Search Results for author:
Found 114 papers, 45 papers with code
VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation
A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data distribution.
Ranked #7 on
Video Generation
on UCF-101
Session-based Recommendation with Graph Neural Networks
To obtain accurate item embedding and take complex transitions of items into account, we propose a novel method, i. e. Session-based Recommendation with Graph Neural Networks, SR-GNN for brevity.
Ranked #1 on
Session-Based Recommendations
on Gowalla
A Light CNN for Deep Face Representation with Noisy Labels
This paper presents a Light CNN framework to learn a compact embedding on the large-scale face data with massive noisy labels.
Ranked #2 on
Age-Invariant Face Recognition
on CAFR
Meta-SR: A Magnification-Arbitrary Network for Super-Resolution
In this work, we propose a novel method called Meta-SR to firstly solve super-resolution of arbitrary scale factor (including non-integer scale factors) with a single model.
A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
Test-time adaptation (TTA), an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions.
Unfolding the Alternating Optimization for Blind Super Resolution
More importantly, \textit{Restorer} is trained with the kernel estimated by \textit{Estimator}, instead of ground-truth kernel, thus \textit{Restorer} could be more tolerant to the estimation error of \textit{Estimator}.
Ranked #2 on
Blind Super-Resolution
on Set5 - 2x upscaling
End-to-end Alternating Optimization for Blind Super Resolution
More importantly, \textit{Restorer} is trained with the kernel estimated by \textit{Estimator}, instead of the ground-truth kernel, thus \textit{Restorer} could be more tolerant to the estimation error of \textit{Estimator}.
Ranked #2 on
Blind Super-Resolution
on DIV2KRK - 4x upscaling
End-to-end Alternating Optimization for Real-World Blind Super Resolution
To address this issue, instead of considering these two problems independently, we adopt an alternating optimization algorithm, which can estimate the degradation and restore the SR image in a single model.
GAIA: A Transfer Learning System of Object Detection that Fits Your Needs
Transfer learning with pre-training on large-scale datasets has played an increasingly significant role in computer vision and natural language processing recently.
BEVBert: Multimodal Map Pre-training for Language-guided Navigation
Concretely, we build a local metric map to explicitly aggregate incomplete observations and remove duplicates, while modeling navigation dependency in a global topological map.
Ranked #2 on
Visual Navigation
on R2R
Learning the Degradation Distribution for Blind Image Super-Resolution
Compared with previous deterministic degradation models, PDM could model more diverse degradations and generate HR-LR pairs that may better cover the various degradations of test images, and thus prevent the SR model from over-fitting to specific ones.
Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation
However, for bottom-up methods, which need to handle a large variance of human scales and labeling ambiguities, the current practice seems unreasonable.
Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification
Graph convolutional networks (GCNs) have been successfully applied in node classification tasks of network mining.
Vision Transformer with Super Token Sampling
STA decomposes vanilla global attention into multiplications of a sparse association map and a low-dimensional attention, leading to high efficiency in capturing global dependencies.
DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation
Our key idea is to investigate and identify a space, namely delta image and text space that has well-aligned distribution between CLIP visual feature differences of two images and CLIP textual embedding differences of source and target texts.
Improving Zero-Shot Generalization for CLIP with Synthesized Prompts
Thereafter, we fine-tune CLIP with off-the-shelf methods by combining labeled and synthesized features.
Neighbor-view Enhanced Model for Vision and Language Navigation
Specifically, our NvEM utilizes a subject module and a reference module to collect contexts from neighbor views.
Ranked #82 on
Vision and Language Navigation
on VLN Challenge
OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling
Online updating of time series forecasting models aims to address the concept drifting problem by efficiently updating forecasting models based on streaming data.
AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation
In particular, when the adaptation target is a series of domains, the adaptation accuracy of AdaNPC is 50% higher than advanced TTA methods.
TAGNN: Target Attentive Graph Neural Networks for Session-based Recommendation
However, these methods compress a session into one fixed representation vector without considering the target items to be predicted.
Ranked #3 on
Session-Based Recommendations
on yoochoose1
Free Lunch for Domain Adversarial Training: Environment Label Smoothing
A fundamental challenge for machine learning models is how to generalize learned models for out-of-distribution (OOD) data.
Ranked #4 on
Domain Adaptation
on Office-Home
Debiasing Multimodal Large Language Models
In the realms of computer vision and natural language processing, Large Vision-Language Models (LVLMs) have become indispensable tools, proficient in generating textual descriptions based on visual inputs.
Dynamic Graph Representation for Partially Occluded Biometrics
During dynamic graph matching, we propose a novel strategy to measure the distances of both nodes and adjacent matrixes.
Fully Sparse Fusion for 3D Object Detection
In this paper, we study how to effectively leverage image modality in the emerging fully sparse architecture.
A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
Extensive results on 17 datasets validate that our method surpasses or achieves comparable results with state-of-the-art methods on few-shot classification, imbalanced learning, and out-of-distribution generalization.
Semantic 3D-aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Field
CNeRF divides the image by semantic regions and learns an independent neural radiance field for each region, and finally fuses them and renders the complete image.
RiDDLE: Reversible and Diversified De-identification with Latent Encryptor
This work presents RiDDLE, short for Reversible and Diversified De-identification with Latent Encryptor, to protect the identity information of people from being misused.
CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation with only image-level labels saves large human effort to annotate pixel-level labels.
Self-Supervised Predictive Learning: A Negative-Free Method for Sound Source Localization in Visual Scenes
Sound source localization in visual scenes aims to localize objects emitting the sound in a given image.
Transferable Sparse Adversarial Attack
The experiment shows that our method has improved the transferability by a large margin under a similar sparsity setting compared with state-of-the-art methods.
Semantic Prompt for Few-Shot Image Recognition
Instead of the naive exploitation of semantic information for remedying classifiers, we explore leveraging semantic information as prompts to tune the visual feature extraction network adaptively.
Pointly-Supervised Panoptic Segmentation
In this paper, we propose a new approach to applying point-level annotations for weakly-supervised panoptic segmentation.
3D Shape Temporal Aggregation for Video-Based Clothing-Change Person Re-Identication
However, existing Re-ID methods usually generate 3D body shapes without considering identity modeling, which severely weakens the discriminability of 3D human shapes.
IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
On the other hand, the inference model is encouraged to classify between the generated and real samples while the generator tries to fool it as GANs.
Learning Instance-level Spatial-Temporal Patterns for Person Re-identification
In this paper, we propose a novel Instance-level and Spatial-Temporal Disentangled Re-ID method (InSTD), to improve Re-ID accuracy.
Ranked #14 on
Person Re-Identification
on DukeMTMC-reID
GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction
Then, in order to better capture the complicated non-linearity of graph data, we present a novel GraphAIR framework which models the neighborhood interaction in addition to neighborhood aggregation.
AdaptGuard: Defending Against Universal Attacks for Model Adaptation
To address this issue, we propose a model preprocessing framework, named AdaptGuard, to improve the security of model adaptation algorithms.
DeepFirearm: Learning Discriminative Feature Representation for Fine-grained Firearm Retrieval
There are great demands for automatically regulating inappropriate appearance of shocking firearm images in social media or identifying firearm types in forensics.
Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models
In this work, we adopt the intuition that the LVLM tends to respond logically consistently for existent objects but inconsistently for hallucinated objects.
Learning Pose-invariant 3D Object Reconstruction from Single-view Images
Learning to reconstruct 3D shapes using 2D images is an active research topic, with benefits of not requiring expensive 3D data.
Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations
Different from previous cross-domain FSL work (CD-FSL) that considers the domain shift between base and novel classes, the new problem, termed cross-domain cross-set FSL (CDSC-FSL), requires few-shot learners not only to adapt to the new domain, but also to be consistent between different domains within each novel class.
Exploiting Semantic Attributes for Transductive Zero-Shot Learning
To address this issue, we present a novel transductive ZSL method that produces semantic attributes of the unseen data and imposes them on the generative process.
What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?
Based on the evaluation results, we also identify the best choices for different factors and propose a new multi-scale image feature representation method to encode the image effectively.
Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning
Skeleton-based action recognition has made great progress recently, but many problems still remain unsolved.
Ranked #81 on
Skeleton Based Action Recognition
on NTU RGB+D
Geometry Guided Adversarial Facial Expression Synthesis
An expression invariant face recognition experiment is also performed to further show the advantages of our proposed method.
Deep Supervised Discrete Hashing
Benefit from recent advances in deep learning, deep hashing methods have achieved promising results for image retrieval.
Anti-Makeup: Learning A Bi-Level Adversarial Network for Makeup-Invariant Face Verification
This paper proposes a learning from generation approach for makeup-invariant face verification by introducing a bi-level adversarial network (BLAN).
Coupled Deep Learning for Heterogeneous Face Recognition
CDL seeks a shared feature space in which the heterogeneous face matching problem can be approximately treated as a homogeneous face matching problem.
Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition
To avoid the over-fitting problem on small-scale heterogeneous face data, a correlation prior is introduced on the fully-connected layers of WCNN network to reduce parameter space.
Ranked #3 on
Face Verification
on BUAA-VisNir
Multimodal Memory Modelling for Video Captioning
In this paper, we propose a Multimodal Memory Model (M3) to describe videos, which builds a visual and textual shared memory to model the long-term visual-textual dependency and further guide global visual attention on described targets.
DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification
The occlusions incurred by random meshes severely degenerate the performance of face verification systems, which raises the MeshFace verification problem between MeshFace and daily photos.
ICE: Information Credibility Evaluation on Social Media via Representation Learning
In this paper, we propose a novel representation learning method, Information Credibility Evaluation (ICE), to learn representations of information credibility on social media.
Learning Structured Ordinal Measures for Video based Face Recognition
This paper presents a structured ordinal measure method for video-based face recognition that simultaneously learns ordinal filters and structured ordinal features.
Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval
Research efforts have been devoted to learning compact binary codes that preserve semantic similarity based on labels.
Deep Steganalysis: End-to-End Learning with Supervisory Information beyond Class Labels
Recently, deep learning has shown its power in steganalysis.
Variational Capsules for Image Analysis and Synthesis
Variational capsules model an image as a composition of entities in a probabilistic model.
Accelerating Deep Neural Networks with Spatial Bottleneck Modules
This paper presents an efficient module named spatial bottleneck for accelerating the convolutional layers in deep neural networks.
Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search
To exploit the multilevel corresponding visual contents, we propose a pose-guided multi-granularity attention network (PMA).
Relevance Topic Model for Unstructured Social Group Activity Recognition
Unstructured social group activity recognition in web videos is a challenging task due to 1) the semantic gap between class labels and low-level visual features and 2) the lack of labeled training data.
Multistage Adversarial Losses for Pose-Based Human Image Synthesis
Human image synthesis has extensive practical applications e. g. person re-identification and data augmentation for human pose estimation.
M3: Multimodal Memory Modelling for Video Captioning
Inspired by the facts that memory modelling poses potential advantages to long-term sequential problems [35] and working memory is the key factor of visual attention [33], we propose a Multimodal Memory Model (M3) to describe videos, which builds a visual and textual shared memory to model the long-term visual-textual dependency and further guide visual attention on described visual targets to solve visual-textual alignments.
End-to-end View Synthesis for Light Field Imaging with Pseudo 4DCNN
Limited angular resolution has become the main bottleneck of microlens-based plenoptic cameras towards practical vision applications.
Deformable Object Matching via Deformation Decomposition based 2D Label MRF
The MRF energy function is derived from the deformation decomposition model.
ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering
For spectral embedding/clustering, it is still an open problem on how to construct an relation graph to reflect the intrinsic structures in data.
See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-Identification
Accordingly, a demanding need is to recognize a person under different cameras, which is called person re-identification.
Wavelet-SRNet: A Wavelet-Based CNN for Multi-Scale Face Super Resolution
Most modern face super-resolution methods resort to convolutional neural networks (CNN) to infer high-resolution (HR) face images.
Ranked #3 on
Face Hallucination
on FFHQ 512 x 512 - 16x upscaling
Cross-spectral Face Completion for NIR-VIS Heterogeneous Face Recognition
This paper models high resolution heterogeneous face synthesis as a complementary combination of two components, a texture inpainting component and pose correction component.
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
Nevertheless, how to effectively extract discriminative spatial and temporal features is still a challenging problem.
Ranked #51 on
Skeleton Based Action Recognition
on NTU RGB+D
Fast Supervised Discrete Hashing
Rather than adopting this method, FSDH uses a very simple yet effective regression of the class labels of training examples to the corresponding hash code to accelerate the algorithm.
Progressive Cluster Purification for Transductive Few-shot Learning
Furthermore, the inter-class classification and the intra-class transduction are extremely flexible to be repeated several times to progressively purify the clusters.
Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection
With the combination of these two designs, an architecture transformation scheme could be discovered to adapt a network designed for image classification to task of object detection.
POD: Practical Object Detection with Scale-Sensitive Network
Scale-sensitive object detection remains a challenging task, where most of the existing methods could not learn it explicitly and are not robust to scale variance.
Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection
Instead of searching and constructing an entire network, NATS explores the architecture space on the base of existing network and reusing its weights.
A3GAN: An Attribute-aware Attentive Generative Adversarial Network for Face Aging
Face aging, which aims at aesthetically rendering a given face to predict its future appearance, has received significant research attention in recent years.
Alignment Free and Distortion Robust Iris Recognition
And illumination variations may cause irregular distortion of iris texture.
A New Ensemble Method for Concessively Targeted Multi-model Attack
Thus, in this paper, we propose a new attack mechanism which performs the non-targeted attack when the targeted attack fails.
Temporal Sparse Adversarial Attack on Sequence-based Gait Recognition
In this paper, we demonstrate that the state-of-the-art gait recognition model is vulnerable to such attacks.
Cosmetic-Aware Makeup Cleanser
Face verification aims at determining whether a pair of face images belongs to the same identity.
Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels
Training with more data has always been the most stable and effective way of improving performance in deep learning era.
TFNet: Multi-Semantic Feature Interaction for CTR Prediction
The CTR (Click-Through Rate) prediction plays a central role in the domain of computational advertising and recommender systems.
Ranked #31 on
Click-Through Rate Prediction
on Criteo
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition
Self-supervised learning (SSL) has been proved very effective at learning representations from unlabeled data in the image domain.
Employing Multi-Estimations for Weakly-Supervised Semantic Segmentation
Instead of struggling to refine a single seed, we propose a novel approach to alleviate the inaccurate seed problem by leveraging the segmentation model's robustness to learn from multiple seeds.
Prediction and Recovery for Adaptive Low-Resolution Person Re-Identification
In this paper, we propose a novel Prediction, Recovery and Identification (PRI) model for LR re-id, which adaptively recovers missing details by predicting a preferable scale factor based on the image content.
Style Intervention: How to Achieve Spatial Disentanglement with Style-based Generators?
Generative Adversarial Networks (GANs) with style-based generators (e. g. StyleGAN) successfully enable semantic control over image synthesis, and recent studies have also revealed that interpretable image translations could be obtained by modifying the latent code.
Efficient Human Pose Estimation by Learning Deeply Aggregated Representations
Instead, we focus on exploiting multi-scale information from layers with different receptive-field sizes and then making full of use this information by improving the fusion method.
Focal and Efficient IOU Loss for Accurate Bounding Box Regression
(ii) Most of the loss functions ignore the imbalance problem in BBR that the large number of anchor boxes which have small overlaps with the target boxes contribute most to the optimization of BBR.
Graph Classification by Mixture of Diverse Experts
Graph classification is a challenging research problem in many applications across a broad range of domains.
Locate then Segment: A Strong Pipeline for Referring Image Segmentation
Referring image segmentation aims to segment the objects referred by a natural language expression.
Generalized Referring Expression Segmentation
Image Segmentation
+2
Learning Domain Invariant Representations for Generalizable Person Re-Identification
Generalizable person Re-Identification (ReID) has attracted growing attention in recent computer vision community.
SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfer
Since human faces are symmetrical in the UV space, we can conveniently remove the undesired shadow and occlusion from the reference image by carefully designing a Flip Attention Module (FAM).
Robust Face-Swap Detection Based on 3D Facial Shape Information
Maliciously-manipulated images or videos - so-called deep fakes - especially face-swap images and videos have attracted more and more malicious attackers to discredit some key figures.
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images
Few-shot learning is a challenging task since only few instances are given for recognizing an unseen class.
Adaptive Dilated Convolution For Human Pose Estimation
It can generate and fuse multi-scale features of the same spatial sizes by setting different dilation rates for different channels.
Generalizable Person Re-identification Without Demographics
However, the convex condition of KL DRO may not hold for overparameterized neural networks, such that applying KL DRO often fails to generalize under distribution shifts in real scenarios.
Generalizable Person Re-Identification via Self-Supervised Batch Norm Test-Time Adaption
In this paper, we investigate the generalization problem of person re-identification (re-id), whose major challenge is the distribution shift on an unseen domain.
Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring
Attributes skew hinders the current federated learning (FL) frameworks from consistent optimization directions among the clients, which inevitably leads to performance reduction and unstable convergence.
HumanDiffusion: a Coarse-to-Fine Alignment Diffusion Framework for Controllable Text-Driven Person Image Generation
In this paper, we propose HumanDiffusion, a coarse-to-fine alignment diffusion framework, for text-driven person image generation.
Semantic-aware One-shot Face Re-enactment with Dense Correspondence Estimation
One-shot face re-enactment is a challenging task due to the identity mismatch between source and driving faces.
Human Image Generation: A Comprehensive Survey
Image and video synthesis has become a blooming topic in computer vision and machine learning communities along with the developments of deep generative models, due to its great academic and application value.
CFFT-GAN: Cross-domain Feature Fusion Transformer for Exemplar-based Image Translation
In this paper, we propose a more general learning approach by considering two domain features as a whole and learning both inter-domain correspondence and intra-domain potential information interactions.
Collaborative Feature Learning for Fine-grained Facial Forgery Detection and Segmentation
An important topic in manipulation detection is the localization of the fake regions.
Clothing-Change Feature Augmentation for Person Re-Identification
Specifically, to formulate meaningful clothing variations in the feature space, our method first estimates a clothing-change normal distribution with intra-ID cross-clothing variances.
GaFET: Learning Geometry-aware Facial Expression Translation from In-The-Wild Images
In this paper, we introduce a novel Geometry-aware Facial Expression Translation (GaFET) framework, which is based on parametric 3D facial representations and can stably decoupled expression.
Towards Realistic Unsupervised Fine-tuning with CLIP
The emergence of vision-language models (VLMs), such as CLIP, has spurred a significant research effort towards their application for downstream supervised learning tasks.
MSRA-SR: Image Super-resolution Transformer with Multi-scale Shared Representation Acquisition
In particular, self-attention with cross-scale matching and convolution filters with different kernel sizes are designed to exploit the multi-scale features in images.
Model-free Test Time Adaptation for Out-Of-Distribution Detection
We demonstrate the effectiveness of \abbr through comprehensive experiments on multiple OOD detection benchmarks, extensive empirical studies show that \abbr significantly improves the performance of OOD detection over state-of-the-art methods.
AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis
Audio-driven talking head synthesis is a promising topic with wide applications in digital human, film making and virtual reality.
Assaying on the Robustness of Zero-Shot Machine-Generated Text Detectors
In an effort to address these issues, we delve into the realm of zero-shot machine-generated text detection.
GraphDIVE: Graph Classification by Mixture of Diverse Experts
Graph classification is a challenging research problem in many applications across a broad range of domains.
Not all Minorities are Equal: Empty-Class-Aware Distillation for Heterogeneous Federated Learning
Data heterogeneity, characterized by disparities in local data distribution across clients, poses a significant challenge in federated learning.
Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
This paper proposes a \textbf{C}ollabo\textbf{ra}tive \textbf{F}ine-\textbf{T}uning (\textbf{CraFT}) approach for fine-tuning black-box VLMs to downstream tasks, where one only has access to the input prompts and the output predictions of the model.
KEBench: A Benchmark on Knowledge Editing for Large Vision-Language Models
We conducted experiments of different editing methods on five LVLMs, and thoroughly analyze how these methods impact the models.
Artifact Feature Purification for Cross-domain Detection of AI-generated Images
We also find that the artifact features APN focuses on across generators and scenes are global and diverse.
