analysis of SiPM-based modularized detectors with physics-constrained deep learning
We mathematically demonstrate the existence of the optimal function desired by the method, and give a systematic algorithm for training and calibration of the model.
MDDL: A Framework for Reinforcement Learning-based Position Allocation in Multi-Channel Feed
There are two types of data employed to train reinforcement learning (RL) model for position allocation, named strategy data and random data.
Wild Face Anti-Spoofing Challenge 2023: Benchmark and Results
Leveraging the WFAS dataset and Protocol 1 (Known-Type), we host the Wild Face Anti-Spoofing Challenge at the CVPR2023 workshop.
One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field
Talking head generation aims to generate faces that maintain the identity information of the source image and imitate the motion of the driving image.
Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement
The popularity of Contrastive Language-Image Pre-training (CLIP) has propelled its application to diverse downstream vision tasks.
Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction
This paper addresses the problem of rolling shutter correction in complex nonlinear and dynamic scenes with extreme occlusion.
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
In this paper, we propose ViewRefer, a multi-view framework for 3D visual grounding exploring how to grasp the view knowledge from both text and 3D modalities.
Propagate And Calibrate: Real-time Passive Non-line-of-sight Tracking
In contrast, we propose a purely passive method to track a person walking in an invisible room by only observing a relay wall, which is more in line with real application scenarios, e. g., security.
Visual Prompt Multi-Modal Tracking
To inherit the powerful representations of the foundation model, a natural modus operandi for multi-modal tracking is full fine-tuning on the RGB-based parameters.
Fully Self-Supervised Depth Estimation from Defocus Clue
We show that our framework circumvents the needs for the depth and AIF image ground-truth, and receives superior predictions, thus closing the gap between the theoretical success of DFD works and their applications in the real world.
Dual Memory Aggregation Network for Event-Based Object Detection with Learnable Representation
To fully exploit information with event streams to detect objects, a dual-memory aggregation network (DMANet) is proposed to leverage both long and short memory along event streams to aggregate effective information for object detection.
Universal Instance Perception as Object Discovery and Retrieval
All instance perception tasks aim at finding certain objects specified by some queries such as category names, language expressions, and target annotations, but this complete field has been split into multiple independent subtasks.
Generalized Referring Expression Comprehension
Multi-Object Tracking and Segmentation
+14
PIER: Permutation-Level Interest-Based End-to-End Re-ranking Framework in E-commerce
Then we design a novel omnidirectional attention mechanism in OCPM to capture the context information in the permutation.
A Deep Behavior Path Matching Network for Click-Through Rate Prediction
User behaviors on an e-commerce app not only contain different kinds of feedback on items but also sometimes imply the cognitive clue of the user's decision-making.
Decision-Making Context Interaction Network for Click-Through Rate Prediction
Click-through rate (CTR) prediction is crucial in recommendation and online advertising systems.
Representation Learning for Visual Object Tracking by Masked Appearance Transfer
However, for the template, we make the decoder reconstruct the target appearance within the search region.
Direct Heterogeneous Causal Learning for Resource Allocation Problems in Marketing
Our key intuition is that we introduce the decision factor to establish a bridge between ML and OR such that the solution can be directly obtained in OR by only performing the sorting or comparison operations on the decision factor.
Wasserstein Archetypal Analysis
We prove a consistency result for the regularized problem, ensuring that if the data are iid samples from a probability measure, then as the number of samples is increased, a subsequence of the archetype points converges to the archetype points for the limiting data distribution, almost surely.
QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation
Unlike existing approaches, we generate pseudo labels and propose to train the model via a novel attention-based contrastive adaptation method.
Unsupervised Domain Adaptation for COVID-19 Information Service with Contrastive Adversarial Domain Mixup
Moreover, we leverage the power of domain adversarial examples to establish an intermediate domain mixup, where the latent representations of the input text from both domains could be mixed during the training process.
On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks
In many applications with real-world consequences, it is crucial to develop reliable uncertainty estimation for the predictions made by the AI decision systems.
Multiscale Latent-Guided Entropy Model for LiDAR Point Cloud Compression
Besides, we propose a residual coding framework for the compression of the latent variable, which explores the spatial correlation of each layer by progressive downsampling, and model the corresponding residual with a fully-factorized entropy model.
PointScatter: Point Set Representation for Tubular Structure Extraction
Inspired by this, we propose PointScatter, an alternative to the segmentation models for the tubular structure extraction task.
Check and Link: Pairwise Lesion Correspondence Guides Mammogram Mass Detection
In mammogram mass detection, modeling pairwise lesion correspondence explicitly is particularly important.
Domain Adaptation for Question Answering via Question Classification
In this work, we investigate the potential benefits of question classification for QA domain adaptation.
TFN: An Interpretable Neural Network with Time-Frequency Transform Embedded for Intelligent Fault Diagnosis
However, the CNN is a typical black-box model, and the mechanism of CNN's decision-making are not clear, which limits its application in high-reliability-required fault diagnosis scenarios.
Contrastive Domain Adaptation for Early Misinformation Detection: A Case Study on COVID-19
However, early misinformation often demonstrates both conditional and label shifts against existing misinformation data (e. g., class imbalance in COVID-19 datasets), rendering such methods less effective for detecting early misinformation.
Task Aligned Meta-learning based Augmented Graph for Cold-Start Recommendation
In this paper, we propose a Task aligned Meta-learning based Augmented Graph (TMAG) to address cold-start recommendation.
Defending Substitution-Based Profile Pollution Attacks on Sequential Recommenders
Additionally, we design an adversarial training method tailored for sequential recommender systems.
Towards Grand Unification of Object Tracking
We present a unified method, termed Unicorn, that can simultaneously solve four tracking problems (SOT, MOT, VOS, MOTS) with a single network using the same model parameters.
Multi-Object Tracking
Multi-Object Tracking and Segmentation
+2
SRRT: Search Region Regulation Tracking
Trackers tend to lose the target object due to the limited search region or be interfered with by distractors due to the excessive search region.
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
By fine-tuning on downstream tasks, Point-M2AE achieves 86. 43% accuracy on ScanObjectNN, +3. 36% to the second-best, and largely benefits the few-shot classification, part segmentation and 3D object detection with the hierarchical pre-training scheme.
Ranked #3 on
3D Point Cloud Linear Classification
on ModelNet40
(using extra training data)
Vision-based Anti-UAV Detection and Tracking
It contains a detection dataset with a total of 10, 000 images and a tracking dataset with 20 videos that include short-term and long-term sequences.
NMA: Neural Multi-slot Auctions with Externalities for Online Advertising
Although VCG-based multi-slot auctions (e. g., VCG, WVCG) make it theoretically possible to model global externalities (e. g., the order and positions of ads and so on), they lack an efficient balance of both revenue and social welfare.
D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction
This paper proposes a novel 3D sparse convolution-based Deep Dynamic Point Cloud Compression (D-DPCC) network to compensate and compress the DPC geometry with 3D motion estimation and motion compensation in the feature space.
Evolving Programmable Computational Metamaterials
Granular metamaterials are a promising choice for the realization of mechanical computing devices.
Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline
With the popularity of multi-modal sensors, visible-thermal (RGB-T) object tracking is to achieve robust performance and wider application scenarios with the guidance of objects' temperature information.
Hybrid Transfer in Deep Reinforcement Learning for Ads Allocation
Ads allocation, which involves allocating ads and organic items to limited slots in feed with the purpose of maximizing platform revenue, has become a research hotspot.
Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks
With the recent prevalence of reinforcement learning (RL), there have been tremendous interests in utilizing RL for ads allocation in recommendation platforms (e. g., e-commerce and news feed sites).
Deep Page-Level Interest Network in Reinforcement Learning for Ads Allocation
A mixed list of ads and organic items is usually displayed in feed and how to allocate the limited slots to maximize the overall revenue is a key problem.
Efficient Localness Transformer for Smart Sensor-Based Energy Disaggregation
Modern smart sensor-based energy management systems leverage non-intrusive load monitoring (NILM) to predict and optimize appliance load distribution in real-time.
Balanced Multimodal Learning via On-the-fly Gradient Modulation
Multimodal learning helps to comprehensively understand the world, by integrating different senses.
Efficient Visual Tracking via Hierarchical Cross-Attention Transformer
Most state-of-the-art trackers are satisfied with the real-time speed on powerful GPUs.
High-Performance Transformer Tracking
First, we present a transformer tracking (named TransT) method based on the Siamese-like feature extraction backbone, the designed attention-based fusion mechanism, and the classification and regression head.
Neural Topic Modeling with Deep Mutual Information Estimation
NTM-DMIE is a neural network method for topic learning which maximizes the mutual information between the input documents and their latent topic representation.
Rényi State Entropy for Exploration Acceleration in Reinforcement Learning
One of the most critical challenges in deep reinforcement learning is to maintain the long-term exploration capability of the agent.
Show, Deconfound and Tell: Image Captioning With Causal Inference
In the encoding stage, the IOD is able to disentangle the region-based visual features by deconfounding the visual confounder.
MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation
Very often, the pose is estimated after the face detection.
Real Additive Margin Softmax for Speaker Verification
The additive margin softmax (AM-Softmax) loss has delivered remarkable performance in speaker verification.
CycleFlow: Purify Information Factors by Cycle Loss
SpeechFlow is a powerful factorization model based on information bottleneck (IB), and its effectiveness has been reported by several studies.
Speech-MLP: a simple MLP architecture for speech processing
Overparameterized transformer-based architectures have shown remarkable performance in recent years, achieving state-of-the-art results in speech processing tasks such as speech recognition, speech synthesis, keyword spotting, and speech enhancement et al.
Generating High-Fidelity Privacy-Conscious Synthetic Patient Data for Causal Effect Estimation with Multiple Treatments
Validation of these models, however, has been a challenge because the ground truth is unknown: only one treatment-outcome pair for each person can be observed.
Extracting Attentive Social Temporal Excitation for Sequential Recommendation
In this paper, we propose a novel time-aware sequential recommendation framework called Social Temporal Excitation Networks (STEN), which introduces temporal point processes to model the fine-grained impact of friends' behaviors on the user s dynamic interests in an event-level direct paradigm.
ICPE: An Item Cluster-Wise Pareto-Efficient Framework for Recommendation Debiasing
In detail, we define our item cluster-wise optimization target as the recommender model should balance all item clusters that differ in popularity, thus we set the model learning on each item cluster as a unique optimization objective.
DemiNet: Dependency-Aware Multi-Interest Network with Self-Supervised Graph Learning for Click-Through Rate Prediction
In this paper, we propose a novel model named DemiNet (short for DEpendency-Aware Multi-Interest Network}) to address the above two issues.
Cross DQN: Cross Deep Q Network for Ads Allocation in Feed
Our model results in higher revenue and better user experience than state-of-the-art baselines in offline experiments.
TPRM: A Topic-based Personalized Ranking Model for Web Search
Ranking models have achieved promising results, but it remains challenging to design personalized ranking systems to leverage user profiles and semantic representations between queries and documents.
GQE-PRF: Generative Query Expansion with Pseudo-Relevance Feedback
To leverage the strength of text generation for information retrieval, in this article, we propose a novel approach which effectively integrates text generation models into PRF-based query expansion.
Probabilistic methods for approximate archetypal analysis
Archetypal analysis is an unsupervised learning method for exploratory data analysis.
Video Annotation for Visual Tracking via Selection and Refinement
Deep learning based visual trackers entail offline pre-training on large volumes of video datasets with accurate bounding box annotations that are labor-expensive to achieve.
OLR 2021 Challenge: Datasets, Rules and Baselines
In addition to the Language Identification (LID) tasks, multilingual Automatic Speech Recognition (ASR) tasks are introduced to OLR 2021 Challenge for the first time.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Multimodal Reward Shaping for Efficient Exploration in Reinforcement Learning
Furthermore, we leverage a variational auto-encoder (VAE) model to capture the life-long novelty of states, which is combined with the global JFI score to form multimodal intrinsic rewards.
Oriental Language Recognition (OLR) 2020: Summary and Analysis
The fifth Oriental Language Recognition (OLR) Challenge focuses on language recognition in a variety of complex environments to promote its development.
Gradient Importance Learning for Incomplete Observations
Though recent works have developed methods that can generate estimates (or imputations) of the missing entries in a dataset to facilitate downstream analysis, most depend on assumptions that may not align with real-world applications and could suffer from poor performance in subsequent tasks such as classification.
Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization
Successful applications of InfoNCE and its variants have popularized the use of contrastive variational mutual information (MI) estimators in machine learning.
CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding
Recent works aimed to improve the robustness of pre-trained models mainly focus on adversarial training from perturbed examples with similar semantics, neglecting the utilization of different or even opposite semantics.
AOMD: An Analogy-aware Approach to Offensive Meme Detection on Social Media
To address the above challenges, we develop a deep learning based Analogy-aware Offensive Meme Detection (AOMD) framework to learn the implicit analogy from the multi-modal contents of the meme and effectively detect offensive analogy memes.
Voting for the right answer: Adversarial defense for speaker verification
Automatic speaker verification (ASV) is a well developed technology for biometric identification, and has been ubiquitous implemented in security-critic applications, such as banking and access control.
A Dataset And Benchmark Of Underwater Object Detection For Robot Picking
Towards these challenges we introduce a dataset, Detecting Underwater Objects (DUO), and a corresponding benchmark, based on the collection and re-annotation of all relevant datasets.
A Streaming End-to-End Framework For Spoken Language Understanding
In this paper, we propose a streaming end-to-end framework that can process multiple intentions in an online and incremental way.
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
Object tracking has achieved significant progress over the past few years.
Learning Spatio-Temporal Transformer for Visual Tracking
In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component.
Ranked #14 on
Visual Object Tracking
on TrackingNet
Transformer Tracking
The correlation operation is a simple fusion manner to consider the similarity between the template and the search region.
Ranked #5 on
Visual Tracking
on TNL2K
Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation
To solve the above problem, in this work, we propose a novel method called Adversarial and Contrastive Variational Autoencoder (ACVAE) for sequential recommendation.
FAST-Dynamic-Vision: Detection and Tracking Dynamic Objects with Event and Depth Sensing
The bottleneck of solving this problem is the accurate perception of rapid dynamic objects.
Motion Compensation
Robust Object Detection
+1
Robotics
Pyramid Spatial-Temporal Aggregation for Video-Based Person Re-Identification
Video-based person re-identification aims to associate the video clips of the same person across multiple non-overlapping cameras.
Ranked #1 on
Person Re-Identification
on DukeMTMC-VideoReID
Towards Robust and Efficient Contrastive Textual Representation Learning
There has been growing interest in representation learning for text data, based on theoretical arguments and empirical evidence.
eTREE: Learning Tree-structured Embeddings
In many applications, the categories of items exhibit a hierarchical tree structure.
Wasserstein Contrastive Representation Distillation
The primary goal of knowledge distillation (KD) is to encapsulate the information of a model learned from a teacher network into a student network, with the latter being more compact than the former.
Ranked #7 on
Knowledge Distillation
on CIFAR-100
Temporal Relational Modeling with Self-Supervision for Action Segmentation
The main reason is that large number of nodes (i. e., video frames) makes GCNs hard to capture and model temporal relations in videos.
Ranked #22 on
Action Segmentation
on Breakfast
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation
Many recent trackers adopt the multiple-stage tracking strategy to improve the quality of bounding box estimation.
Ranked #13 on
Semi-Supervised Video Object Segmentation
on VOT2020
Semi-Supervised Video Object Segmentation
Visual Object Tracking
Multi-modal Visual Tracking: Review and Experimental Comparison
Visual object tracking, as a fundamental task in computer vision, has drawn much attention in recent years.
Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models
Deep neural networks excel at comprehending complex visual signals, delivering on par or even superior performance to that of human experts.
Decoder-side Cross Resolution Synthesis for Video Compression Enhancement
This paper proposes a decoder-side Cross Resolution Synthesis (CRS) module to pursue better compression efficiency beyond the latest Versatile Video Coding (VVC), where we encode intra frames at original high resolution (HR), compress inter frames at a lower resolution (LR), and then super-resolve decoded LR inter frames with the help from preceding HR intra and neighboring LR inter frames.
Summarize before Aggregate: A Global-to-local Heterogeneous Graph Inference Network for Conversational Emotion Recognition
Local dependencies, which captures short-term emotional effects between neighbouring utterances, are further injected via an Aggregation Graph to distinguish the subtle differences between utterances containing emotional phrases.
Ranked #20 on
Emotion Recognition in Conversation
on IEMOCAP
Integrating User History into Heterogeneous Graph for Dialogue Act Recognition
Dialogue Act Recognition (DAR) is a challenging problem in Natural Language Understanding, which aims to attach Dialogue Act (DA) labels to each utterance in a conversation.
Can We Trust Deep Speech Prior?
Recently, speech enhancement (SE) based on deep speech prior has attracted much attention, such as the variational auto-encoder with non-negative matrix factorization (VAE-NMF) architecture.
Deep Speaker Vector Normalization with Maximum Gaussianality Training
In this paper, we argue that this problem is largely attributed to the maximum-likelihood (ML) training criterion of the DNF model, which aims to maximize the likelihood of the observations but not necessarily improve the Gaussianality of the latent codes.
Deep generative LDA
Limited by its linear form and the underlying Gaussian assumption, however, LDA is not applicable in situations where the data distribution is complex.
Squeezing value of cross-domain labels: a decoupled scoring approach for speaker verification
Domain mismatch often occurs in real applications and causes serious performance reduction on speaker verification systems.
Deep generative factorization for speech signal
Various information factors are blended in speech signals, which forms the primary difficulty for most speech information processing tasks.
Consistency of archetypal analysis
Archetypal analysis is an unsupervised learning method that uses a convex polytope to summarize multivariate data.
Remarks on Optimal Scores for Speaker Recognition
In this article, we first establish the theory of optimal scores for speaker recognition.
WANA: Symbolic Execution of Wasm Bytecode for Cross-Platform Smart Contract Vulnerability Detection
Furthermore, WANA proposes a set of test oracles to detect the vulnerabilities in EOSIO and Ethereum smart contracts based on WebAssembly bytecode analysis.
Software Engineering D.2.5
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation
In recent years, the multiple-stage strategy has become a popular trend for visual tracking.
Jointly Modeling Motion and Appearance Cues for Robust RGB-T Tracking
In this study, we propose a novel RGB-T tracking framework by jointly modeling both appearance and motion cues.
A Characteristic Function-based Algorithm for Geodesic Active Contours
Active contour models have been widely used in image segmentation, and the level set method (LSM) is the most popular approach for solving the models, via implicitly representing the contour by a level set function.
AP20-OLR Challenge: Three Tasks and Their Baselines
Based on Kaldi and Pytorch, recipes for i-vector and x-vector systems are also conducted as baselines for the three tasks.
DASC: Towards A Road Damage-Aware Social-Media-Driven Car Sensing Framework for Disaster Response Applications
iii) How to efficiently guide the cars to the event locations with little prior knowledge of the road damage caused by the disaster, while also handling the dynamics of the physical world and social media?
Improve bone age assessment by learning from anatomical local regions
In the clinical practice, Tanner and Whitehouse (TW2) method is a widely-used method for radiologists to perform BAA.
An efficient iterative method for reconstructing surface from point clouds
In this paper, we develop an efficient iterative method on a variational model for the surface reconstruction from point clouds.
Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning
Domain generalization remains a critical problem for speaker recognition, even with the state-of-the-art architectures based on deep neural nets.
Audio and Speech Processing
Conversational Word Embedding for Retrieval-Based Dialog System
Human conversations contain many types of information, e. g., knowledge, common sense, and language habits.
Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent
Generative adversarial networks (GANs), famous for the capability of learning complex underlying data distribution, are however known to be tricky in the training process, which would probably result in mode collapse or performance deterioration.
CovidSens: A Vision on Reliable Social Sensing for COVID-19
In this vision paper, we discuss the roles of CovidSens and identify potential challenges in developing reliable social sensing based risk alert systems.
Deep Normalization for Speaker Vectors
Deep speaker embedding has demonstrated state-of-the-art performance in speaker recognition tasks.
High-Performance Long-Term Tracking with Meta-Updater
Most top-ranked long-term trackers adopt the offline-trained Siamese architectures, thus, they cannot benefit from great progress of short-term trackers with online update.
Ranked #7 on
Visual Object Tracking
on LaSOT-ext
Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises
An effective and efficient perturbation generator is trained with a carefully designed adversarial loss, which can simultaneously cool hot regions where the target exists on the heatmaps and force the predicted bounding box to shrink, making the tracked target invisible to trackers.
FocalMix: Semi-Supervised Learning for 3D Medical Image Detection
Applying artificial intelligence techniques in medical imaging is one of the most promising areas in medicine.
Group Activity Recognition by Using Effective Multiple Modality Relation Representation With Temporal-Spatial Attention
Then, we propose two types of inference models, opt-GRU and relation-GRU, which are used to encode the object relationship and motion representation effectively, and form the discriminative frame-level feature representation.
Ranked #4 on
Group Activity Recognition
on Volleyball
Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing
In this paper, we present a graph representation learning method atop of transaction networks for merchant incentive optimization in mobile payment marketing.
Deep Variational Luenberger-type Observer for Stochastic Video Prediction
Our model builds upon an variational encoder which transforms the input video into a latent feature space and a Luenberger-type observer which captures the dynamic evolution of the latent features.
Curriculum Audiovisual Learning
Associating sound and its producer in complex audiovisual scene is a challenging task, especially when we are lack of annotated training data.
ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard
21 teams submit results for Task 1, 23 teams submit results for Task 2, 24 teams submit results for Task 3, and 13 teams submit results for Task 4.
On Fenchel Mini-Max Learning
Inference, estimation, sampling and likelihood evaluation are four primary goals of probabilistic modeling.
OpenArray v1.0: a simple operator library for the decoupling of ocean modeling and parallel computing
In this work, we design a simple computing library to bridge the gap and decouple the work of ocean modeling from parallel computing.
Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding
Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks.
ROI Pooled Correlation Filters for Visual Tracking
The ROI (region-of-interest) based pooling method performs pooling operations on the cropped ROI regions for various samples and has shown great success in the object detection methods.
CN-CELEB: a challenging Chinese speaker recognition dataset
These datasets tend to deliver over optimistic performance and do not meet the request of research on speaker recognition in unconstrained conditions.
On Investigation of Unsupervised Speech Factorization Based on Normalization Flow
Speech signals are complex composites of various information, including phonetic content, speaker traits, channel effect, etc.
VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results
Results of 33 object detection algorithms are presented.
GradNet: Gradient-Guided Network for Visual Object Tracking
In this work, we propose a novel gradient-guided network to exploit the discriminative information in gradients and update the template in the siamese network through feed-forward and backward operations.
Ranked #3 on
Visual Object Tracking
on OTB-2015
(Precision metric)
An Online Reinforcement Learning Approach to Quality-Cost-Aware Task Allocation for Multi-Attribute Social Sensing
Social sensing has emerged as a new sensing paradigm where humans (or devices on their behalf) collectively report measurements about the physical world.
'Skimming-Perusal' Tracking: A Framework for Real-Time and Robust Long-term Tracking
In this work, we present a novel robust and real-time long-term tracking framework based on the proposed skimming and perusal modules.
VAE-based Domain Adaptation for Speaker Verification
By enforcing the neural model to discriminate the speakers in the training set, deep speaker embedding (called `x-vectors`) can be derived from the hidden layers.
signADAM: Learning Confidences for Deep Neural Networks
In this paper, we propose a new first-order gradient-based algorithm to train deep neural networks.
Towards Reliable Online Clickbait Video Detection: A Content-Agnostic Approach
Current clickbait detection solutions that mainly focus on analyzing the text of the title, the image of the thumbnail, or the content of the video are shown to be suboptimal in detecting the online clickbait videos.
AP19-OLR Challenge: Three Tasks and Their Baselines
The participants can refer to these online-published recipes to deploy LID systems for convenience.
C^3 Framework: An Open-source PyTorch Code for Crowd Counting
This technical report attempts to provide efficient and solid kits addressed on the field of crowd counting, which is denoted as Crowd Counting Code Framework (C$^3$F).
LMVP: Video Predictor with Leaked Motion Information
We propose a Leaked Motion Video Predictor (LMVP) to predict future frames by capturing the spatial and temporal dependencies from given inputs.
A One-step Pruning-recovery Framework for Acceleration of Convolutional Neural Networks
Our method accelerates the network in one-step pruning-recovery manner with a novel optimization objective function, which achieves higher accuracy with much less cost compared with existing pruning methods.
A Preliminary Study on Data Augmentation of Deep Learning for Image Classification
Deep learning models have a large number of freeparameters that need to be calculated by effective trainingof the models on a great deal of training data to improvetheir generalization performance.
Exploiting Persona Information for Diverse Generation of Conversational Responses
Giving conversational context with persona information to a chatbot, how to exploit the information to generate diverse and sustainable conversations is still a non-trivial task.
Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems
First-order methods such as stochastic gradient descent (SGD) are currently the standard algorithm for training deep neural networks.
Globally Soft Filter Pruning For Efficient Convolutional Neural Networks
Therefore, accumulating the saliency of the filter over the entire data set can provide more accurate guidance for pruning.
Early Action Prediction with Generative Adversarial Networks
Action Prediction is aimed to determine what action is occurring in a video as early as possible, whi