Search Results for author:
Found 270 papers, 100 papers with code
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.
VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results
Results of 33 object detection algorithms are presented.
Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking
Also, our method shows strong generalization for diverse trackers and scenarios in a plug-and-play and training-free manner.
Ranked #9 on
Multi-Object Tracking
on DanceTrack
Learning to Navigate for Fine-grained Classification
In consideration of intrinsic consistency between informativeness of the regions and their probability being ground-truth class, we design a novel training paradigm, which enables Navigator to detect most informative regions under the guidance from Teacher.
Ranked #42 on
Fine-Grained Image Classification
on FGVC Aircraft
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.
Ranked #1 on
Referring Expression Segmentation
on RefCoCo val
(using extra training data)
Described Object Detection
Generalized Referring Expression Comprehension
+15
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
+3
Off-Policy Primal-Dual Safe Reinforcement Learning
Results on benchmark tasks show that our method not only achieves an asymptotic performance comparable to state-of-the-art on-policy methods while using much fewer samples, but also significantly reduces constraint violation during training.
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 #5 on
Semi-Supervised Video Object Segmentation
on YouTube-VOS 2019
(using extra training data)
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).
BRITS: Bidirectional Recurrent Imputation for Time Series
It is ubiquitous that time series contains many missing values.
General Classification
Multivariate Time Series Forecasting
+5
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 #18 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
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
Object tracking has achieved significant progress over the past few years.
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.
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 #10 on
Visual Object Tracking
on LaSOT-ext
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.
Ranked #10 on
Rgb-T Tracking
on LasHeR
Learning regression and verification networks for long-term visual tracking
Compared with short-term tracking, the long-term tracking task requires determining the tracked object is present or absent, and then estimating the accurate bounding box if present or conducting image-wide re-detection if absent.
Balanced Multimodal Learning via On-the-fly Gradient Modulation
Multimodal learning helps to comprehensively understand the world, by integrating different senses.
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 #4 on
3D Point Cloud Linear Classification
on ModelNet40
(using extra training data)
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.
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 #15 on
Semi-Supervised Video Object Segmentation
on VOT2020
Semi-Supervised Video Object Segmentation
Visual Object Tracking
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.
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.
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
'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.
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.
LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking
Recently, large language models (LLMs) have exhibited significant progress in language understanding and generation.
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)
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.
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.
Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters
Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset.
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.
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.
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.
Learning Uncertain Convolutional Features for Accurate Saliency Detection
In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection.
Ranked #5 on
Saliency Detection
on DUT-OMRON
Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
In addition, to achieve accurate boundary inference and semantic enhancement, edge-aware feature maps in low-level layers and the predicted results of low resolution features are recursively embedded into the learning framework.
Ranked #20 on
RGB Salient Object Detection
on DUTS-TE
(max F-measure metric)
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.
Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models
To this end, we introduce Point-PEFT, a novel framework for adapting point cloud pre-trained models with minimal learnable parameters.
Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding
The adapter incorporates prior spatial knowledge from the source modality to guide the local feature aggregation of 3D tokens, compelling the semantic adaption of any-modality transformers.
Efficient Visual Tracking via Hierarchical Cross-Attention Transformer
Most state-of-the-art trackers are satisfied with the real-time speed on powerful GPUs.
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.
THCHS-30 : A Free Chinese Speech Corpus
Speech data is crucially important for speech recognition research.
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
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.
Ranked #2 on
Rgb-T Tracking
on GTOT
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.
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.
Conversational Word Embedding for Retrieval-Based Dialog System
Human conversations contain many types of information, e. g., knowledge, common sense, and language habits.
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.
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.
Linear Recurrent Units for Sequential Recommendation
State-of-the-art sequential recommendation relies heavily on self-attention-based recommender models.
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
Correlation Tracking via Joint Discrimination and Reliability Learning
To address this issue, we propose a novel CF-based optimization problem to jointly model the discrimination and reliability information.
Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
In this paper, we introduce a new sequence-to-sequence learning framework for RGB-based and multi-modal object tracking.
Ranked #1 on
Rgb-T Tracking
on LasHeR
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.
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.
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.
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 #23 on
Action Segmentation
on Breakfast
Real Additive Margin Softmax for Speaker Verification
The additive margin softmax (AM-Softmax) loss has delivered remarkable performance in speaker verification.
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.
Learning Spatial-Aware Regressions for Visual Tracking
Second, we propose a fully convolutional neural network with spatially regularized kernels, through which the filter kernel corresponding to each output channel is forced to focus on a specific region of the target.
Ranked #12 on
Visual Object Tracking
on VOT2017/18
Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMs
Generalizable articulated object manipulation is essential for home-assistant robots.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Domain Adaptation for Question Answering via Question Classification
In this work, we investigate the potential benefits of question classification for QA domain adaptation.
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.
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.
AP18-OLR Challenge: Three Tasks and Their Baselines
The third oriental language recognition (OLR) challenge AP18-OLR is introduced in this paper, including the data profile, the tasks and the evaluation principles.
AP17-OLR Challenge: Data, Plan, and Baseline
We present the data profile and the evaluation plan of the second oriental language recognition (OLR) challenge AP17-OLR.
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)
signADAM: Learning Confidences for Deep Neural Networks
In this paper, we propose a new first-order gradient-based algorithm to train deep neural networks.
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
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.
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.
Federated Recommendation via Hybrid Retrieval Augmented Generation
To this end, we propose GPT-FedRec, a federated recommendation framework leveraging ChatGPT and a novel hybrid Retrieval Augmented Generation (RAG) mechanism.
On Fenchel Mini-Max Learning
Inference, estimation, sampling and likelihood evaluation are four primary goals of probabilistic modeling.
Deep Normalization for Speaker Vectors
Deep speaker embedding has demonstrated state-of-the-art performance in speaker recognition tasks.
eTREE: Learning Tree-structured Embeddings
In many applications, the categories of items exhibit a hierarchical tree structure.
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.
Subspace-Configurable Networks
The obtained subspace is low-dimensional and has a surprisingly simple structure even for complex, non-invertible transformations of the input, leading to an exceptionally high efficiency of subspace-configurable networks (SCNs) when limited storage and computing resources are at stake.
An efficient iterative thresholding method for image segmentation
We proposed an efficient iterative thresholding method for multi-phase image segmentation.
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.
Defending Substitution-Based Profile Pollution Attacks on Sequential Recommenders
Additionally, we design an adversarial training method tailored for sequential recommender systems.
Deployable Reinforcement Learning with Variable Control Rate
Unfortunately, the system should be controlled at the highest, worst-case frequency to ensure stability, which can demand significant computational and energy resources and hinder the deployability of the controller on onboard hardware.
Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression
In this way, most of the representative information in the network can be retained in each cluster.
Deep factorization for speech signal
Various informative factors mixed in speech signals, leading to great difficulty when decoding any of the factors.
Full-info Training for Deep Speaker Feature Learning
In recent studies, it has shown that speaker patterns can be learned from very short speech segments (e. g., 0. 3 seconds) by a carefully designed convolutional & time-delay deep neural network (CT-DNN) model.
Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Maps
Extensive experiments demonstrate that the proposed algorithm achieves competitive performance in both saliency detection and visual tracking, especially outperforming other related trackers on the non-rigid object tracking datasets.
Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
This paper proposes an Agile Aggregating Multi-Level feaTure framework (Agile Amulet) for salient object detection.
Human and Machine Speaker Recognition Based on Short Trivial Events
Trivial events are ubiquitous in human to human conversations, e. g., cough, laugh and sniff.
Medical Diagnosis From Laboratory Tests by Combining Generative and Discriminative Learning
In hospital, physicians rely on massive clinical data to make diagnosis decisions, among which laboratory tests are one of the most important resources.
Enhanced Neural Machine Translation by Learning from Draft
Neural machine translation (NMT) has recently achieved impressive results.
Phonetic Temporal Neural Model for Language Identification
Deep neural models, particularly the LSTM-RNN model, have shown great potential for language identification (LID).
Memory-augmented Neural Machine Translation
Neural machine translation (NMT) has achieved notable success in recent times, however it is also widely recognized that this approach has limitations with handling infrequent words and word pairs.
Memory-augmented Chinese-Uyghur Neural Machine Translation
Neural machine translation (NMT) has achieved notable performance recently.
Deep Factorization for Speech Signal
In this paper, we demonstrated that the speaker factor is also a short-time spectral pattern and can be largely identified with just a few frames using a simple deep neural network (DNN).
Deep Speaker Verification: Do We Need End to End?
This principle has recently been applied to several prototype research on speaker verification (SV), where the feature learning and classifier are learned together with an objective function that is consistent with the evaluation metric.
Cross-lingual Speaker Verification with Deep Feature Learning
The experiments demonstrated that the feature-based system outperformed the i-vector system with a large margin, particularly with language mismatch between enrollment and test.
Speaker Recognition with Cough, Laugh and "Wei"
This paper proposes a speaker recognition (SRE) task with trivial speech events, such as cough and laugh.
Weakly Supervised PLDA Training
PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification.
Collaborative Learning for Language and Speaker Recognition
This paper presents a unified model to perform language and speaker recognition simultaneously and altogether.
Phone-aware Neural Language Identification
Pure acoustic neural models, particularly the LSTM-RNN model, have shown great potential in language identification (LID).
Flexible and Creative Chinese Poetry Generation Using Neural Memory
It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism.
Deep Speaker Feature Learning for Text-independent Speaker Verification
Recently deep neural networks (DNNs) have been used to learn speaker features.
Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition
Recurrent neural networks (RNNs) have shown clear superiority in sequence modeling, particularly the ones with gated units, such as long short-term memory (LSTM) and gated recurrent unit (GRU).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
AP16-OL7: A Multilingual Database for Oriental Languages and A Language Recognition Baseline
We present the AP16-OL7 database which was released as the training and test data for the oriental language recognition (OLR) challenge on APSIPA 2016.
System Combination for Short Utterance Speaker Recognition
This paper presents a combination approach to the SUSR tasks with two phonetic-aware systems: one is the DNN-based i-vector system and the other is our recently proposed subregion-based GMM-UBM system.
Local Training for PLDA in Speaker Verification
PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification.
OC16-CE80: A Chinese-English Mixlingual Database and A Speech Recognition Baseline
We present the OC16-CE80 Chinese-English mixlingual speech database which was released as a main resource for training, development and test for the Chinese-English mixlingual speech recognition (MixASR-CHEN) challenge on O-COCOSDA 2016.
Multi-task Recurrent Model for Speech and Speaker Recognition
Although highly correlated, speech and speaker recognition have been regarded as two independent tasks and studied by two communities.
Multi-task Recurrent Model for True Multilingual Speech Recognition
Research on multilingual speech recognition remains attractive yet challenging.
Chinese Song Iambics Generation with Neural Attention-based Model
Learning and generating Chinese poems is a charming yet challenging task.
Can Machine Generate Traditional Chinese Poetry? A Feigenbaum Test
Recent progress in neural learning demonstrated that machines can do well in regularized tasks, e. g., the game of Go.
Recurrent Neural Network Training with Dark Knowledge Transfer
Recent research found that a well-trained model can be used as a teacher to train other child models, by using the predictions generated by the teacher model as supervision.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Bayesian Neighbourhood Component Analysis
Learning a good distance metric in feature space potentially improves the performance of the KNN classifier and is useful in many real-world applications.
Binary Speaker Embedding
The popular i-vector model represents speakers as low-dimensional continuous vectors (i-vectors), and hence it is a way of continuous speaker embedding.
Max-margin Metric Learning for Speaker Recognition
Probabilistic linear discriminant analysis (PLDA) is a popular normalization approach for the i-vector model, and has delivered state-of-the-art performance in speaker recognition.
A Universal Update-pacing Framework For Visual Tracking
Given a base tracker, an ensemble of trackers is generated, in which each tracker's update behavior will be paced and then traces the target object forward and backward to generate a pair of trajectories in an interval.
Relation Classification via Recurrent Neural Network
Deep learning has gained much success in sentence-level relation classification.
Transfer Learning for Speech and Language Processing
Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks.
Deep Representation of Facial Geometric and Photometric Attributes for Automatic 3D Facial Expression Recognition
In this paper, we present a novel approach to automatic 3D Facial Expression Recognition (FER) based on deep representation of facial 3D geometric and 2D photometric attributes.
3D Facial Expression Recognition
Facial Expression Recognition
Stochastic Top-k ListNet
ListNet is a well-known listwise learning to rank model and has gained much attention in recent years.
Learning from LDA using Deep Neural Networks
Latent Dirichlet Allocation (LDA) is a three-level hierarchical Bayesian model for topic inference.
VMF-SNE: Embedding for Spherical Data
This assumption does not hold for a wide range of data types in practical applications, for instance spherical data for which the local proximity is better modelled by the von Mises-Fisher (vMF) distribution instead of the Gaussian.
Improved Deep Speaker Feature Learning for Text-Dependent Speaker Recognition
A deep learning approach has been proposed recently to derive speaker identifies (d-vector) by a deep neural network (DNN).
Recognize Foreign Low-Frequency Words with Similar Pairs
We also employ this approach to deal with out-of-language words in the task of multi-lingual speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Knowledge Transfer Pre-training
Compared to the conventional layer-wise methods, this new method does not care about the model structure, so can be used to pre-train very complex models.
Learning Speech Rate in Speech Recognition
A significant performance reduction is often observed in speech recognition when the rate of speech (ROS) is too low or too high.
Unsupervised Feature Learning with C-SVDDNet
To address this issue, we propose a SVDD based feature learning algorithm that describes the density and distribution of each cluster from K-means with an SVDD ball for more robust feature representation.
Ranked #23 on
Image Classification
on MNIST
Deep Speaker Vectors for Semi Text-independent Speaker Verification
Recent research shows that deep neural networks (DNNs) can be used to extract deep speaker vectors (d-vectors) that preserve speaker characteristics and can be used in speaker verification.
Chinese Poetry Generation with Flexible Styles
Research has shown that sequence-to-sequence neural models, particularly those with the attention mechanism, can successfully generate classical Chinese poems.
Gaussian-Constrained training for speaker verification
This paper proposes a Gaussian-constrained training approach that (1) discards the parametric classifier, and (2) enforces the distribution of the derived speaker vectors to be Gaussian.
Phonetic-attention scoring for deep speaker features in speaker verification
This score reflects the similarity of the two frames in phonetic content, and is used to weigh the contribution of this frame pair in the utterance-based scoring.
Discourse Mode Identification in Essays
Evaluation results show that discourse modes can be identified automatically with an average F1-score of 0. 7.
Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Fully Convolutional Network
To address these issues, we propose a multi-stream bottom-top-bottom fully convolutional network (BTBNet), which is the first attempt to develop an end-to-end deep network for DBD.
Ranked #2 on
Defocus Estimation
on CUHK - Blur Detection Dataset
(MAE metric)
Structured Siamese Network for Real-Time Visual Tracking
In this paper, we circumvent this issue by proposing a local structure learning method, which simultaneously considers the local patterns of the target and their structural relationships for more accurate target tracking.
Real-time 'Actor-Critic' Tracking
In this work, we propose a novel tracking algorithm with real-time performance based on the âActor-Criticâ framework.
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.
CONet: A Cognitive Ocean Network
The Cognitive Ocean Network (CONet) will become the mainstream of future ocean science and engineering developments.
Least Soft-Threshold Squares Tracking
In this paper, we propose a generative tracking method based on a novel robust linear regression algorithm.
Visual Tracking via Probability Continuous Outlier Model
In this paper, we present a novel online visual tracking method based on linear representation.
Learning to Detect Salient Objects With Image-Level Supervision
In the second stage, FIN is fine-tuned with its predicted saliency maps as ground truth.
Stepwise Metric Promotion for Unsupervised Video Person Re-Identification
The intensive annotation cost and the rich but unlabeled data contained in videos motivate us to propose an unsupervised video-based person re-identification (re-ID) method.
Ranked #7 on
Person Re-Identification
on PRID2011
Effort of Genre Variation and Prediction of System Performance
Our experiments show that the predicted scores are close to the real scores when tested on the CTB data.
VAE-based regularization for deep speaker embedding
Deep speaker embedding has achieved state-of-the-art performance in speaker recognition.
Listen to the Image
different encoding schemes indicate that using machine model to accelerate optimization evaluation and reduce experimental cost is feasible to some extent, which could dramatically promote the upgrading of encoding scheme then help the blind to improve their visual perception ability.
The iterative convolution-thresholding method (ICTM) for image segmentation
In this paper, we propose a novel iterative convolution-thresholding method (ICTM) that is applicable to a range of variational models for image segmentation.
Early Action Prediction with Generative Adversarial Networks
Action Prediction is aimed to determine what action is occurring in a video as early as possible, which is crucial to many online applications, such as predicting a traffic accident before it happens and detecting malicious actions in the monitoring system.
Memory-Augmented Temporal Dynamic Learning for Action Recognition
Human actions captured in video sequences contain two crucial factors for action recognition, i. e., visual appearance and motion dynamics.
Anomaly Detection in Traffic Scenes via Spatial-aware Motion Reconstruction
3) Results of motion orientation and magnitude are adaptively weighted and fused by a Bayesian model, which makes the proposed method more robust and handle more kinds of abnormal events.
Cross-Modal Message Passing for Two-stream Fusion
The classification object ensures that each modal network predicts the true action category while the competing objective encourages each modal network to outperform the other one.
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.
Neural IR Meets Graph Embedding: A Ranking Model for Product Search
Recently, neural models for information retrieval are becoming increasingly popular.
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.
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 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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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?
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.
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.
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.
Ranked #4 on
Rgb-T Tracking
on GTOT
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.
Remarks on Optimal Scores for Speaker Recognition
In this article, we first establish the theory of optimal scores for speaker recognition.
Consistency of archetypal analysis
Archetypal analysis is an unsupervised learning method that uses a convex polytope to summarize multivariate data.
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.
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.
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.
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 #10 on
Knowledge Distillation
on CIFAR-100
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 #29 on
Emotion Recognition in Conversation
on IEMOCAP
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.
