Search Results for author:
Found 57 papers, 32 papers with code
Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection
In this study, a Down-Up Sampling Network (DUS-Net) is proposed to reconstruct high-precision point clouds for 3D anomaly detection by preserving the group center geometric structure.
Ranked #1 on
3D Anomaly Detection
on Real 3D-AD
EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models
To address this problem, we propose the Entity Visual Description enhanced CLIP (EvdCLIP), designed to leverage the visual knowledge of entities to enrich queries.
Logic-of-Thought: Empowering Large Language Models with Logic Programs for Solving Puzzles in Natural Language
This hybrid approach combines the natural language understanding of LLMs with the precise reasoning capabilities of logic programs.
Efficient Differentiable Approximation of Generalized Low-rank Regularization
To overcome this difficulty, various relaxations of the rank function were studied.
MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detection
Therefore, this paper presents a novel unified model for Multi-Category 3D Anomaly Detection (MC3D-AD) that aims to utilize both local and global geometry-aware information to reconstruct normal representations of all categories.
Ranked #3 on
3D Anomaly Detection
on Anomaly-ShapeNet
Embracing Collaboration Over Competition: Condensing Multiple Prompts for Visual In-Context Learning
Visual In-Context Learning (VICL) enables adaptively solving vision tasks by leveraging pixel demonstrations, mimicking human-like task completion through analogy.
FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning
We further extend FastVAR to zero-shot generation of higher resolution images.
Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations
Extensive experiments demonstrate that our video watermarking methods effectively protect video data by significantly reducing video annotation performance across various video-based LLMs, showcasing both stealthiness and robustness in protecting personal video content.
FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting
Addressing these limitations, we propose FinTSB, a comprehensive and practical benchmark for financial time series forecasting (FinTSF).
TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting
Time series forecasting methods generally fall into two main categories: Channel Independent (CI) and Channel Dependent (CD) strategies.
PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter
To overcome this limitation, we propose an orthogonal solution: Point Mamba Adapter (PMA), which constructs an ordered feature sequence from all layers of the pre-trained model and leverages Mamba to fuse all complementary semantics, thereby promoting comprehensive point cloud understanding.
Adapting Pre-trained 3D Models for Point Cloud Video Understanding via Cross-frame Spatio-temporal Perception
Point cloud video understanding is becoming increasingly important in fields such as robotics, autonomous driving, and augmented reality, as they can accurately represent object motion and environmental changes.
Diffusion Prior Interpolation for Flexibility Real-World Face Super-Resolution
In this paper, we propose a masking strategy with strong and weak constraints and iterative refinement for real-world FSR, termed Diffusion Prior Interpolation (DPI).
MambaIRv2: Attentive State Space Restoration
The Mamba-based image restoration backbones have recently demonstrated significant potential in balancing global reception and computational efficiency.
IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models
Fine-tuning pre-trained diffusion models under limited budgets has gained great success.
BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping
The historical samples are filtered from the testing data stream and serve to extract useful information from the target distribution, while the boosting samples are drawn from regional bootstrapping and capture the knowledge of the test sample itself.
Block-to-Scene Pre-training for Point Cloud Hybrid-Domain Masked Autoencoders
We first propose a hybrid-domain masked autoencoder consisting of an encoder and decoder belonging to the scene domain and object domain, respectively.
Towards Scalable Semantic Representation for Recommendation
With recent advances in large language models (LLMs), there has been emerging numbers of research in developing Semantic IDs based on LLMs to enhance the performance of recommendation systems.
ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
In this paper, we propose an orthogonal solution called the Retrieval-augmented Framework for Image Restoration (ReFIR), which incorporates retrieved images as external knowledge to extend the knowledge boundary of existing LRMs in generating details faithful to the original scene.
TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting
Eliminating non-stationarity is essential for avoiding spurious regressions and capturing local dependencies in short-term modeling, while preserving it is crucial for revealing long-term cointegration across variates.
Large Point-to-Gaussian Model for Image-to-3D Generation
Recently, image-to-3D approaches have significantly advanced the generation quality and speed of 3D assets based on large reconstruction models, particularly 3D Gaussian reconstruction models.
Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning
High-resolution point clouds~(HRPCD) anomaly detection~(AD) plays a critical role in precision machining and high-end equipment manufacturing.
Ranked #7 on
3D Anomaly Detection
on Real 3D-AD
CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks
Transferable targeted adversarial attacks aim to mislead models into outputting adversary-specified predictions in black-box scenarios.
Pre-training Point Cloud Compact Model with Partial-aware Reconstruction
Firstly, the positional embedding of masked patches in the decoder results in the leakage of their central coordinates, leading to limited 3D representations.
Hierarchical Features Matter: A Deep Exploration of GAN Priors for Improved Dataset Distillation
Dataset distillation is an emerging dataset reduction method, which condenses large-scale datasets while maintaining task accuracy.
Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting
Transformer-based and MLP-based methods have emerged as leading approaches in time series forecasting (TSF).
Ranked #14 on
Time Series Forecasting
on ETTh1 (336) Multivariate
LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling
Considering the varying information density between masked and unmasked patches in the decoder inputs of MPM, we introduce a locally constrained Mamba-based decoder.
MambaVC: Learned Visual Compression with Selective State Spaces
Learned visual compression is an important and active task in multimedia.
GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval
Given a text query, partially relevant video retrieval (PRVR) aims to retrieve untrimmed videos containing relevant moments.
Invertible Residual Rescaling Models
To address this issue, we propose Invertible Residual Rescaling Models (IRRM) for image rescaling by learning a bijection between a high-resolution image and its low-resolution counterpart with a specific distribution.
Boundary-aware Decoupled Flow Networks for Realistic Extreme Rescaling
Recently developed generative methods, including invertible rescaling network (IRN) based and generative adversarial network (GAN) based methods, have demonstrated exceptional performance in image rescaling.
RAT: Retrieval-Augmented Transformer for Click-Through Rate Prediction
Predicting click-through rates (CTR) is a fundamental task for Web applications, where a key issue is to devise effective models for feature interactions.
CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning
Unlike existing methods that focus on training models from a single modal of time series input, large language models (LLMs) based MTSF methods with cross-modal text and time series input have recently shown great superiority, especially with limited temporal data.
Ranked #42 on
Time Series Forecasting
on ETTh1 (336) Multivariate
Knowledge Distillation
Multivariate Time Series Forecasting
+2
MambaIR: A Simple Baseline for Image Restoration with State-Space Model
In this way, our MambaIR takes advantage of the local pixel similarity and reduces the channel redundancy.
Ranked #19 on
Image Super-Resolution
on Set14 - 4x upscaling
SpirDet: Towards Efficient, Accurate and Lightweight Infrared Small Target Detector
To tackle this challenge, we propose SpirDet, a novel approach for efficient detection of infrared small targets.
Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders
Specifically, to learn more compact features, a share-parameter Transformer encoder is introduced to extract point features from the global and local unmasked patches obtained by global random and local block mask strategies, followed by a specific decoder to reconstruct.
Ranked #5 on
Few-Shot 3D Point Cloud Classification
on ModelNet40 10-way (10-shot)
(using extra training data)
Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts
In this work, we introduce an alternative solution to improve the generalization of image restoration models.
Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression
In this paper, we propose a progressive learning paradigm for transformer-based variable-rate image compression.
Perceptual Image Compression with Cooperative Cross-Modal Side Information
The explosion of data has resulted in more and more associated text being transmitted along with images.
WFTNet: Exploiting Global and Local Periodicity in Long-term Time Series Forecasting
In this paper, we propose a Wavelet-Fourier Transform Network (WFTNet) for long-term time series forecasting.
One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer
Current solutions for low-resolution text recognition (LTR) typically rely on a two-stage pipeline that involves super-resolution as the first stage followed by the second-stage recognition.
Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement
Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success.
Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models.
3D Parameter-Efficient Fine-Tuning for Classification
Few-Shot 3D Point Cloud Classification
+1
Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model
Unsupervised surface anomaly detection aims at discovering and localizing anomalous patterns using only anomaly-free training samples.
Towards Effective Image Manipulation Detection with Proposal Contrastive Learning
Most existing methods mainly focus on extracting global features from tampered images, while neglecting the relationships of local features between tampered and authentic regions within a single tampered image.
Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature Domain
Specifically, MSFDPM consists of a side information feature extractor, a multi-scale feature domain patch matching module, and a multi-scale feature fusion network.
VLMAE: Vision-Language Masked Autoencoder
Image and language modeling is of crucial importance for vision-language pre-training (VLP), which aims to learn multi-modal representations from large-scale paired image-text data.
Adaptive Local Implicit Image Function for Arbitrary-scale Super-resolution
Image representation is critical for many visual tasks.
Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer
Specifically, our method exploits multi-modal knowledge of image-text pairs based on a vision and language pre-training (VLP) model.
Ranked #1 on
Multi-label zero-shot learning
on Open Images V4
A Comparative Study of Feature Expansion Unit for 3D Point Cloud Upsampling
Recently, deep learning methods have shown great success in 3D point cloud upsampling.
Contrastive Quantization with Code Memory for Unsupervised Image Retrieval
The high efficiency in computation and storage makes hashing (including binary hashing and quantization) a common strategy in large-scale retrieval systems.
PHPQ: Pyramid Hybrid Pooling Quantization for Efficient Fine-Grained Image Retrieval
To improve fine-grained image hashing, we propose Pyramid Hybrid Pooling Quantization (PHPQ).
JSRT: James-Stein Regression Tree
To address this issue, we propose a novel regression tree, named James-Stein Regression Tree (JSRT) by considering global information from different nodes.
DPAttack: Diffused Patch Attacks against Universal Object Detection
Recently, deep neural networks (DNNs) have been widely and successfully used in Object Detection, e. g.
Adversarial Attack on Deep Product Quantization Network for Image Retrieval
Deep product quantization network (DPQN) has recently received much attention in fast image retrieval tasks due to its efficiency of encoding high-dimensional visual features especially when dealing with large-scale datasets.
Second-Order Attention Network for Single Image Super-Resolution
Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and obtained remarkable performance.
Ranked #13 on
Image Super-Resolution
on BSD100 - 4x upscaling
Exploiting Common Characters in Chinese and Japanese to Learn Cross-Lingual Word Embeddings via Matrix Factorization
Learning vector space representation of words (i. e., word embeddings) has recently attracted wide research interests, and has been extended to cross-lingual scenario.
