Search Results for author:
Found 113 papers, 40 papers with code
Layered Neighborhood Expansion for Incremental Multiple Graph Matching
In this paper, we treat the graphs as graphs on a super-graph, and propose a novel breadth first search based method for expanding the neighborhood on the super-graph for a new coming graph, such that the matching with the new graph can be efficiently performed within the constructed neighborhood.
A K-variate Time Series Is Worth K Words: Evolution of the Vanilla Transformer Architecture for Long-term Multivariate Time Series Forecasting
In this study, we point out that the current tokenization strategy in MTSF Transformer architectures ignores the token uniformity inductive bias of Transformers.
Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition
For face recognition attacks, existing methods typically generate the l_p-norm perturbations on pixels, however, resulting in low attack transferability and high vulnerability to denoising defense models.
Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop
No-reference image quality assessment (NR-IQA) aims to quantify how humans perceive visual distortions of digital images without access to their undistorted references.
Perceptual Quality Assessment of Omnidirectional Images
The original and distorted omnidirectional images, subjective quality ratings, and the head and eye movement data together constitute the OIQA database.
A Survey on Label-efficient Deep Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction
The rapid development of deep learning has made a great progress in segmentation, one of the fundamental tasks of computer vision.
Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models
First, by optimizing the inverse dynamics, we encourage the world model to learn controllable and noncontrollable sources of spatiotemporal changes on isolated state transition branches.
DOTIN: Dropping Task-Irrelevant Nodes for GNNs
Scalability is an important consideration for deep graph neural networks.
Continual Predictive Learning from Videos
Can we develop predictive learning algorithms that can deal with more realistic, non-stationary physical environments?
Confusing Image Quality Assessment: Towards Better Augmented Reality Experience
An objective metric termed CFIQA is also proposed to better evaluate the confusing image quality.
Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation
Capturing the dynamics in user preference is crucial to better predict user future behaviors because user preferences often drift over time.
Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation
User interests are usually dynamic in the real world, which poses both theoretical and practical challenges for learning accurate preferences from rich behavior data.
Exploring Frequency Adversarial Attacks for Face Forgery Detection
In addition, the proposed frequency attack enhances the transferability across face forgery detectors as black-box attacks.
Analysis Method of Strapdown Inertial Navigation Error Distribution Based on Covariance Matrix Decomposition
Compared with the Monte-Carlo method and other method based on covariance matrix, the proposed method uses more complete error model, considers the interaction effect of error sources and can be easily realized with less computation.
EAutoDet: Efficient Architecture Search for Object Detection
In contrast, this paper introduces an efficient framework, named EAutoDet, that can discover practical backbone and FPN architectures for object detection in 1. 4 GPU-days.
Ranked #23 on
Object Detection In Aerial Images
on DOTA
Facial Geometric Detail Recovery via Implicit Representation
Learning a dense 3D model with fine-scale details from a single facial image is highly challenging and ill-posed.
ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation
We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions.
DialogueNeRF: Towards Realistic Avatar Face-to-face Conversation Video Generation
Conversation is an essential component of virtual avatar activities in the metaverse.
NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields
Deep learning has shown great potential for modeling the physical dynamics of complex particle systems such as fluids.
DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Rendering
Specifically, neural radiance field takes lip movements features and personalized attributes as two disentangled conditions, where lip movements are directly predicted from the audio inputs to achieve lip-synchronized generation.
Align Representations With Base: A New Approach to Self-Supervised Learning
Existing symmetric contrastive learning methods suffer from collapses (complete and dimensional) or quadratic complexity of objectives.
End-to-End Reconstruction-Classification Learning for Face Forgery Detection
Reconstruction learning over real images enhances the learned representations to be aware of forgery patterns that are even unknown, while classification learning takes the charge of mining the essential discrepancy between real and fake images, facilitating the understanding of forgeries.
Learning Invisible Markers for Hidden Codes in Offline-to-Online Photography
In addition, the automatic localization of hidden codes significantly reduces the time of manually correcting geometric distortions for photos, which is a revolutionary innovation for information hiding in mobile applications.
A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs
Solving combinatorial optimization (CO) on graphs is among the fundamental tasks for upper-stream applications in data mining, machine learning and operations research.
Fully Context-Aware Image Inpainting with a Learned Semantic Pyramid
We train the prior learner and the image generator as a unified model without any post-processing.
TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification
In the meantime, we design an adaptive BN layer in the domain-invariant stream, to approximate the statistics of various unseen domains.
Domain Generalization
Generalizable Person Re-identification
Consensus Synergizes with Memory: A Simple Approach for Anomaly Segmentation in Urban Scenes
Anomaly segmentation is a crucial task for safety-critical applications, such as autonomous driving in urban scenes, where the goal is to detect out-of-distribution (OOD) objects with categories which are unseen during training.
Ranked #6 on
Anomaly Detection
on Fishyscapes L&F
Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation
We consider a new problem of adapting a human mesh reconstruction model to out-of-domain streaming videos, where performance of existing SMPL-based models are significantly affected by the distribution shift represented by different camera parameters, bone lengths, backgrounds, and occlusions.
Ranked #1 on
3D Absolute Human Pose Estimation
on Surreal
ZARTS: On Zero-order Optimization for Neural Architecture Search
Also, we search on the search space of DARTS to compare with peer methods, and our discovered architecture achieves 97. 54% accuracy on CIFAR-10 and 75. 7% top-1 accuracy on ImageNet, which are state-of-the-art performance.
DAAS: Differentiable Architecture and Augmentation Policy Search
Neural architecture search (NAS) has been an active direction of automatic machine learning (Auto-ML), aiming to explore efficient network structures.
$m$-mix: Generating hard negatives via multiple samples mixing for contrastive learning
Negative pairs are essential in contrastive learning, which plays the role of avoiding degenerate solutions.
Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning
The proposed two methods (FCL, ICL) can be combined synthetically, called Zero-CL, where ``Zero'' means negative samples are \textbf{zero} relevant, which allows Zero-CL to completely discard negative pairs i. e., with \textbf{zero} negative samples.
On Learning to Solve Cardinality Constrained Combinatorial Optimization in One-Shot: A Re-parameterization Approach via Gumbel-Sinkhorn-TopK
Cardinality constrained combinatorial optimization requires selecting an optimal subset of $k$ elements, and it will be appealing to design data-driven algorithms that perform TopK selection over a probability distribution predicted by a neural network.
Efficient Person Search: An Anchor-Free Approach
Third, by investigating the advantages of both anchor-based and anchor-free models, we further augment AlignPS with an ROI-Align head, which significantly improves the robustness of re-id features while still keeping our model highly efficient.
Ranked #3 on
Person Search
on PRW
Learning to Track Objects from Unlabeled Videos
In this paper, we propose to learn an Unsupervised Single Object Tracker (USOT) from scratch.
Task-Specific Normalization for Continual Learning of Blind Image Quality Models
In this paper, we present a simple yet effective continual learning method for BIQA with improved quality prediction accuracy, plasticity-stability trade-off, and task-order/length robustness.
Angel's Girl for Blind Painters: an Efficient Painting Navigation System Validated by Multimodal Evaluation Approach
This work demonstrates that it is practicable for the blind people to feel the world through the brush in their hands.
Local-to-Global Self-Attention in Vision Transformers
Transformers have demonstrated great potential in computer vision tasks.
PointAugmenting: Cross-Modal Augmentation for 3D Object Detection
On one hand, PointAugmenting decorates point clouds with corresponding point-wise CNN features extracted by pretrained 2D detection models, and then performs 3D object detection over the decorated point clouds.
Exploring Visual Context for Weakly Supervised Person Search
This paper inventively considers weakly supervised person search with only bounding box annotations.
Context-Aware Image Inpainting with Learned Semantic Priors
Based on the semantic priors, we further propose a context-aware image inpainting model, which adaptively integrates global semantics and local features in a unified image generator.
A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs
Combinatorial Optimization (CO) has been a long-standing challenging research topic featured by its NP-hard nature.
Making CNNs Interpretable by Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learning
In this paper, we propose a generic model transfer scheme to make Convlutional Neural Networks (CNNs) interpretable, while maintaining their high classification accuracy.
Scalable and Explainable 1-Bit Matrix Completion via Graph Signal Learning
One-bit matrix completion is an important class of positiveunlabeled (PU) learning problems where the observations consist of only positive examples, eg, in top-N recommender systems.
Learning Multi-Attention Context Graph for Group-Based Re-Identification
Extensive experiments on the novel dataset as well as three existing datasets clearly demonstrate the effectiveness of the proposed framework for both group-based re-id tasks.
Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction
This paper considers a new problem of adapting a pre-trained model of human mesh reconstruction to out-of-domain streaming videos.
Ranked #16 on
3D Human Pose Estimation
on 3DPW
IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking
Recently, adversarial attack has been applied to visual object tracking to evaluate the robustness of deep trackers.
Learning Comprehensive Motion Representation for Action Recognition
For action recognition learning, 2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame.
Continual Learning for Blind Image Quality Assessment
In this paper, we formulate continual learning for BIQA, where a model learns continually from a stream of IQA datasets, building on what was learned from previously seen data.
Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting
We propose a deep state space model for probabilistic time series forecasting whereby the non-linear emission model and transition model are parameterized by networks and the dependency is modeled by recurrent neural nets.
Self-supervised representation learning via adaptive hard-positive mining
Despite their success in perception over the last decade, deep neural networks are also known ravenous to labeled data for training, which limits their applicability to real-world problems.
Rethinking Pseudo-labeled Sample Mining for Semi-Supervised Object Detection
However, the impact of the pseudo-labeled samples' quality as well as the mining strategies for high quality training sample have rarely been studied in SSL.
Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning
This paper considers the setting of jointly matching and clustering multiple graphs belonging to different groups, which naturally rises in many realistic problems.
Ranked #2 on
Graph Matching
on Willow Object Class
Combinatorial Learning of Graph Edit Distance via Dynamic Embedding
This paper presents a hybrid approach by combing the interpretability of traditional search-based techniques for producing the edit path, as well as the efficiency and adaptivity of deep embedding models to achieve a cost-effective GED solver.
ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradients Accumulation
Single-path based differentiable neural architecture search has great strengths for its low computational cost and memory-friendly nature.
Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning
We then propose to recursively alternate the learning schemes of imitation and exploration to narrow the discrepancy between training and inference.
Hierarchical Style-based Networks for Motion Synthesis
Generating diverse and natural human motion is one of the long-standing goals for creating intelligent characters in the animated world.
Cross-Modality 3D Object Detection
In this paper, we focus on exploring the fusion of images and point clouds for 3D object detection in view of the complementary nature of the two modalities, i. e., images possess more semantic information while point clouds specialize in distance sensing.
Robust Tracking against Adversarial Attacks
On one hand, we add the temporal perturbations into the original video sequences as adversarial examples to greatly degrade the tracking performance.
Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering
However, there are few works studying the data augmentation problem for VQA and none of the existing image based augmentation schemes (such as rotation and flipping) can be directly applied to VQA due to its semantic structure -- an $\langle image, question, answer\rangle$ triplet needs to be maintained correctly.
Collaborative Learning for Faster StyleGAN Embedding
The latent code of the recent popular model StyleGAN has learned disentangled representations thanks to the multi-layer style-based generator.
Video Prediction via Example Guidance
In video prediction tasks, one major challenge is to capture the multi-modal nature of future contents and dynamics.
Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild
Nevertheless, due to the distributional shift between images simulated in the laboratory and captured in the wild, models trained on databases with synthetic distortions remain particularly weak at handling realistic distortions (and vice versa).
Permutation Matters: Anisotropic Convolutional Layer for Learning on Point Clouds
Various point neural networks have been developed with isotropic filters or using weighting matrices to overcome the structure inconsistency on point clouds.
SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing
Instance-level denoising on the feature map is performed to enhance the detection to small and cluttered objects.
Ranked #26 on
Object Detection In Aerial Images
on DOTA
Learning Local Neighboring Structure for Robust 3D Shape Representation
Mesh is a powerful data structure for 3D shapes.
Toward Better Understanding of Saliency Prediction in Augmented 360 Degree Videos
The saliency annotations of head and eye movements for both original and augmented videos are collected and together constitute the ARVR dataset.
Robust Invisible Hyperlinks in Physical Photographs Based on 3D Rendering Attacks
To train a robust decoder against the physical distortion from the real world, a distortion network based on 3D rendering is inserted between the encoder and the decoder to simulate the camera imaging process.
Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching
We also show how to extend our network to hypergraph matching, and matching of multiple graphs.
Ranked #3 on
Graph Matching
on SPair-71k
Decoding Spiking Mechanism with Dynamic Learning on Neuron Population
Our model is aimed to reconstruct neuron information while inferring representations of neuron spiking states.
Deep Unsupervised Clustering with Clustered Generator Model
We propose the clustered generator model for clustering which contains both continuous and discrete latent variables.
Composable Semi-parametric Modelling for Long-range Motion Generation
Learning diverse and natural behaviors is one of the longstanding goal for creating intelligent characters in the animated world.
Semi-supervised 3D Face Reconstruction with Nonlinear Disentangled Representations
Moreover, the identity and expression representations are entangled in these models, which hurdles many facial editing applications.
Learning to Blindly Assess Image Quality in the Laboratory and Wild
Computational models for blind image quality assessment (BIQA) are typically trained in well-controlled laboratory environments with limited generalizability to realistically distorted images.
Reinforcement Learning with Policy Mixture Model for Temporal Point Processes Clustering
Temporal point process is an expressive tool for modeling event sequences over time.
Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer
We propose adversarial gated networks (Gated GAN) to transfer multiple styles in a single model.
Learning Context Graph for Person Search
Person re-identification has achieved great progress with deep convolutional neural networks.
Learning Combinatorial Embedding Networks for Deep Graph Matching
In addition with its NP-completeness nature, another important challenge is effective modeling of the node-wise and structure-wise affinity across graphs and the resulting objective, to guide the matching procedure effectively finding the true matching against noises.
Video Prediction via Selective Sampling
Most adversarial learning based video prediction methods suffer from image blur, since the commonly used adversarial and regression loss pair work rather in a competitive way than collaboration, yielding compromised blur effect.
Correlation Propagation Networks for Scene Text Detection
In this work, we propose a novel hybrid method for scene text detection namely Correlation Propagation Network (CPN).
Deep Regression Tracking with Shrinkage Loss
Regression trackers directly learn a mapping from regularly dense samples of target objects to soft labels, which are usually generated by a Gaussian function, to estimate target positions.
Fine-Grained Video Captioning for Sports Narrative
First, to facilitate this novel research of fine-grained video caption, we collected a novel dataset called Fine-grained Sports Narrative dataset (FSN) that contains 2K sports videos with ground-truth narratives from YouTube. com.
Crowd Counting via Adversarial Cross-Scale Consistency Pursuit
Crowd counting or density estimation is a challenging task in computer vision due to large scale variations, perspective distortions and serious occlusions, etc.
Ranked #4 on
Crowd Counting
on WorldExpo’10
Structure Preserving Video Prediction
Despite recent emergence of adversarial based methods for video prediction, existing algorithms often produce unsatisfied results in image regions with rich structural information (i. e., object boundary) and detailed motion (i. e., articulated body movement).
Multiple Granularity Group Interaction Prediction
Most human activity analysis works (i. e., recognition orãprediction) only focus on a single granularity, i. e., eitherãmodelling global motion based on the coarse level movement such as human trajectories orãforecasting future detailed action based on body partsâ movement such as skeleton motion.
Attention-GAN for Object Transfiguration in Wild Images
This paper studies the object transfiguration problem in wild images.
Decoupled Learning for Factorial Marked Temporal Point Processes
In conventional (multi-dimensional) marked temporal point process models, event is often encoded by a single discrete variable i. e. a marker.
Performance Guaranteed Network Acceleration via High-Order Residual Quantization
Input binarization has shown to be an effective way for network acceleration.
Terahertz Security Image Quality Assessment by No-reference Model Observers
Subsequently, the existing no-reference IQA algorithms, which were 5 opinion-aware approaches viz., NFERM, GMLF, DIIVINE, BRISQUE and BLIINDS2, and 8 opinion-unaware approaches viz., QAC, SISBLIM, NIQE, FISBLIM, CPBD, S3 and Fish_bb, were executed for the evaluation of the THz security image quality.
Robust Visual Tracking via Hierarchical Convolutional Features
Specifically, we learn adaptive correlation filters on the outputs from each convolutional layer to encode the target appearance.
Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking
Second, we learn a correlation filter over a feature pyramid centered at the estimated target position for predicting scale changes.
Skeleton-aided Articulated Motion Generation
This work make the first attempt to generate articulated human motion sequence from a single image.
Ranked #2 on
Gesture-to-Gesture Translation
on NTU Hand Digit
Video Segmentation via Multiple Granularity Analysis
We introduce a Multiple Granularity Analysis framework for video segmentation in a coarse-to-fine manner.
Recurrent Modeling of Interaction Context for Collective Activity Recognition
However, most of the previous activity recognition methods do not offer a flexible and scalable scheme to handle the high order context modeling problem.
Image Matching via Loopy RNN
Towards this end, we propose a novel loopy recurrent neural network (Loopy RNN), which is capable of aggregating relationship information of two input images in a progressive/iterative manner and outputting the consolidated matching score in the final iteration.
Depth Structure Preserving Scene Image Generation
Key to automatically generate natural scene images is to properly arrange among various spatial elements, especially in the depth direction.
Predicting Human Interaction via Relative Attention Model
Predicting human interaction is challenging as the on-going activity has to be inferred based on a partially observed video.
Modeling The Intensity Function Of Point Process Via Recurrent Neural Networks
In this paper, we model the background by a Recurrent Neural Network (RNN) with its units aligned with time series indexes while the history effect is modeled by another RNN whose units are aligned with asynchronous events to capture the long-range dynamics.
Joint Modeling of Event Sequence and Time Series with Attentional Twin Recurrent Neural Networks
A variety of real-world processes (over networks) produce sequences of data whose complex temporal dynamics need to be studied.
Person Re-Identification via Recurrent Feature Aggregation
We address the person re-identification problem by effectively exploiting a globally discriminative feature representation from a sequence of tracked human regions/patches.
Learning a No-Reference Quality Metric for Single-Image Super-Resolution
Numerous single-image super-resolution algorithms have been proposed in the literature, but few studies address the problem of performance evaluation based on visual perception.
Factors in Finetuning Deep Model for Object Detection With Long-Tail Distribution
Our analysis and empirical results show that classes with more samples have higher impact on the feature learning.
Progressively Parsing Interactional Objects for Fine Grained Action Detection
Fine grained video action analysis often requires reliable detection and tracking of various interacting objects and human body parts, denoted as interactional object parsing.
Temporal Action Localization With Pyramid of Score Distribution Features
We investigate the feature design and classification architectures in temporal action localization.
Cascaded Interactional Targeting Network for Egocentric Video Analysis
Firstly, a novel EM-like learning framework is proposed to train the pixel-level deep convolutional neural network (DCNN) by seamlessly integrating weakly supervised data (i. e., massive bounding box annotations) with a small set of strongly supervised data (i. e., fully annotated hand segmentation maps) to achieve state-of-the-art hand segmentation performance.
Factors in Finetuning Deep Model for object detection
Our analysis and empirical results show that classes with more samples have higher impact on the feature learning.
A Matrix Decomposition Perspective to Multiple Graph Matching
Graph matching has a wide spectrum of real-world applications and in general is known NP-hard.
Hierarchical Convolutional Features for Visual Tracking
The outputs of the last convolutional layers encode the semantic information of targets and such representations are robust to significant appearance variations.
Cross-Scene Crowd Counting via Deep Convolutional Neural Networks
To address this problem, we propose a deep convolutional neural network (CNN) for crowd counting, and it is trained alternatively with two related learning objectives, crowd density and crowd count.
Ranked #15 on
Crowd Counting
on WorldExpo’10
Discrete Hyper-Graph Matching
Evaluations on both synthetic and real-world data corroborate the efficiency of our method.
Motion Part Regularization: Improving Action Recognition via Trajectory Selection
Inspired by the recent advance in sentence regularization for text classification, we introduce a Motion Part Regularization framework to mining discriminative semi-local groups of dense trajectories.
Long-Term Correlation Tracking
In this paper, we address the problem of long-term visual tracking where the target objects undergo significant appearance variation due to deformation, abrupt motion, heavy occlusion and out-of-the-view.
A General Multi-Graph Matching Approach via Graduated Consistency-regularized Boosting
We propose multi-graph matching methods to incorporate the two aspects by boosting the affinity score, meanwhile gradually infusing the consistency as a regularizer.
