Search Results for author:
Found 164 papers, 89 papers with code
Dynamic Multistep Reasoning based on Video Scene Graph for Video Question Answering
Then, it performs multistep reasoning for better answer decision between the representations of the question and the video, and dynamically integrate the reasoning results.
API-Net: Robust Generative Classifier via a Single Discriminator
On the contrary, a discriminative classifier only models the conditional distribution of labels given inputs, but benefits from effective optimization owing to its succinct structure.
Hierarchical Representation-based Dynamic Reasoning Network for Biomedical Question Answering
It then performs dynamic reasoning based on the hierarchical representations of evidences to solve complex biomedical problems.
Dual-Branch Graph Transformer Network for 3D Human Mesh Reconstruction from Video
DGTR employs a dual-branch network including a Global Motion Attention (GMA) branch and a Local Details Refine (LDR) branch to parallelly extract long-term dependencies and local crucial information, helping model global human motion and local human details (e. g., local motion, tiny movement).
CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial Search
Our CPRM framework includes three modules: 1) employing both queries and multi-field item to jointly pre-train for enhancing domain knowledge, 2) applying in-context pre-training, a novel approach where LLMs are pre-trained on a sequence of related queries or items, and 3) conducting reading comprehension on items to produce associated domain knowledge and background information (e. g., generating summaries and corresponding queries) to further strengthen LLMs.
DoubleCCA: Improving Foundation Model Group Robustness with Random Sentence Embeddings
Second, we use an additional sentence embedding model to generate different text embeddings with respect to these random sentences.
D$^3$epth: Self-Supervised Depth Estimation with Dynamic Mask in Dynamic Scenes
First, within the self-supervised framework, we design a reprojection constraint to identify regions likely to contain dynamic objects, allowing the construction of a dynamic mask that mitigates their impact at the loss level.
Diffusion as Reasoning: Enhancing Object Goal Navigation with LLM-Biased Diffusion Model
Diffusion models have been shown to be able to learn the distribution relationships between features in RGB images, and thus generate new realistic images. In this work, we propose a new approach to solving the ObjectNav task, by training a diffusion model to learn the statistical distribution patterns of objects in semantic maps, and using the map of the explored regions during navigation as the condition to generate the map of the unknown regions, thereby realizing the semantic reasoning of the target object, i. e., diffusion as reasoning (DAR).
DMT-HI: MOE-based Hyperbolic Interpretable Deep Manifold Transformation for Unspervised Dimensionality Reduction
DMT-HI enhances DR accuracy by leveraging hyperbolic embeddings to represent the hierarchical nature of data, while also improving interpretability by explicitly linking input data, embedding outcomes, and key features through the MOE structure.
ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos
Then, to fully utilize these representations, we introduce a semi-analytical regressor to estimate the parameters of the human mesh model.
STNet: Deep Audio-Visual Fusion Network for Robust Speaker Tracking
Audio-visual speaker tracking aims to determine the location of human targets in a scene using signals captured by a multi-sensor platform, whose accuracy and robustness can be improved by multi-modal fusion methods.
DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion
The rapid progress of Deepfake technology has made face swapping highly realistic, raising concerns about the malicious use of fabricated facial content.
A Multimodal Object-level Contrast Learning Method for Cancer Survival Risk Prediction
In this paper, we propose a new training method, multimodal object-level contrast learning, for cancer survival risk prediction.
Global-Local Distillation Network-Based Audio-Visual Speaker Tracking with Incomplete Modalities
By transferring knowledge from teacher to student, the student network can better adapt to complex dynamic scenes with incomplete observations.
PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection
The integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection.
ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models
Based on W2*A8 quantization configuration on LLaMA-7B model, it achieved a WikiText2 perplexity of 7. 59 (2. 17$\downarrow $ vs 9. 76 in AffineQuant).
Advancing Multi-grained Alignment for Contrastive Language-Audio Pre-training
Recent advances have been witnessed in audio-language joint learning, such as CLAP, that shows much success in multi-modal understanding tasks.
LiD-FL: Towards List-Decodable Federated Learning
Federated learning is often used in environments with many unverified participants.
ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models
To address these challenges, we propose a controllable grasp generation task and introduce ClickDiff, a controllable conditional generation model that leverages a fine-grained Semantic Contact Map (SCM).
Ranked #1 on
Controllable Grasp Generation
on GRAB
SCMIL: Sparse Context-aware Multiple Instance Learning for Predicting Cancer Survival Probability Distribution in Whole Slide Images
Cancer survival prediction is a challenging task that involves analyzing of the tumor microenvironment within Whole Slide Image (WSI).
USD: Unsupervised Soft Contrastive Learning for Fault Detection in Multivariate Time Series
Unsupervised fault detection in multivariate time series is critical for maintaining the integrity and efficiency of complex systems, with current methodologies largely focusing on statistical and machine learning techniques.
Learning Social Graph for Inactive User Recommendation
In this paper, we propose a novel social recommendation method called LSIR (\textbf{L}earning \textbf{S}ocial Graph for \textbf{I}nactive User \textbf{R}ecommendation) that learns an optimal social graph structure for social recommendation, especially for inactive users.
Transformer-Enhanced Motion Planner: Attention-Guided Sampling for State-Specific Decision Making
EISE and MPT are collaboratively trained, enabling EISE to autonomously learn and extract patterns from environmental data, thereby forming semantic representations that MPT could more effectively interpret and utilize for motion planning.
MLP: Motion Label Prior for Temporal Sentence Localization in Untrimmed 3D Human Motions
In this paper, we address the unexplored question of temporal sentence localization in human motions (TSLM), aiming to locate a target moment from a 3D human motion that semantically corresponds to a text query.
Federated Modality-specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentation
In practice, it is not uncommon that some FL participants only possess a subset of the complete imaging modalities, posing inter-modal heterogeneity as a challenge to effectively training a global model on all participants' data.
AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Adversarial Visual-Instructions
To bridge this gap, we introduce AVIBench, a framework designed to analyze the robustness of LVLMs when facing various adversarial visual-instructions (AVIs), including four types of image-based AVIs, ten types of text-based AVIs, and nine types of content bias AVIs (such as gender, violence, cultural, and racial biases, among others).
WSI-SAM: Multi-resolution Segment Anything Model (SAM) for histopathology whole-slide images
In particular, our model outperforms SAM by 4. 1 and 2. 5 percent points on a ductal carcinoma in situ (DCIS) segmentation tasks and breast cancer metastasis segmentation task (CAMELYON16 dataset).
Identity-aware Dual-constraint Network for Cloth-Changing Person Re-identification
In addition, a Multi-scale Constraint Block (MCB) is designed, which extracts fine-grained identity-related features and effectively transfers cloth-irrelevant knowledge.
Position: Towards Implicit Prompt For Text-To-Image Models
We call for increased attention to the potential and risks of implicit prompts in the T2I community and further investigation into the capabilities and impacts of implicit prompts, advocating for a balanced approach that harnesses their benefits while mitigating their risks.
Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
Given input length $n$, previous works have shown that constant-depth transformers with finite precision $\mathsf{poly}(n)$ embedding size can only solve problems in $\mathsf{TC}^0$ without CoT.
GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks
Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse fields, especially for open-ended tasks.
Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation
We observe that previous optimization-based methods commonly rely on projection constraint, which only ensures alignment in 2D space, potentially leading to the overfitting problem.
Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition
Recognizing interactive actions, including hand-to-hand interaction and human-to-human interaction, has attracted increasing attention for various applications in the field of video analysis and human-robot interaction.
GraphGPT: Graph Learning with Generative Pre-trained Transformers
We introduce \textit{GraphGPT}, a novel model for Graph learning by self-supervised Generative Pre-training Transformers.
Ranked #1 on
Link Property Prediction
on ogbl-citation2
Near-Optimal Resilient Aggregation Rules for Distributed Learning Using 1-Center and 1-Mean Clustering with Outliers
Our analysis show that constant approximations to the 1-center and 1-mean clustering problems with outliers provide near-optimal resilient aggregators for metric-based criteria, which have been proven to be crucial in the homogeneous and heterogeneous cases respectively.
Simultaneous Alignment and Surface Regression Using Hybrid 2D-3D Networks for 3D Coherent Layer Segmentation of Retinal OCT Images with Full and Sparse Annotations
Experiments on a synthetic dataset and three public clinical datasets show that our framework can effectively align the B-scans for potential motion correction, and achieves superior performance to state-of-the-art 2D deep learning methods in terms of both layer segmentation accuracy and cross-B-scan 3D continuity in both fully and semi-supervised settings, thus offering more clinical values than previous works.
Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
Transformers have been successfully applied in the field of video-based 3D human pose estimation.
Prompt Pool based Class-Incremental Continual Learning for Dialog State Tracking
Inspired by the recently emerging prompt tuning method that performs well on dialog systems, we propose to use the prompt pool method, where we maintain a pool of key-value paired prompts and select prompts from the pool according to the distance between the dialog history and the prompt keys.
Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning
We thereby present a new Triplet Partial Margin Contrastive Learning (TPM-CL) module to construct partial order triplet samples by automatically generating fine-grained hard negatives for matched text-video pairs.
Ranked #4 on
Video Retrieval
on MSR-VTT-1kA
Audio-free Prompt Tuning for Language-Audio Models
Contrastive Language-Audio Pretraining (CLAP) is pre-trained to associate audio features with human language, making it a natural zero-shot classifier to recognize unseen sound categories.
Semi-supervised Sound Event Detection with Local and Global Consistency Regularization
Then, the local consistency is adopted to encourage the model to leverage local features for frame-level predictions, and the global consistency is applied to force features to align with global prototypes through a specially designed contrastive loss.
Semantic-aware Consistency Network for Cloth-changing Person Re-Identification
Despite recent progress in CC-ReID, existing approaches are still hindered by the interference of clothing variations since they lack effective constraints to keep the model consistently focused on clothing-irrelevant regions.
Audio Generation with Multiple Conditional Diffusion Model
To address this issue, we propose a novel model that enhances the controllability of existing pre-trained text-to-audio models by incorporating additional conditions including content (timestamp) and style (pitch contour and energy contour) as supplements to the text.
Leveraging Language Model Capabilities for Sound Event Detection
Large language models reveal deep comprehension and fluent generation in the field of multi-modality.
Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video
Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging.
GraphDAC: A Graph-Analytic Approach to Dynamic Airspace Configuration
The current National Airspace System (NAS) is reaching capacity due to increased air traffic, and is based on outdated pre-tactical planning.
UniMatch: A Unified User-Item Matching Framework for the Multi-purpose Merchant Marketing
When doing private domain marketing with cloud services, the merchants usually have to purchase different machine learning models for the multiple marketing purposes, leading to a very high cost.
You've Got Two Teachers: Co-evolutionary Image and Report Distillation for Semi-supervised Anatomical Abnormality Detection in Chest X-ray
Inversely, we also use the prediction of the vision detection model for abnormality-guided pseudo classification label refinement (APCLR) in the auxiliary report classification task, and propose a co-evolution strategy where the vision and report models mutually promote each other with RPDLR and APCLR performed alternatively.
Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
Inspired by SkeletonBYOL, this paper further presents a Cross-Model and Cross-Stream (CMCS) framework.
A Gated Cross-domain Collaborative Network for Underwater Object Detection
Firstly, a real-time UIE method is employed to generate enhanced images, which can improve the visibility of objects in low-contrast areas.
Ranked #1 on
2D Object Detection
on DUO
FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation
Existing skeleton-based action recognition methods typically follow a centralized learning paradigm, which can pose privacy concerns when exposing human-related videos.
Revisiting and Advancing Adversarial Training Through A Simple Baseline
In this paper, we delve into the essential components of adversarial training which is a pioneering defense technique against adversarial attacks.
Sparse-Inductive Generative Adversarial Hashing for Nearest Neighbor Search
In this paper, we propose a novel unsupervised hashing method, termed Sparsity-Induced Generative Adversarial Hashing (SiGAH), to encode large-scale high-dimensional features into binary codes, which well solves the two problems through a generative adversarial training framework.
STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection
To solve this problem, we propose a Self-adapTive Ambiguity Reduction (STAR) loss by exploiting the properties of semantic ambiguity.
Ranked #1 on
Face Alignment
on 300W
Edge-guided Representation Learning for Underwater Object Detection
The key to addressing these challenges is to focus the model on obtaining more discriminative information.
Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
Given the massive cost of language model pre-training, a non-trivial improvement of the optimization algorithm would lead to a material reduction on the time and cost of training.
Exploring Energy-based Language Models with Different Architectures and Training Methods for Speech Recognition
Energy-based language models (ELMs) parameterize an unnormalized distribution for natural sentences and are radically different from popular autoregressive language models (ALMs).
Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervision
Most existing task-oriented dialog (TOD) systems track dialog states in terms of slots and values and use them to query a database to get relevant knowledge to generate responses.
Cross-Modal Retrieval for Motion and Text via DopTriple Loss
On the latest HumanML3D dataset, we achieve a recall of 62. 9% for motion retrieval and 71. 5% for text retrieval (both based on R@10).
Interweaved Graph and Attention Network for 3D Human Pose Estimation
Despite substantial progress in 3D human pose estimation from a single-view image, prior works rarely explore global and local correlations, leading to insufficient learning of human skeleton representations.
Ranked #149 on
3D Human Pose Estimation
on Human3.6M
Solving Dynamic Traveling Salesman Problems With Deep Reinforcement Learning
This brings in a dynamic version of the traveling salesman problem (DTSP), which takes into account the information of real-time traffic and customer requests.
Latent Feature Relation Consistency for Adversarial Robustness
Deep neural networks have been applied in many computer vision tasks and achieved state-of-the-art performance.
GATOR: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D Pose
3D human mesh recovery from a 2D pose plays an important role in various applications.
Ranked #159 on
3D Human Pose Estimation
on Human3.6M
M3AE: Multimodal Representation Learning for Brain Tumor Segmentation with Missing Modalities
In the first stage, a multimodal masked autoencoder (M3AE) is proposed, where both random modalities (i. e., modality dropout) and random patches of the remaining modalities are masked for a reconstruction task, for self-supervised learning of robust multimodal representations against missing modalities.
Feature Completion Transformer for Occluded Person Re-identification
In this paper, different from most previous works that discard the occluded region, we propose a Feature Completion Transformer (FCFormer) to implicitly complement the semantic information of occluded parts in the feature space.
HTNet: Human Topology Aware Network for 3D Human Pose Estimation
3D human pose estimation errors would propagate along the human body topology and accumulate at the end joints of limbs.
Ranked #36 on
3D Human Pose Estimation
on MPI-INF-3DHP
(AUC metric)
AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challenge
Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effective manner, making glaucoma screening more accessible.
Learning Concordant Attention via Target-aware Alignment for Visible-Infrared Person Re-identification
Owing to the large distribution gap between the heterogeneous data in Visible-Infrared Person Re-identification (VI Re-ID), we point out that existing paradigms often suffer from the inter-modal semantic misalignment issue and thus fail to align and compare local details properly.
Uniform Sequence Better: Time Interval Aware Data Augmentation for Sequential Recommendation
However, we observe that the time interval in a sequence may vary significantly different, and thus result in the ineffectiveness of user modeling due to the issue of \emph{preference drift}.
An Unpaired Cross-modality Segmentation Framework Using Data Augmentation and Hybrid Convolutional Networks for Segmenting Vestibular Schwannoma and Cochlea
We adopt two data augmentation methods for effectively learning the semantic information and generating realistic target domain scans: generative and online data augmentation.
Self-distillation with Online Diffusion on Batch Manifolds Improves Deep Metric Learning
However, this type of method normally ignores the crucial knowledge hidden in the data (e. g., intra-class information variation), which is harmful to the generalization of the trained model.
Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models
Toward understanding this implicit bias, we prove that SGD with standard mini-batch noise implicitly prefers flatter minima in language models, and empirically observe a strong correlation between flatness and downstream performance among models with the same minimal pre-training loss.
A Hybrid System of Sound Event Detection Transformer and Frame-wise Model for DCASE 2022 Task 4
For the frame-wise model, the ICT-TOSHIBA system of DCASE 2021 Task 4 is used.
A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems
Second, an important ingredient in a US is that the user goal can be effectively incorporated and tracked; but how to flexibly integrate goal state tracking and develop an end-to-end trainable US for multi-domains has remained to be a challenge.
Jointly Reinforced User Simulator and Task-oriented Dialog System with Simplified Generative Architecture
Recently, there has been progress in supervised funetuning pretrained GPT-2 to build end-to-end task-oriented dialog (TOD) systems.
Information Extraction and Human-Robot Dialogue towards Real-life Tasks: A Baseline Study with the MobileCS Dataset
Recently, there have merged a class of task-oriented dialogue (TOD) datasets collected through Wizard-of-Oz simulated games.
Identity-Sensitive Knowledge Propagation for Cloth-Changing Person Re-identification
To mitigate the resolution degradation issue and mine identity-sensitive cues from human faces, we propose to restore the missing facial details using prior facial knowledge, which is then propagated to a smaller network.
Advancing Semi-Supervised Task Oriented Dialog Systems by JSA Learning of Discrete Latent Variable Models
In this paper, we propose to apply JSA to semi-supervised learning of the latent state TOD models, which is referred to as JSA-TOD.
Spatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction
By this means, STPN allows cross-talk of spatial and temporal factors for modeling delay propagation.
Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition
First, SkeleMix utilizes the topological information of skeleton data to mix two skeleton sequences by randomly combing the cropped skeleton fragments (the trimmed view) with the remaining skeleton sequences (the truncated view).
A Challenge on Semi-Supervised and Reinforced Task-Oriented Dialog Systems
A challenge on Semi-Supervised and Reinforced Task-Oriented Dialog Systems, Co-located with EMNLP2022 SereTOD Workshop.
Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition
To solve this problem, we present a multi-scale spatial graph convolution (MS-GC) module and a multi-scale temporal graph convolution (MT-GC) module to enrich the receptive field of the model in spatial and temporal dimensions.
Transformers Improve Breast Cancer Diagnosis from Unregistered Multi-View Mammograms
For this purpose, we employ local Transformer blocks to separately learn patch relationships within four mammograms acquired from two-view (CC/MLO) of two-side (right/left) breasts.
GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation
To the best of our knowledge, this is the first MLP-Like architecture for 3D human pose estimation in a single frame and a video sequence.
Ranked #61 on
3D Human Pose Estimation
on Human3.6M
AO2-DETR: Arbitrary-Oriented Object Detection Transformer
Comprehensive experiments on several challenging datasets show that our method achieves superior performance on the AOOD task.
Building Markovian Generative Architectures over Pretrained LM Backbones for Efficient Task-Oriented Dialog Systems
Recently, Transformer based pretrained language models (PLMs), such as GPT2 and T5, have been leveraged to build generative task-oriented dialog (TOD) systems.
Breast Cancer Molecular Subtypes Prediction on Pathological Images with Discriminative Patch Selecting and Multi-Instance Learning
A weakly supervised learning framework based on discriminative patch selecting and multi-instance learning was proposed for breast cancer molecular subtype prediction from H&E WSIs.
Simultaneous Alignment and Surface Regression Using Hybrid 2D-3D Networks for 3D Coherent Layer Segmentation of Retina OCT Images
To the best of our knowledge, this is the first study that attempts 3D retinal layer segmentation in volumetric OCT images based on CNNs.
Virtual Adversarial Training for Semi-supervised Breast Mass Classification
This study aims to develop a novel computer-aided diagnosis (CAD) scheme for mammographic breast mass classification using semi-supervised learning.
Facial-Sketch Synthesis: A New Challenge
Besides, we elaborate comprehensive experiments on the existing 19 cutting-edge models.
Multi-Modal Perception Attention Network with Self-Supervised Learning for Audio-Visual Speaker Tracking
Multi-modal fusion is proven to be an effective method to improve the accuracy and robustness of speaker tracking, especially in complex scenarios.
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition
In this paper, to make better use of the movement patterns introduced by extreme augmentations, a Contrastive Learning framework utilizing Abundant Information Mining for self-supervised action Representation (AimCLR) is proposed.
Contrastive Learning
Few-Shot Skeleton-Based Action Recognition
+5
Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer
Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e. g. human body or joint parts) and selectively match non-occluded parts correspondingly.
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion.
Ranked #24 on
3D Human Pose Estimation
on MPI-INF-3DHP
Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels
This framework consists of three key components, i. e., a pseudo-edge generator, a pseudo-map generator, and an uncertainty-aware refinement module.
Empowering General-purpose User Representation with Full-life Cycle Behavior Modeling
User Modeling plays an essential role in industry.
Self-supervised Learning is More Robust to Dataset Imbalance
Third, inspired by the theoretical insights, we devise a re-weighted regularization technique that consistently improves the SSL representation quality on imbalanced datasets with several evaluation criteria, closing the small gap between balanced and imbalanced datasets with the same number of examples.
Ranked #10 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection
A critical issue with the frame-based model is that it pursues the best frame-level prediction rather than the best event-level prediction.
Learning Universal User Representations via Self-Supervised Lifelong Behaviors Modeling
However, existing researches have little ability to model universal user representation based on lifelong behavior sequences since user registration.
Interest-oriented Universal User Representation via Contrastive Learning
Universal user representation has received many interests recently, with which we can be free from the cumbersome work of training a specific model for each downstream application.
Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems
In this paper, we propose Variational Latent-State GPT model (VLS-GPT), which is the first to combine the strengths of the two approaches.
Transformer for Single Image Super-Resolution
LTB is composed of a series of Efficient Transformers (ET), which occupies a small GPU memory occupation, thanks to the specially designed Efficient Multi-Head Attention (EMHA).
Towards Robustness Against Natural Language Word Substitutions
Robustness against word substitutions has a well-defined and widely acceptable form, i. e., using semantically similar words as substitutions, and thus it is considered as a fundamental stepping-stone towards broader robustness in natural language processing.
Recent advances and clinical applications of deep learning in medical image analysis
Deep learning has received extensive research interest in developing new medical image processing algorithms, and deep learning based models have been remarkably successful in a variety of medical imaging tasks to support disease detection and diagnosis.
Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network
Instead, exploiting multi-view information is a practical way to achieve absolute 3D human pose estimation.
Monocular 3D Human Pose Estimation
Weakly-supervised 3D Human Pose Estimation
+1
Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack
We argue this is due to the lack of rich information in the probability prediction and the overfitting caused by hard labels.
Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learning
Second, for the images with the same semantic content in different domains, their hidden features should be equivalent.
Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation
The modified VTE is termed as Strided Transformer Encoder (STE), which is built upon the outputs of VTE.
Ranked #2 on
3D Human Pose Estimation
on HumanEva-I
Cycle Self-Training for Domain Adaptation
In the forward step, CST generates target pseudo-labels with a source-trained classifier.
Stability from graph symmetrisation arguments with applications to inducibility
We present a sufficient condition for the stability property of extremal graph problems that can be solved via Zykov's symmetrisation.
Combinatorics
Part-based Lipreading for Audio-Visual Speech Recognition
In this paper, A part-based lipreading (PBL) method is proposed to deal with the mismatch between an overall lip model and the separate parts of lips, also the excessive dependence of models on the speakers in training set.
Ranked #3 on
Audio-Visual Speech Recognition
on LRW
Multi-Scale Cascading Network with Compact Feature Learning for RGB-Infrared Person Re-Identification
RGB-Infrared person re-identification (RGB-IR Re-ID) aims to match persons from heterogeneous images captured by visible and thermal cameras, which is of great significance in the surveillance system under poor light conditions.
Extremal density for sparse minors and subdivisions
We prove an asymptotically tight bound on the extremal density guaranteeing subdivisions of bounded-degree bipartite graphs with a mild separability condition.
Combinatorics 05C83, 05C35
Learning to Adapt to Evolving Domains
(2) Since the target data arrive online, the agent should also maintain competence on previous target domains, i. e. to adapt without forgetting.
Meta-learning Transferable Representations with a Single Target Domain
Recent works found that fine-tuning and joint training---two popular approaches for transfer learning---do not always improve accuracy on downstream tasks.
Lip Graph Assisted Audio-Visual Speech Recognition Using Bidirectional Synchronous Fusion
Second, the hybrid visual stream is combined with the audio stream by an attention-based bidirectional synchronous fusion which allows bidirectional information interaction to resolve the asynchrony between the two modalities during fusion.
Ranked #5 on
Landmark-based Lipreading
on LRW
Audio-Visual Speech Recognition
Landmark-based Lipreading
+2
Applying a random projection algorithm to optimize machine learning model for breast lesion classification
Then, support vector machine (SVM) models embedded with several feature dimensionality reduction methods are built to predict likelihood of lesions being malignant.
Anti-Bandit Neural Architecture Search for Model Defense
Deep convolutional neural networks (DCNNs) have dominated as the best performers in machine learning, but can be challenged by adversarial attacks.
Two-stage growth mode for lift-off mechanism in oblique shock-wave/jet interaction
Based on the objective coordinate system in frame of oblique shock structure, it is found that the nature of three-dimensional lift-off structure of a shockinduced streamwise vortex is inherently and precisely controlled by a two-stage growth mode of structure kinetics of a shock bubble interaction (SBI for short).
Fluid Dynamics
Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification
As an angularly discriminative feature space is important for classifying the human images based on their embedding vectors, in this paper, we propose a novel ranking loss function, named Bi-directional Exponential Angular Triplet Loss, to help learn an angularly separable common feature space by explicitly constraining the included angles between embedding vectors.
When Dictionary Learning Meets Deep Learning: Deep Dictionary Learning and Coding Network for Image Recognition with Limited Data
Then the activated dictionary atoms are assembled and passed to the compound dictionary learning and coding layers.
Projection & Probability-Driven Black-Box Attack
For reducing the solution space, we first model the adversarial perturbation optimization problem as a process of recovering frequency-sparse perturbations with compressed sensing, under the setting that random noise in the low-frequency space is more likely to be adversarial.
WQT and DG-YOLO: towards domain generalization in underwater object detection
This paper aims to build a GUOD with small underwater dataset with limited types of water quality.
Online Initialization and Extrinsic Spatial-Temporal Calibration for Monocular Visual-Inertial Odometry
To compensate for the impact of time offset, our method includes two short-term motion interpolation algorithms for the camera and IMU pose estimation.
Spatial Pyramid Based Graph Reasoning for Semantic Segmentation
The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation.
A Survey on 3D Skeleton-Based Action Recognition Using Learning Method
To the best of our knowledge, this research represents the first comprehensive discussion of deep learning-based action recognition using 3D skeleton data.
Unified Generative Adversarial Networks for Controllable Image-to-Image Translation
The proposed model consists of a single generator and a discriminator taking a conditional image and the target controllable structure as input.
Ranked #1 on
Cross-View Image-to-Image Translation
on cvusa
Facial Expression Translation
Generative Adversarial Network
+3
AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks
State-of-the-art methods in image-to-image translation are capable of learning a mapping from a source domain to a target domain with unpaired image data.
Ranked #1 on
Facial Expression Translation
on CelebA
An End-to-end Approach for Lexical Stress Detection based on Transformer
For this, we train transformer model using feature sequence of audio and their phoneme sequence with lexical stress marks.
Universal Adversarial Perturbation via Prior Driven Uncertainty Approximation
Deep learning models have shown their vulnerabilities to universal adversarial perturbations (UAP), which are quasi-imperceptible.
Towards Understanding the Transferability of Deep Representations
3) The feasibility of transferability is related to the similarity of both input and label.
Guided Learning Convolution System for DCASE 2019 Task 4
In this paper, we describe in detail the system we submitted to DCASE2019 task 4: sound event detection (SED) in domestic environments.
Expectation-Maximization Attention Networks for Semantic Segmentation
It is designed to compute the representation of each position by a weighted sum of the features at all positions.
Ranked #6 on
Semantic Segmentation
on BDD100K val
Identifying Illicit Accounts in Large Scale E-payment Networks -- A Graph Representation Learning Approach
In the context of e-payment transaction graphs, the resultant node and edge embeddings can effectively characterize the user-background as well as the financial transaction patterns of individual account holders.
Guided learning for weakly-labeled semi-supervised sound event detection
Instead of designing a single model by considering a trade-off between the two sub-targets, we design a teacher model aiming at audio tagging to guide a student model aiming at boundary detection to learn using the unlabeled data.
Separate to Adapt: Open Set Domain Adaptation via Progressive Separation
While several methods have been proposed to address OSDA, none of them takes into account the openness of the target domain, which is measured by the proportion of unknown classes in all target classes.
Specialized Decision Surface and Disentangled Feature for Weakly-Supervised Polyphonic Sound Event Detection
In this paper, a special decision surface for the weakly-supervised sound event detection (SED) and a disentangled feature (DF) for the multi-label problem in polyphonic SED are proposed.
A novel algorithm for segmentation of leukocytes in peripheral blood
First, the nucleus of leukocyte was separated by using the stepwise averaging method.
Dual-branch residual network for lung nodule segmentation
Experimental results show that the DB-ResNet achieves superior segmentation performance with an average dice score of 82. 74% on the dataset.
Hadamard Matrix Guided Online Hashing
We then treat the learning of hash functions as a set of binary classification problems to fit the assigned target code.
Two-Stage Convolutional Neural Network Architecture for Lung Nodule Detection
The CNN architecture in the first stage is based on the improved UNet segmentation network to establish an initial detection of lung nodules.
Supervised Online Hashing via Hadamard Codebook Learning
Notably, the proposed HCOH can be embedded with supervised labels and it not limited to a predefined category number.
Multi-view Vector-valued Manifold Regularization for Multi-label Image Classification
In computer vision, image datasets used for classification are naturally associated with multiple labels and comprised of multiple views, because each image may contain several objects (e. g. pedestrian, bicycle and tree) and is properly characterized by multiple visual features (e. g. color, texture and shape).
Towards Optimal Discrete Online Hashing with Balanced Similarity
In this paper, we propose a novel supervised online hashing method, termed Balanced Similarity for Online Discrete Hashing (BSODH), to solve the above problems in a unified framework.
Fast and Robust Dynamic Hand Gesture Recognition via Key Frames Extraction and Feature Fusion
Gesture recognition is a hot topic in computer vision and pattern recognition, which plays a vitally important role in natural human-computer interface.
Ranked #1 on
Hand Gesture Recognition
on Cambridge