Search Results for author:
Found 95 papers, 45 papers with code
Exploit Bounding Box Annotations for Multi-label Object Recognition
With strong labels, our framework is able to achieve state-of-the-art results in both datasets.
Ranked #16 on
Multi-Label Classification
on PASCAL VOC 2007
N-ary Error Correcting Coding Scheme
The coding matrix design plays a fundamental role in the prediction performance of the error correcting output codes (ECOC)-based multi-class task.
Simple and Efficient Learning using Privileged Information
The Support Vector Machine using Privileged Information (SVM+) has been proposed to train a classifier to utilize the additional privileged information that is only available in the training phase but not available in the test phase.
Transfer Hashing with Privileged Information
Specifically, we extend the standard learning to hash method, Iterative Quantization (ITQ), in a transfer learning manner, namely ITQ+.
Improving Multi-label Learning with Missing Labels by Structured Semantic Correlations
Experimental results demonstrate the effectiveness of the proposed semantic descriptor and the usefulness of incorporating the structured semantic correlations.
MIML-FCN+: Multi-instance Multi-label Learning via Fully Convolutional Networks with Privileged Information
As the proposed PI loss is convex and SGD compatible and the framework itself is a fully convolutional network, MIML-FCN+ can be easily integrated with state of-the-art deep learning networks.
Action Recognition for Depth Video using Multi-view Dynamic Images
To better exploit three-dimensional (3D) characteristics, multi-view dynamic images are proposed.
Towards Good Practices on Building Effective CNN Baseline Model for Person Re-identification
Person re-identification is indeed a challenging visual recognition task due to the critical issues of human pose variation, human body occlusion, camera view variation, etc.
XAI Beyond Classification: Interpretable Neural Clustering
The second is implementing discrete $k$-means with a differentiable neural network that embraces the advantages of parallel computing, online clustering, and clustering-favorable representation learning.
Towards Real-time Eyeblink Detection in The Wild:Dataset,Theory and Practices
Effective and real-time eyeblink detection is of wide-range applications, such as deception detection, drive fatigue detection, face anti-spoofing, etc.
DATNet: Dual Adversarial Transfer for Low-resource Named Entity Recognition
We propose a new architecture termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity Recognition (NER).
Low Resource Named Entity Recognition
named-entity-recognition
+2
Query-efficient Meta Attack to Deep Neural Networks
Black-box attack methods aim to infer suitable attack patterns to targeted DNN models by only using output feedback of the models and the corresponding input queries.
Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition
We propose a new neural transfer method termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity Recognition (NER).
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models.
Robust Regression via Deep Negative Correlation Learning
Nonlinear regression has been extensively employed in many computer vision problems (e. g., crowd counting, age estimation, affective computing).
A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image
For 3D hand and body pose estimation task in depth image, a novel anchor-based approach termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is proposed.
Ranked #1 on
Hand Pose Estimation
on K2HPD
Multi-graph Fusion for Multi-view Spectral Clustering
Most existing methods don't pay attention to the quality of the graphs and perform graph learning and spectral clustering separately.
Unsupervised Domain Adaptation on Reading Comprehension
On the other hand, it further reduces domain distribution discrepancy through conditional adversarial learning across domains.
CPM-Nets: Cross Partial Multi-View Networks
Despite multi-view learning progressed fast in past decades, it is still challenging due to the difficulty in modeling complex correlation among different views, especially under the context of view missing.
Ordered or Orderless: A Revisit for Video based Person Re-Identification
Specifically, with a diagnostic analysis, we show that the recurrent structure may not be effective to learn temporal dependencies than what we expected and implicitly yields an orderless representation.
A Simple Baseline to Semi-Supervised Domain Adaptation for Machine Translation
State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on new domains with no supervised data.
Hooks in the Headline: Learning to Generate Headlines with Controlled Styles
Current summarization systems only produce plain, factual headlines, but do not meet the practical needs of creating memorable titles to increase exposure.
RAIN: A Simple Approach for Robust and Accurate Image Classification Networks
However, similar to existing preprocessing-based methods, the randomized process will degrade the prediction accuracy.
Heterogeneous Representation Learning: A Review
The real-world data usually exhibits heterogeneous properties such as modalities, views, or resources, which brings some unique challenges wherein the key is Heterogeneous Representation Learning (HRL) termed in this paper.
Span-based Localizing Network for Natural Language Video Localization
Given an untrimmed video and a text query, natural language video localization (NLVL) is to locate a matching span from the video that semantically corresponds to the query.
3DV: 3D Dynamic Voxel for Action Recognition in Depth Video
Each available 3DV voxel intrinsically involves 3D spatial and motion feature jointly.
The Power of Triply Complementary Priors for Image Compressive Sensing
In this paper, we propose a joint low-rank and deep (LRD) image model, which contains a pair of triply complementary priors, namely \textit{external} and \textit{internal}, \textit{deep} and \textit{shallow}, and \textit{local} and \textit{non-local} priors.
Omni-supervised Facial Expression Recognition via Distilled Data
However, the performance of the current state-of-the-art facial expression recognition (FER) approaches is directly related to the labeled data for training.
Facial Expression Recognition
Facial Expression Recognition (FER)
EDCompress: Energy-Aware Model Compression for Dataflows
EDCompress could also find the optimal dataflow type for specific neural networks in terms of energy consumption, which can guide the deployment of CNN models on hardware systems.
You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network
In this paper, we study two challenging and less-touched problems in single image dehazing, namely, how to make deep learning achieve image dehazing without training on the ground-truth clean image (unsupervised) and a image collection (untrained).
Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering
Multiple-choice question answering (MCQA) is one of the most challenging tasks in machine reading comprehension since it requires more advanced reading comprehension skills such as logical reasoning, summarization, and arithmetic operations.
ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification
Embedding RMML into the proposed ECML mechanism, our metric learning paradigm (EC-RMML) can run in the one-pass learning manner.
Attentive Graph Neural Networks for Few-Shot Learning
Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks.
Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition
In this paper, we propose a simple yet effective approach, named Point Adversarial Self Mining (PASM), to improve the recognition accuracy in facial expression recognition.
Contrastive Clustering
In this paper, we propose a one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning.
Ranked #4 on
Image Clustering
on STL-10
(using extra training data)
Deep N-ary Error Correcting Output Codes
To facilitate the training of N-ary ECOC with deep learning base learners, we further propose three different variants of parameter sharing architectures for deep N-ary ECOC.
Deep Neural Networks with Short Circuits for Improved Gradient Learning
Deep neural networks have achieved great success both in computer vision and natural language processing tasks.
Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
We study reinforcement learning (RL) for text-based games, which are interactive simulations in the context of natural language.
Deep Partial Multi-View Learning
Although multi-view learning has made signifificant progress over the past few decades, it is still challenging due to the diffificulty in modeling complex correlations among different views, especially under the context of view missing.
Partially View-aligned Clustering
To solve this practical and challenging problem, we propose a novel multi-view clustering method termed partially view-aligned clustering (PVC).
Adaptive Precision Training for Resource Constrained Devices
We use model of the same precision for both forward and backward pass in order to reduce memory usage for training.
Multi-View Disentangled Representation
Learning effective representations for data with multiple views is crucial in machine learning and pattern recognition.
Deep Learning for Latent Events Forecasting in Twitter Aided Caching Networks
A novel Twitter context aided content caching (TAC) framework is proposed for enhancing the caching efficiency by taking advantage of the legibility and massive volume of Twitter data.
Trusted Multi-View Classification
To this end, we propose a novel multi-view classification method, termed trusted multi-view classification, which provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level.
Natural Language Video Localization: A Revisit in Span-based Question Answering Framework
Our study suggests that the span-based QA framework is an effective strategy to solve the NLVL problem.
RCT: Resource Constrained Training for Edge AI
For example, quantisation-aware training (QAT) method involves two copies of model parameters, which is usually beyond the capacity of on-chip memory in edge devices.
PointBA: Towards Backdoor Attacks in 3D Point Cloud
We present the backdoor attacks in 3D point cloud with a unified framework that exploits the unique properties of 3D data and networks.
Video Corpus Moment Retrieval with Contrastive Learning
We adopt the first approach and introduce two contrastive learning objectives to refine video encoder and text encoder to learn video and text representations separately but with better alignment for VCMR.
Efficient Spiking Neural Networks with Radix Encoding
Traditionally, a spike train needs around one thousand time steps to approach similar accuracy as its ANN counterpart.
Parallel Attention Network with Sequence Matching for Video Grounding
In this work, we propose a Parallel Attention Network with Sequence matching (SeqPAN) to address the challenges in this task: multi-modal representation learning, and target moment boundary prediction.
Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentation
In this work, we propose an adversarial semantic hallucination approach (ASH), which combines a class-conditioned hallucination module and a semantic segmentation module.
Automated Deepfake Detection
In this paper, we propose to utilize Automated Machine Learning to adaptively search a neural architecture for deepfake detection.
Word2Pix: Word to Pixel Cross Attention Transformer in Visual Grounding
Current one-stage methods for visual grounding encode the language query as one holistic sentence embedding before fusion with visual feature.
Simultaneously Transmitting and Reflecting (STAR) Intelligent Omni-Surfaces, Their Modeling and Implementation
With the rapid development of advanced electromagnetic manipulation technologies, researchers and engineers are starting to study smart surfaces that can achieve enhanced coverages, high reconfigurability, and are easy to deploy.
Efficient Sharpness-aware Minimization for Improved Training of Neural Networks
Recently, the relation between the sharpness of the loss landscape and the generalization error has been established by Foret et al. (2020), in which the Sharpness Aware Minimizer (SAM) was proposed to mitigate the degradation of the generalization.
Towards Debiasing Temporal Sentence Grounding in Video
In this paper, we propose two debiasing strategies, data debiasing and model debiasing, to "force" a TSGV model to capture cross-modal interactions.
Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions
Multimodal regression is a fundamental task, which integrates the information from different sources to improve the performance of follow-up applications.
Temporal Sentence Grounding in Videos: A Survey and Future Directions
Temporal sentence grounding in videos (TSGV), \aka natural language video localization (NLVL) or video moment retrieval (VMR), aims to retrieve a temporal moment that semantically corresponds to a language query from an untrimmed video.
Multi-Scale Adaptive Network for Single Image Denoising
AFuB devotes to adaptively sampling and transferring the features from one scale to another scale, which fuses the multi-scale features with varying characteristics from coarse to fine.
Perceiving the World: Question-guided Reinforcement Learning for Text-based Games
Text-based games provide an interactive way to study natural language processing.
Trusted Multi-View Classification with Dynamic Evidential Fusion
With this in mind, we propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC), providing a new paradigm for multi-view learning by dynamically integrating different views at an evidence level.
Sharpness-Aware Training for Free
Intuitively, SAF achieves this by avoiding sudden drops in the loss in the sharp local minima throughout the trajectory of the updates of the weights.
Simultaneously Transmitting and Reflecting (STAR)-RISs: Are they Applicable to Dual-Sided Incidence?
A hardware model and a signal model are proposed for dual-sided simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs), where the signal simultaneously incident on both sides of the surface.
Meta Knowledge Condensation for Federated Learning
In this work, we first introduce a meta knowledge representation method that extracts meta knowledge from distributed clients.
TFormer: 3D Tooth Segmentation in Mesh Scans with Geometry Guided Transformer
Optical Intra-oral Scanners (IOS) are widely used in digital dentistry, providing 3-Dimensional (3D) and high-resolution geometrical information of dental crowns and the gingiva.
Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation
To mitigate the adverse impact of this accumulated trajectory error, we propose a novel approach that encourages the optimization algorithm to seek a flat trajectory.
Deep Negative Correlation Classification
Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm.
Frequency Guidance Matters in Few-Shot Learning
Few-shot classification aims to learn a discriminative feature representation to recognize unseen classes with few labeled support samples.
Active Simultaneously Transmitting and Reflecting (STAR)-RISs: Modelling and Analysis
The amplitude gains of the STAR element are derived for both coupled and independent phase-shift scenarios.
Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video
Experiments on MPEblink verify the essential challenges of real-time multi-person eyeblink detection in the wild for untrimmed video.
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image
3D interacting hand pose estimation from a single RGB image is a challenging task, due to serious self-occlusion and inter-occlusion towards hands, confusing similar appearance patterns between 2 hands, ill-posed joint position mapping from 2D to 3D, etc.. To address these, we propose to extend A2J-the state-of-the-art depth-based 3D single hand pose estimation method-to RGB domain under interacting hand condition.
Ranked #7 on
Hand Pose Estimation
on NYU Hands
Dual Stage Stylization Modulation for Domain Generalized Semantic Segmentation
To tackle this challenge, we introduce a dual-stage Feature Transform (dFT) layer within the Adversarial Semantic Hallucination+ (ASH+) framework.
Calibrating Multimodal Learning
Specifically, we find that the confidence estimated by current models could even increase when some modalities are corrupted.
dugMatting: Decomposed-Uncertainty-Guided Matting
Cutting out an object and estimating its opacity mask, known as image matting, is a key task in image and video editing.
Provable Dynamic Fusion for Low-Quality Multimodal Data
The inherent challenge of multimodal fusion is to precisely capture the cross-modal correlation and flexibly conduct cross-modal interaction.
Proceedings of the 40th International Conference on Machine Learning
Specifically, we find that the confidence estimated by current models could even increase when some modalities are corrupted.
Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification
With the growth of 3D sensing technology, deep learning system for 3D point clouds has become increasingly important, especially in applications like autonomous vehicles where safety is a primary concern.
Noisy-Correspondence Learning for Text-to-Image Person Re-identification
Text-to-image person re-identification (TIReID) is a compelling topic in the cross-modal community, which aims to retrieve the target person based on a textual query.
Ranked #2 on
Text based Person Retrieval
on ICFG-PEDES
(using extra training data)
Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection
In response to these identified gaps, we introduce the Ladder-of-Thought (LoT) for the stance detection task.
Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering
In this paper, we propose a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations.
Towards Distribution-Agnostic Generalized Category Discovery
In this paper, we formally define a more realistic task as distribution-agnostic generalized category discovery (DA-GCD): generating fine-grained predictions for both close- and open-set classes in a long-tailed open-world setting.
Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer
Data privacy and long-tailed distribution are the norms rather than the exception in many real-world tasks.
You Only Condense Once: Two Rules for Pruning Condensed Datasets
However, these scenarios have two significant challenges: 1) the varying computational resources available on the devices require a dataset size different from the pre-defined condensed dataset, and 2) the limited computational resources often preclude the possibility of conducting additional condensation processes.
Cross-modal Active Complementary Learning with Self-refining Correspondence
Recently, image-text matching has attracted more and more attention from academia and industry, which is fundamental to understanding the latent correspondence across visual and textual modalities.
TSegFormer: 3D Tooth Segmentation in Intraoral Scans with Geometry Guided Transformer
Optical Intraoral Scanners (IOS) are widely used in digital dentistry to provide detailed 3D information of dental crowns and the gingiva.
Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning
Dataset pruning aims to construct a coreset capable of achieving performance comparable to the original, full dataset.
Direct Distillation between Different Domains
Then, we build a fusion-activation mechanism to transfer the valuable domain-invariant knowledge to the student network, while simultaneously encouraging the adapter within the teacher network to learn the domain-specific knowledge of the target data.
FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data
Federated Long-Tailed Learning (Fed-LT), a paradigm wherein data collected from decentralized local clients manifests a globally prevalent long-tailed distribution, has garnered considerable attention in recent times.
A Concise but Effective Network for Image Guided Depth Completion in Autonomous Driving
Depth completion is a crucial task in autonomous driving, aiming to convert a sparse depth map into a dense depth prediction.
Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching
Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have raised growing concerns.
Selective Learning: Towards Robust Calibration with Dynamic Regularization
The objective can be understood as seeking a model that fits the ground-truth labels by increasing the confidence while also maximizing the entropy of predicted probabilities by decreasing the confidence.
Multisize Dataset Condensation
These two challenges connect to the "subset degradation problem" in traditional dataset condensation: a subset from a larger condensed dataset is often unrepresentative compared to directly condensing the whole dataset to that smaller size.
CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner
Most existing one-shot skeleton-based action recognition focuses on raw low-level information (e. g., joint location), and may suffer from local information loss and low generalization ability.
Collaborative Knowledge Infusion for Low-resource Stance Detection
Specifically, our stance detection approach leverages target background knowledge collaboratively from different knowledge sources with the help of knowledge alignment.
Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning
In addressing this issue, we are inspired by the notion that a backdoor acts as a shortcut and posit that this shortcut stems from the contrast between the trigger and the data utilized for poisoning.
