Search Results for author:
Found 275 papers, 62 papers with code
Learning Progressive Joint Propagation for Human Motion Prediction
Last, in order to incorporate a general motion space for high-quality prediction, we build a memory-based dictionary, which aims to preserve the global motion patterns in training data to guide the predictions.
HARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity Prediction
In this paper, we propose a novel Hardness-AwaRe Discrimination Network (HARD-Net) to specifically investigate the relationships between the similar activity pairs that are hard to be discriminated.
Ranked #4 on
Skeleton Based Action Recognition
on UAV-Human
OID: Outlier Identifying and Discarding in Blind Image Deblurring
Even a small amount of outliers can dramatically degrade the quality of the estimated blur kernel, because the outliers are not conforming to the linear formation of the blurring process.
Collaborative Learning of Gesture Recognition and 3D Hand Pose Estimation with Multi-Order Feature Analysis
The proposed network exploits joint-aware features that are crucial for both tasks, with which gesture recognition and 3D hand pose estimation boost each other to learn highly discriminative features and models.
Adaptive Computationally Efficient Network for Monocular 3D Hand Pose Estimation
A novel model, called Adaptive Computationally Efficient (ACE) network, is proposed, which takes advantage of a Gaussian kernel based Gate Module to dynamically switch the computation between a light model and a heavy network for feature extraction.
Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering
The former leads to a large, diverse test space, while the latter results in a comprehensive robustness evaluation on rare, frequent, and overall questions.
An Interpretable Power System Transient Stability Assessment Method with Expert Guiding Neural-Regression-Tree
TSA-ENRT utilizes an expert guiding nonlinear regression tree to approximate the neural network prediction and the neural network can be explained by the interpretive rules generated by the tree model.
Action Detection via an Image Diffusion Process
Action detection aims to localize the starting and ending points of action instances in untrimmed videos, and predict the classes of those instances.
LLMs are Good Sign Language Translators
Sign Language Translation (SLT) is a challenging task that aims to translate sign videos into spoken language.
LLMs are Good Action Recognizers
Motivated by this, we propose a novel LLM-AR framework, in which we investigate treating the Large Language Model as an Action Recognizer.
Learning Piecewise Residuals of Control Barrier Functions for Safety of Switching Systems using Multi-Output Gaussian Processes
This uncertainty results in piecewise residuals for each switching surface, impacting the CLF and CBF constraints.
Manifold-Guided Lyapunov Control with Diffusion Models
This paper presents a novel approach to generating stabilizing controllers for a large class of dynamical systems using diffusion models.
GPT-Connect: Interaction between Text-Driven Human Motion Generator and 3D Scenes in a Training-free Manner
Recently, while text-driven human motion generation has received massive research attention, most existing text-driven motion generators are generally only designed to generate motion sequences in a blank background.
SoftPatch: Unsupervised Anomaly Detection with Noisy Data
Noise discriminators are utilized to generate outlier scores for patch-level noise elimination before coreset construction.
Efficient Pruning of Large Language Model with Adaptive Estimation Fusion
Large language models (LLMs) have become crucial for many generative downstream tasks, leading to an inevitable trend and significant challenge to deploy them efficiently on resource-constrained devices.
Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning
Human-centered dynamic scene understanding plays a pivotal role in enhancing the capability of robotic and autonomous systems, in which Video-based Human-Object Interaction (V-HOI) detection is a crucial task in semantic scene understanding, aimed at comprehensively understanding HOI relationships within a video to benefit the behavioral decisions of mobile robots and autonomous driving systems.
LyZNet: A Lightweight Python Tool for Learning and Verifying Neural Lyapunov Functions and Regions of Attraction
In this paper, we describe a lightweight Python framework that provides integrated learning and verification of neural Lyapunov functions for stability analysis.
Compositionally Verifiable Vector Neural Lyapunov Functions for Stability Analysis of Interconnected Nonlinear Systems
While there has been increasing interest in using neural networks to compute Lyapunov functions, verifying that these functions satisfy the Lyapunov conditions and certifying stability regions remain challenging due to the curse of dimensionality.
Learning High-Order Control Barrier Functions for Safety-Critical Control with Gaussian Processes
However, the effectiveness of CBFs is closely tied to the system model.
CRB Analysis for Mixed-ADC Based DOA Estimation
The Cram{\'e}r-Rao bound (CRB) with the antenna-varying threshold is obtained.
LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content
Long-tail recognition is challenging because it requires the model to learn good representations from tail categories and address imbalances across all categories.
InstructGIE: Towards Generalizable Image Editing
In response to this challenge, our study introduces a novel image editing framework with enhanced generalization robustness by boosting in-context learning capability and unifying language instruction.
IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding
Despite achieving rapid developments and with widespread applications, Large Vision-Language Models (LVLMs) confront a serious challenge of being prone to generating hallucinations.
An inexact Bregman proximal point method and its acceleration version for unbalanced optimal transport
The algorithm (1) converges to the true solution of UOT, (2) has theoretical guarantees and robust regularization parameter selection, (3) mitigates numerical stability issues, and (4) can achieve comparable computational complexity to the Scaling algorithm in specific practice.
Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification
We provide a theoretical analysis of both algorithms in terms of convergence of neural approximations towards the true optimal solutions in a general setting.
Denoising Diffusion Restoration Tackles Forward and Inverse Problems for the Laplace Operator
Equivalently, we present an approach to restore the solution and the parameters in the Poisson equation by exploiting the eigenvalues and the eigenfunctions of the Laplacian operator.
Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment
For a support sequence, we match it with view-simulated query sequences, as in the popular Dynamic Time Warping (DTW).
AoSRNet: All-in-One Scene Recovery Networks via Multi-knowledge Integration
Additionally, we suggest a multi-receptive field extraction module (MEM) to attenuate the loss of image texture details caused by GC nonlinear and OLS linear transformations.
Source-free Domain Adaptive Object Detection in Remote Sensing Images
To address this challenge, we propose a practical source-free object detection (SFOD) setting for RS images, which aims to perform target domain adaptation using only the source pre-trained model.
Left-right Discrepancy for Adversarial Attack on Stereo Networks
Stereo matching neural networks often involve a Siamese structure to extract intermediate features from left and right images.
Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery
The key challenges of GRD are how to mitigate the serious model biases caused by labeled pre-defined relations to learn effective relational representations and how to determine the specific semantics of novel relations during classifying or clustering unlabeled instances.
FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs
However, existing GPU and transformer-based accelerators cannot efficiently process compressed LLMs, due to the following unresolved challenges: low computational efficiency, underutilized memory bandwidth, and large compilation overheads.
Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports
Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval.
Double-well Net for Image Segmentation
In this study, our goal is to integrate classical mathematical models with deep neural networks by introducing two novel deep neural network models for image segmentation known as Double-well Nets.
6D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimation
Estimating the 6D object pose from a single RGB image often involves noise and indeterminacy due to challenges such as occlusions and cluttered backgrounds.
Stochastic Control Barrier Functions with Bayesian Inference for Unknown Stochastic Differential Equations
Control barrier functions are widely used to synthesize safety-critical controls.
MatchDet: A Collaborative Framework for Image Matching and Object Detection
Image matching and object detection are two fundamental and challenging tasks, while many related applications consider them two individual tasks (i. e. task-individual).
Physics-Informed Neural Network Lyapunov Functions: PDE Characterization, Learning, and Verification
We provide a systematic investigation of using physics-informed neural networks to compute Lyapunov functions.
CattleEyeView: A Multi-task Top-down View Cattle Dataset for Smarter Precision Livestock Farming
Cattle farming is one of the important and profitable agricultural industries.
MWSIS: Multimodal Weakly Supervised Instance Segmentation with 2D Box Annotations for Autonomous Driving
Instance segmentation is a fundamental research in computer vision, especially in autonomous driving.
LLaFS: When Large Language Models Meet Few-Shot Segmentation
This paper proposes LLaFS, the first attempt to leverage large language models (LLMs) in few-shot segmentation.
Enabling Fast 2-bit LLM on GPUs: Memory Alignment and Asynchronous Dequantization
Weights are quantized by groups, while the ranges of weights are large in some groups, resulting in large quantization errors and nonnegligible accuracy loss (e. g. >3% for Llama2-7b with 2-bit quantization in GPTQ and Greenbit).
ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation
The main idea of our approach is to explore the natural relationship between multi-view correspondences and the prompt mechanism of foundational models and build bridges on it.
Trustworthy Large Models in Vision: A Survey
The rapid progress of Large Models (LMs) has recently revolutionized various fields of deep learning with remarkable grades, ranging from Natural Language Processing (NLP) to Computer Vision (CV).
Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models
Although Large Language Models (LLMs) demonstrate remarkable ability in processing and generating human-like text, they do have limitations when it comes to comprehending and expressing world knowledge that extends beyond the boundaries of natural language(e. g., chemical molecular formula).
Holistic Evaluation of GPT-4V for Biomedical Imaging
GPT-4V represents a breakthrough in artificial general intelligence (AGI) for computer vision, with applications in the biomedical domain.
FlashDecoding++: Faster Large Language Model Inference on GPUs
A single and static dataflow may lead to a 50. 25% performance loss for GEMMs of different shapes in LLM inference.
FuXi-Extreme: Improving extreme rainfall and wind forecasts with diffusion model
State-of-the-art ML-based weather forecast models, such as FuXi, have demonstrated superior statistical forecast performance in comparison to the high-resolution forecasts (HRES) of the European Centre for Medium-Range Weather Forecasts (ECMWF).
Recoverable Privacy-Preserving Image Classification through Noise-like Adversarial Examples
Extensive experiments demonstrate that 1) the classification accuracy of the classifier trained in the plaintext domain remains the same in both the ciphertext and plaintext domains; 2) the encrypted images can be recovered into their original form with an average PSNR of up to 51+ dB for the SVHN dataset and 48+ dB for the VGGFace2 dataset; 3) our system exhibits satisfactory generalization capability on the encryption, decryption and classification tasks across datasets that are different from the training one; and 4) a high-level of security is achieved against three potential threat models.
Generating Robust Adversarial Examples against Online Social Networks (OSNs)
In this work, we aim to design a new framework for generating robust AEs that can survive the OSN transmission; namely, the AEs before and after the OSN transmission both possess strong attack capabilities.
Learning Comprehensive Representations with Richer Self for Text-to-Image Person Re-Identification
Since the support set is unavailable during inference, we propose to distill the knowledge learned by the "richer" model into a lightweight model for inference with a single image/text as input.
MAC: ModAlity Calibration for Object Detection
The flourishing success of Deep Neural Networks(DNNs) on RGB-input perception tasks has opened unbounded possibilities for non-RGB-input perception tasks, such as object detection from wireless signals, lidar scans, and infrared images.
ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data
Radiology report generation, as a key step in medical image analysis, is critical to the quantitative analysis of clinically informed decision-making levels.
Harmonic Control Lyapunov Barrier Functions for Constrained Optimal Control with Reach-Avoid Specifications
This paper introduces harmonic control Lyapunov barrier functions (harmonic CLBF) that aid in constrained control problems such as reach-avoid problems.
Revisiting Cephalometric Landmark Detection from the view of Human Pose Estimation with Lightweight Super-Resolution Head
Accurate localization of cephalometric landmarks holds great importance in the fields of orthodontics and orthognathics due to its potential for automating key point labeling.
LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition
Open-set object recognition aims to identify if an object is from a class that has been encountered during training or not.
CloudBrain-NMR: An Intelligent Cloud Computing Platform for NMR Spectroscopy Processing, Reconstruction and Analysis
Particularly, the emerging deep learning tools is hard to be widely used in NMR due to the sophisticated setup of computation.
Deep Learning Overloaded Vehicle Identification for Long Span Bridges Based on Structural Health Monitoring Data
In this paper, a deep learning based overloaded vehicle identification approach (DOVI) is proposed, with the purpose of overloaded vehicle identification for long-span bridges by the use of structural health monitoring data.
Radiology-Llama2: Best-in-Class Large Language Model for Radiology
This paper introduces Radiology-Llama2, a large language model specialized for radiology through a process known as instruction tuning.
AI-Generated Content (AIGC) for Various Data Modalities: A Survey
Due to its wide range of applications and the demonstrated potential of recent works, AIGC developments have been attracting lots of attention recently, and AIGC methods have been developed for various data modalities, such as image, video, text, 3D shape (as voxels, point clouds, meshes, and neural implicit fields), 3D scene, 3D human avatar (body and head), 3D motion, and audio -- each presenting different characteristics and challenges.
Unsupervised Domain Adaptation via Domain-Adaptive Diffusion
Unsupervised Domain Adaptation (UDA) is quite challenging due to the large distribution discrepancy between the source domain and the target domain.
DISGO: Automatic End-to-End Evaluation for Scene Text OCR
This paper discusses the challenges of optical character recognition (OCR) on natural scenes, which is harder than OCR on documents due to the wild content and various image backgrounds.
Distribution-Aligned Diffusion for Human Mesh Recovery
Inspired by their capability, we explore a diffusion-based approach for human mesh recovery, and propose a Human Mesh Diffusion (HMDiff) framework which frames mesh recovery as a reverse diffusion process.
Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation
Translating images from a source domain to a target domain for learning target models is one of the most common strategies in domain adaptive semantic segmentation (DASS).
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition
In the analysis and ablation study, we demonstrate that our method compared with previous work can effectively increase the diversity of experts, significantly reduce the variance of the model, and improve recognition accuracy.
Ranked #5 on
Long-tail Learning
on CIFAR-10-LT (ρ=50)
Learning Gabor Texture Features for Fine-Grained Recognition
We innovatively utilize Gabor filters as a powerful extractor to exploit texture features, motivated by the capability of Gabor filters in effectively capturing multi-frequency features and detailed local information.
M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition
Due to the scarcity of manually annotated data required for fine-grained video understanding, few-shot fine-grained (FS-FG) action recognition has gained significant attention, with the aim of classifying novel fine-grained action categories with only a few labeled instances.
Evaluating Large Language Models for Radiology Natural Language Processing
The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP).
A Theoretically Guaranteed Quaternion Weighted Schatten p-norm Minimization Method for Color Image Restoration
Very recently, a quaternion-based WNNM approach (QWNNM) has been developed to mitigate this issue, which is capable of representing the color image as a whole in the quaternion domain and preserving the inherent correlation among the three color channels.
Robust Visual Question Answering: Datasets, Methods, and Future Challenges
Specifically, we first provide an overview of the development process of datasets from in-distribution and out-of-distribution perspectives.
One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching
The first is multi-scale matching which captures the scale-wise semantic relevance of skeleton data at multiple spatial and temporal scales simultaneously.
Interpretable Small Training Set Image Segmentation Network Originated from Multi-Grid Variational Model
The main objective of image segmentation is to divide an image into homogeneous regions for further analysis.
Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond
Firstly, to offer systematic evaluations, we select fifteen typical logical reasoning datasets and organize them into deductive, inductive, abductive and mixed-form reasoning settings.
Radiology-GPT: A Large Language Model for Radiology
We introduce Radiology-GPT, a large language model for radiology.
Artificial General Intelligence for Medical Imaging
In this review, we explore the potential applications of Artificial General Intelligence (AGI) models in healthcare, focusing on foundational Large Language Models (LLMs), Large Vision Models, and Large Multimodal Models.
Actor-Critic Methods using Physics-Informed Neural Networks: Control of a 1D PDE Model for Fluid-Cooled Battery Packs
The Hamilton-Jacobi-Bellman (HJB) equation is a PDE that evaluates the optimality of the value function and determines an optimal controller.
Adaptive loose optimization for robust question answering
Question answering methods are well-known for leveraging data bias, such as the language prior in visual question answering and the position bias in machine reading comprehension (extractive question answering).
Extractive Question-Answering
Machine Reading Comprehension
+2
MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer
TransMix uses unreliable attention maps to compute mixed attention labels that can affect the model.
Ranked #1 on
Data Augmentation
on ImageNet
Clustered-patch Element Connection for Few-shot Learning
According to this, we propose a novel Clustered-patch Element Connection (CEC) layer to correct the mismatch problem.
Ranked #47 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization
We investigate self-supervised representation learning and design a novel skeleton cloud colorization technique that is capable of learning spatial and temporal skeleton representations from unlabeled skeleton sequence data.
Continual Semantic Segmentation with Automatic Memory Sample Selection
Continual Semantic Segmentation (CSS) extends static semantic segmentation by incrementally introducing new classes for training.
Meta Compositional Referring Expression Segmentation
Then, following a novel meta optimization scheme to optimize the model to obtain good testing performance on the virtual testing sets after training on the virtual training set, our framework can effectively drive the model to better capture semantics and visual representations of individual concepts, and thus obtain robust generalization performance even when handling novel compositions.
Token Boosting for Robust Self-Supervised Visual Transformer Pre-training
Pre-training VTs on such corrupted data can be challenging, especially when we pre-train via the masked autoencoding approach, where both the inputs and masked ``ground truth" targets can potentially be unreliable in this case.
Efficient automatic segmentation for multi-level pulmonary arteries: The PARSE challenge
Efficient automatic segmentation of multi-level (i. e. main and branch) pulmonary arteries (PA) in CTPA images plays a significant role in clinical applications.
Progressive Channel-Shrinking Network
Currently, salience-based channel pruning makes continuous breakthroughs in network compression.
GradMDM: Adversarial Attack on Dynamic Networks
Dynamic neural networks can greatly reduce computation redundancy without compromising accuracy by adapting their structures based on the input.
System-status-aware Adaptive Network for Online Streaming Video Understanding
Recent years have witnessed great progress in deep neural networks for real-time applications.
Optimal Mixed-ADC arrangement for DOA Estimation via CRB using ULA
Simulation results show the validity of the asymptotic CRB and better performance under the optimal mixed-precision arrangement.
SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning
Then we derive two specific attention modules, named SpatialFormer Semantic Attention (SFSA) and SpatialFormer Target Attention (SFTA), to enhance the target object regions while reduce the background distraction.
Precise Facial Landmark Detection by Reference Heatmap Transformer
Most facial landmark detection methods predict landmarks by mapping the input facial appearance features to landmark heatmaps and have achieved promising results.
Robustly Complete Finite-State Abstractions for Control Synthesis of Stochastic Systems
The essential step of abstraction-based control synthesis for nonlinear systems to satisfy a given specification is to obtain a finite-state abstraction of the original systems.
Almost Sure Saddle Avoidance of Stochastic Gradient Methods without the Bounded Gradient Assumption
We prove that various stochastic gradient descent methods, including the stochastic gradient descent (SGD), stochastic heavy-ball (SHB), and stochastic Nesterov's accelerated gradient (SNAG) methods, almost surely avoid any strict saddle manifold.
Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models
Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within videos.
Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)
The Proximal Policy Optimization (PPO)-Clipped algorithm is improvised with this implementation as it uses a value network to compute the objective function for its policy network.
Modeling Uncertain Feature Representation for Domain Generalization
In this paper, we improve the network generalization ability by modeling domain shifts with uncertainty (DSU), i. e., characterizing the feature statistics as uncertain distributions during training.
The state-of-the-art 3D anisotropic intracranial hemorrhage segmentation on non-contrast head CT: The INSTANCE challenge
It is intended to resolve the above-mentioned problems and promote the development of both intracranial hemorrhage segmentation and anisotropic data processing.
Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text
(2) How to enhance the perception of reasoning types for the models?
STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition
For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i. e., sparsification and anonymization, to remove privacy from a spatio-temporal perspective.
Instance and Category Supervision are Alternate Learners for Continual Learning
Continual Learning (CL) is the constant development of complex behaviors by building upon previously acquired skills.
Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling
In this paper, we propose a space decoupling (SD) algorithm to decouple the feature space into a pair of complementary subspaces, i. e., the stability space I, and the plasticity space R. I is established by conducting space intersection between the historic and current feature space, and thus I contains more task-shared bases.
Bi-Directional Feature Fusion Generative Adversarial Network for Ultra-High Resolution Pathological Image Virtual Re-Staining
In order to eliminate the square effect, we design a bi-directional feature fusion generative adversarial network (BFF-GAN) with a global branch and a local branch.
A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation
Therefore, via minimizing the distance between the two characteristic functions, we can optimize the model to provide a more accurate localization result for the body joints in different sub-regions of the predicted heatmap.
Chaotic World: A Large and Challenging Benchmark for Human Behavior Understanding in Chaotic Events
Understanding and analyzing human behaviors (actions and interactions of people), voices, and sounds in chaotic events is crucial in many applications, e. g., crowd management, emergency response services.
Unified Pose Sequence Modeling
We propose a Unified Pose Sequence Modeling approach to unify heterogeneous human behavior understanding tasks based on pose data, e. g., action recognition, 3D pose estimation and 3D early action prediction.
Heterogeneous Diversity Driven Active Learning for Multi-Object Tracking
HD-AMOT defines the diversified informative representation by encoding the geometric and semantic information, and formulates the frame inference strategy as a Markov decision process to learn an optimal sampling policy based on the designed informative representation.
GPTR: Gestalt-Perception Transformer for Diagram Object Detection
These lead to the fact that traditional data-driven detection model is not suitable for diagrams.
HDNet: A Hierarchically Decoupled Network for Crowd Counting
Recently, density map regression-based methods have dominated in crowd counting owing to their excellent fitting ability on density distribution.
DiffPose: Toward More Reliable 3D Pose Estimation
Monocular 3D human pose estimation is quite challenging due to the inherent ambiguity and occlusion, which often lead to high uncertainty and indeterminacy.
Ranked #11 on
3D Human Pose Estimation
on MPI-INF-3DHP
Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision
This paper builds a unified framework to perform effective noisy-proposal suppression and to interact between global and local features for robust feature learning.
Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective
In this paper, for the first time, we investigate the contributions of different distance metrics, and propose an adaptive fusion scheme, bringing significant improvements in few-shot classification.
tSF: Transformer-based Semantic Filter for Few-Shot Learning
Few-Shot Learning (FSL) alleviates the data shortage challenge via embedding discriminative target-aware features among plenty seen (base) and few unseen (novel) labeled samples.
Improving the Reliability for Confidence Estimation
Confidence estimation, a task that aims to evaluate the trustworthiness of the model's prediction output during deployment, has received lots of research attention recently, due to its importance for the safe deployment of deep models.
Towards Continual Adaptation in Industrial Anomaly Detection
We believe that the proposed task and benchmark will be beneficial to the field of AD.
Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior
To address this challenge, we suggest a dataset-free deep residual prior for the kernel induced error (termed as residual) expressed by a customized untrained deep neural network, which allows us to flexibly adapt to different blurs and images in real scenarios.
Heatmap Distribution Matching for Human Pose Estimation
In this paper, we show that optimizing the heatmap prediction in such a way, the model performance of body joint localization, which is the intrinsic objective of this task, may not be consistently improved during the optimization process of the heatmap prediction.
Downlink Compression Improves TopK Sparsification
One of the largest bottlenecks in distributed training is communicating gradients across different nodes.
Multiple Control Barrier Functions: An Application to Reactive Obstacle Avoidance for a Multi-steering Tractor-trailer System
We develop a control structure based on a multiple CBFs scheme for a multi-steering tractor-trailer system to ensure a collision-free maneuver for both the tractor and trailer in the presence of several obstacles.
nVFNet-RDC: Replay and Non-Local Distillation Collaboration for Continual Object Detection
Continual Learning (CL) focuses on developing algorithms with the ability to adapt to new environments and learn new skills.
Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation
This paper focus on few-shot object detection~(FSOD) and instance segmentation~(FSIS), which requires a model to quickly adapt to novel classes with a few labeled instances.
Ranked #3 on
Few-Shot Object Detection
on MS-COCO (1-shot)
Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition
We design a novel Dynamic Spatio-Temporal Specialization (DSTS) module, which consists of specialized neurons that are only activated for a subset of samples that are highly similar.
Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation
Second, to resist overfitting issues caused by few training samples, a hyper-class embedding is learned by clustering all category embeddings for initialization and aligned with category embedding of the new class for enhancement, where learned knowledge assists to learn new knowledge, thus alleviating performance dependence on training data scale.
IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition
Human interaction recognition is very important in many applications.
Ranked #2 on
Human Interaction Recognition
on SBU
Meta Spatio-Temporal Debiasing for Video Scene Graph Generation
Video scene graph generation (VidSGG) aims to parse the video content into scene graphs, which involves modeling the spatio-temporal contextual information in the video.
ERA: Expert Retrieval and Assembly for Early Action Prediction
Early action prediction aims to successfully predict the class label of an action before it is completely performed.
Position-prior Clustering-based Self-attention Module for Knee Cartilage Segmentation
The morphological changes in knee cartilage (especially femoral and tibial cartilages) are closely related to the progression of knee osteoarthritis, which is expressed by magnetic resonance (MR) images and assessed on the cartilage segmentation results.
Neural Lyapunov Control of Unknown Nonlinear Systems with Stability Guarantees
This paper proposes a learning framework to simultaneously stabilize an unknown nonlinear system with a neural controller and learn a neural Lyapunov function to certify a region of attraction (ROA) for the closed-loop system.
Data-Driven Learning of Safety-Critical Control with Stochastic Control Barrier Functions
More specifically, we propose a data-driven stochastic control barrier function (DDSCBF) framework and use supervised learning to learn the unknown stochastic dynamics via the DDSCBF scheme.
GDSRec: Graph-Based Decentralized Collaborative Filtering for Social Recommendation
However, existing graph-based methods fails to consider the bias offsets of users (items).
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Surface Representation for Point Clouds
Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency.
Ranked #6 on
3D Point Cloud Classification
on ModelNet40
Deeply Supervised Skin Lesions Diagnosis with Stage and Branch Attention
Visual features of skin lesions vary significantly because the images are collected from patients with different lesion colours and morphologies by using dissimilar imaging equipment.
Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning
Firstly, we introduce different extraction strategies to split the text into two sets of logical units, and construct the logical graph and the syntax graph respectively.
Ranked #14 on
Reading Comprehension
on ReClor
Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding
More specifically, our dataset contains 50 hours of annotated videos to localize relevant animal behavior segments in long videos for the video grounding task, 30K video sequences for the fine-grained multi-label action recognition task, and 33K frames for the pose estimation task, which correspond to a diverse range of animals with 850 species across 6 major animal classes.
Ranked #2 on
Action Recognition
on Animal Kingdom
Image Segmentation with Adaptive Spatial Priors from Joint Registration
In medical imaging for instance, intensity inhomogeneity and noise are common.
Prompt-based Generative Approach towards Multi-Hierarchical Medical Dialogue State Tracking
The dialogue state tracking (DST) module in the medical dialogue system which interprets utterances into the machine-readable structure for downstream tasks is particularly challenging.
Cluster Head Detection for Hierarchical UAV Swarm With Graph Self-supervised Learning
We first propose a graph attention self-supervised learning algorithm (GASSL) to detect the HUAVs of a single UAV cluster, where the GASSL can fit the IFS at the same time.
Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains
Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer.
Towards Class-agnostic Tracking Using Feature Decorrelation in Point Clouds
In this work, we investigate a more challenging task in the LiDAR point clouds, class-agnostic tracking, where a general model is supposed to be learned for any specified targets of both observed and unseen categories.
Theoretical Analysis of Deep Neural Networks in Physical Layer Communication
In this paper, we aim to quantitatively analyze why DNNs can achieve comparable performance in the physical layer comparing with traditional techniques, and also drive their cost in terms of computational complexity.
On Almost Sure Convergence Rates of Stochastic Gradient Methods
We further provide last-iterate almost sure convergence rates analysis for stochastic gradient methods on weakly convex smooth functions, in contrast with most existing results in the literature that only provide convergence in expectation for a weighted average of the iterates.
Uncertainty Modeling for Out-of-Distribution Generalization
In this paper, we improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training.
En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning
Our ICCE promotes intra-class compactness with inter-class separability on both seen and unseen classes in the embedding space and visual feature space.
Robust Image Forgery Detection Over Online Social Network Shared Images
To fight against the OSN-shared forgeries, in this work, a novel robust training scheme is proposed.
Meta Agent Teaming Active Learning for Pose Estimation
The existing pose estimation approaches often require a large number of annotated images to attain good estimation performance, which are laborious to acquire.
Under-Approximate Reachability Analysis for a Class of Linear Systems with Inputs
Under-approximations of reachable sets and tubes have been receiving growing research attention due to their important roles in control synthesis and verification.
3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve
In this paper, we propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE).
MoCA: Incorporating Multi-stage Domain Pretraining and Cross-guided Multimodal Attention for Textbook Question Answering
Textbook Question Answering (TQA) is a complex multimodal task to infer answers given large context descriptions and abundant diagrams.
Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides
Conclusion: Our study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC.
LVIS Challenge Track Technical Report 1st Place Solution: Distribution Balanced and Boundary Refinement for Large Vocabulary Instance Segmentation
Our method focuses on the problem in following two aspects: the long-tail distribution and the segmentation quality of mask and boundary.
Ranked #3 on
Instance Segmentation
on LVIS v1.0 val
Learning First-Order Rules with Relational Path Contrast for Inductive Relation Reasoning
Relation reasoning in knowledge graphs (KGs) aims at predicting missing relations in incomplete triples, whereas the dominant paradigm is learning the embeddings of relations and entities, which is limited to a transductive setting and has restriction on processing unseen entities in an inductive situation.
Disarranged Zone Learning (DZL): An unsupervised and dynamic automatic stenosis recognition methodology based on coronary angiography
Hence, the prediction accuracy of DZL is used as an approximator of coronary stenosis indicator.
Recent Advances of Continual Learning in Computer Vision: An Overview
In contrast to batch learning where all training data is available at once, continual learning represents a family of methods that accumulate knowledge and learn continuously with data available in sequential order.
Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation
Particularly, we propose a domain translator and align the heterogeneous data to the estimated class prototypes (i. e., class centers) in a hyper-sphere manifold.
RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions
Then we extend SOLOV2 to capture temporal information in video to learn motion information, and propose a moving object instance segmentation network with RiWFPN called RiWNet.
Learning Inner-Group Relations on Point Clouds
We further verify the expandability of RPNet, in terms of both depth and width, on the tasks of classification and segmentation.
Ranked #18 on
Semantic Segmentation
on ScanNet
The Multi-Modal Video Reasoning and Analyzing Competition
In this paper, we introduce the Multi-Modal Video Reasoning and Analyzing Competition (MMVRAC) workshop in conjunction with ICCV 2021.
Seirios: Leveraging Multiple Channels for LoRaWAN Indoor and Outdoor Localization
By exploiting both the original and the conjugate of the physical layer, Seirios can resolve the direct path from multiple reflectors in both indoor and outdoor environments.
Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning
It is a heavy workload to re-extract features of the whole database every time. Feature compatibility enables the learned new visual features to be directly compared with the old features stored in the database.
Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation
In this work, we propose two simple yet effective texture randomization mechanisms, Global Texture Randomization (GTR) and Local Texture Randomization (LTR), for Domain Generalization based SRSS.
IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
To ensure these two properties to better characterize appropriate intermediate domains, we enforce the bridge losses on intermediate domains' prediction space and feature space, and enforce a diversity loss on the two domain factors.
Domain Adaptive Person Re-Identification
Person Re-Identification
Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning
We investigate unsupervised representation learning for skeleton action recognition, and design a novel skeleton cloud colorization technique that is capable of learning skeleton representations from unlabeled skeleton sequence data.
DeceFL: A Principled Decentralized Federated Learning Framework
Although there has been a joint effort in tackling such a critical issue by proposing privacy-preserving machine learning frameworks, such as federated learning, most state-of-the-art frameworks are built still in a centralized way, in which a central client is needed for collecting and distributing model information (instead of data itself) from every other client, leading to high communication pressure and high vulnerability when there exists a failure at or attack on the central client.
A Low Complexity Learning-based Channel Estimation for OFDM Systems with Online Training
Besides, a training data construction approach utilizing least square (LS) estimation results is proposed so that the training data can be collected during the data transmission.
Resilient UAV Swarm Communications with Graph Convolutional Neural Network
Numerical results show that the proposed algorithms can rebuild the communication connectivity of the USNET more quickly than the existing algorithms under both one-off UEDs and general UEDs.
Interventional Video Grounding with Dual Contrastive Learning
2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations.
QFCNN: Quantum Fourier Convolutional Neural Network
The neural network and quantum computing are both significant and appealing fields, with their interactive disciplines promising for large-scale computing tasks that are untackled by conventional computers.
Person30K: A Dual-Meta Generalization Network for Person Re-Identification
Recently, person re-identification (ReID) has vastly benefited from the surging waves of data-driven methods.
Conterfactual Generative Zero-Shot Semantic Segmentation
In this work, we consider counterfactual methods to avoid the confounder in the original model.
Knowledge-aware Deep Framework for Collaborative Skin Lesion Segmentation and Melanoma Recognition
In this paper, we propose a novel knowledge-aware deep framework that incorporates some clinical knowledge into collaborative learning of two important melanoma diagnosis tasks, i. e., skin lesion segmentation and melanoma recognition.
Opening the Black Box of Deep Neural Networks in Physical Layer Communication
Deep Neural Network (DNN)-based physical layer techniques are attracting considerable interest due to their potential to enhance communication systems.
Generalizable Person Re-identification with Relevance-aware Mixture of Experts
Specifically, we propose a decorrelation loss to make the source domain networks (experts) keep the diversity and discriminability of individual domains' characteristics.
Safety-Critical Control of Stochastic Systems using Stochastic Control Barrier Functions
We propose a notion of stochastic control barrier functions (SCBFs)and show that SCBFs can significantly reduce the control efforts, especially in the presence of noise, compared to stochastic reciprocal control barrier functions (SRCBFs), and offer a less conservative estimation of safety probability, compared to stochastic zeroing control barrier functions (SZCBFs).
A Specification-Guided Framework for Temporal Logic Control of Nonlinear Systems
We show that the proposed algorithm is sound for full LTL specifications, and robustly complete for specifications recognizable by deterministic B\"uchi automata (DBA), the latter in the sense that control strategies can be found whenever the given specification can be satisfied with additional bounded disturbances.
UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles
Human behavior understanding with unmanned aerial vehicles (UAVs) is of great significance for a wide range of applications, which simultaneously brings an urgent demand of large, challenging, and comprehensive benchmarks for the development and evaluation of UAV-based models.
Analyzing the Forgetting Problem in Pretrain-Finetuning of Open-domain Dialogue Response Models
We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent.
Rank-One Prior: Toward Real-Time Scene Recovery
To improve visual quality under different weather/imaging conditions, we propose a real-time light correction method to recover the degraded scenes in the cases of sandstorms, underwater, and haze.
SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events
In this paper, we create a novel dataset, SUTD-TrafficQA (Traffic Question Answering), which takes the form of video QA based on the collected 10, 080 in-the-wild videos and annotated 62, 535 QA pairs, for benchmarking the cognitive capability of causal inference and event understanding models in complex traffic scenarios.
Ranked #2 on
Video Question Answering
on SUTD-TrafficQA
Constrained Radar Waveform Design for Range Profiling
Range profiling refers to the measurement of target response along the radar slant range.
RL-CSDia: Representation Learning of Computer Science Diagrams
Another type of diagrams such as from Computer Science is composed of graphics containing complex topologies and relations, and research on this type of diagrams is still blank.
A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning
How to fast and accurately assess the severity level of COVID-19 is an essential problem, when millions of people are suffering from the pandemic around the world.
Else-Net: Elastic Semantic Network for Continual Action Recognition From Skeleton Data
This makes online continual action recognition a challenging task.
A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder
Notably, by considering this problem as a conditional generation process, we estimate a parametric distribution of the missing regions based on the input conditions, from which to sample and synthesize the full motion series.
Interaction via Bi-Directional Graph of Semantic Region Affinity for Scene Parsing
In this work, we treat each respective region in an image as a whole, and capture the structure topology as well as the affinity among different regions.
Motion Adaptive Pose Estimation From Compressed Videos
A novel model, called Motion Adaptive Pose Net is proposed to exploit the compressed streams to efficiently decode pose sequences from videos.
Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification
To this end, we propose a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase, to alternatively boost the label purity and feature discriminability in the target domain for more reliable re-ID.
Human Action Recognition from Various Data Modalities: A Review
Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action.
A ROM-accelerated parallel-in-time preconditioner for solving all-at-once systems from evolutionary PDEs
In this paper we propose to use model reduction techniques for speeding up the diagonalization-based parallel-in-time (ParaDIAG) preconditioner, for iteratively solving all-at-once systems from evolutionary PDEs.
Numerical Analysis Numerical Analysis Dynamical Systems
A Boundary Regression Model for Nested Named Entity Recognition
Then, a regression operation is introduced to regress boundaries of NEs in a sentence.
XTQA: Span-Level Explanations of the Textbook Question Answering
Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams.
Skeleton-based Relational Reasoning for Group Activity Analysis
In this paper, we leverage the skeleton information to learn the interactions between the individuals straight from it.
Multiscale Attention Guided Network for COVID-19 Diagnosis Using Chest X-ray Images
Moreover, massive data collection is impractical for a newly emerged disease, which limited the performance of data thirsty deep learning models.
Deep Learning based Monocular Depth Prediction: Datasets, Methods and Applications
Despite the rapid progress in this topic, there are lacking of a comprehensive review, which is needed to summarize the current progress and provide the future directions.
Benchmarking LF-MMI, CTC and RNN-T Criteria for Streaming ASR
In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on three popular training criteria: LF-MMI, CTC and RNN-T.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Exact Phase Transitions of Model RB with Slower-Growing Domains
The second moment method has always been an effective tool to lower bound the satisfiability threshold of many random constraint satisfaction problems.
Robust Face Alignment by Multi-order High-precision Hourglass Network
Heatmap regression (HR) has become one of the mainstream approaches for face alignment and has obtained promising results under constrained environments.
Ranked #7 on
Face Alignment
on AFLW-19
Novel Parameter Estimation and Radar Detection Approaches for Multiple Point-like Targets: Designs and Comparisons
In this work, we develop and compare two innovative strategies for parameter estimation and radar detection of multiple point-like targets.
Smooth Converse Lyapunov-Barrier Theorems for Asymptotic Stability with Safety Constraints and Reach-Avoid-Stay Specifications
While the converse Lyapunov-barrier theorems are not constructive, as with classical converse Lyapunov theorems, we believe that the unified necessary and sufficient conditions with a single Lyapunov-barrier function are of theoretical interest and can hopefully shed some light on computational approaches.
Radar Adaptive Detection Architectures for Heterogeneous Environments
In this paper, four adaptive radar architectures for target detection in heterogeneous Gaussian environments are devised.
