Search Results for author:
Found 176 papers, 53 papers with code
From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion
Additionally, diffusion models typically rely on global learned distributions rather than localized features, leading to inconsistencies between the generated and existing image parts.
Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum
Employing DFL methods to solve such general optimization problems leads to the formulation of Decentralized Nonconvex Composite Federated Learning (DNCFL), a topic that remains largely underexplored.
SmartFreeEdit: Mask-Free Spatial-Aware Image Editing with Complex Instruction Understanding
The key innovations of SmartFreeEdit include:(1)the introduction of region aware tokens and a mask embedding paradigm that enhance the spatial understanding of complex scenes;(2) a reasoning segmentation pipeline designed to optimize the generation of editing masks based on natural language instructions;and (3) a hypergraph-augmented inpainting module that ensures the preservation of both structural integrity and semantic coherence during complex edits, overcoming the limitations of local-based image generation.
Metric-Solver: Sliding Anchored Metric Depth Estimation from a Single Image
Our design enables a unified and adaptive depth representation across diverse environments.
OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding
In this paper, we propose a novel framework for controllable video diffusion, OmniVDiff, aiming to synthesize and comprehend multiple video visual content in a single diffusion model.
AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations
Furthermore, we propose an innovative model especially for the AerialVG task, where a Hierarchical Cross-Attention is devised to focus on target regions, and a Relation-Aware Grounding module is designed to infer positional relations.
Bridging the Gap between Continuous and Informative Discrete Representations by Random Product Quantization
Its quantization error is lower-bounded by the product of rho and epsilon-kms, where epsilon-kms denotes the quantization error of a single K-means quantizer.
Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation
Building a lifelong robot that can effectively leverage prior knowledge for continuous skill acquisition remains significantly challenging.
Riemannian Optimization on Relaxed Indicator Matrix Manifold
The indicator matrix plays an important role in machine learning, but optimizing it is an NP-hard problem.
Optimal Transport Adapter Tuning for Bridging Modality Gaps in Few-Shot Remote Sensing Scene Classification
Central to this approach is the Optimal Transport Adapter (OTA), which employs a cross-modal attention mechanism to enrich textual representations and facilitate subsequent better information interaction.
Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference
To address this challenge, we propose a task-oriented feature compression (TOFC) method for multimodal understanding in a device-edge co-inference framework, where visual features are merged by clustering and encoded by a learnable and selective entropy model before feature projection.
MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation
Our approach enables models to learn affordance-based final positioning that accommodates different arm types and platform heights, thereby paving the way for more robust and generalizable integration of navigation and manipulation in embodied AI.
Bidirectional Prototype-Reward co-Evolution for Test-Time Adaptation of Vision-Language Models
BPRE first employs a Multi-Dimensional Quality-Aware Reward Module to evaluate feature quality and guide prototype refinement precisely.
NFIG: Autoregressive Image Generation with Next-Frequency Prediction
Autoregressive models have achieved promising results in natural language processing.
Large model enhanced computational ghost imaging
Ghost imaging (GI) achieves 2D image reconstruction through high-order correlation of 1D bucket signals and 2D light field information, particularly demonstrating enhanced detection sensitivity and high-quality image reconstruction via efficient photon collection in scattering media.
From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models
Aligning large vision-language models (LVLMs) with human preferences is challenging due to the scarcity of fine-grained, high-quality, and multimodal preference data without human annotations.
DualSpec: Text-to-spatial-audio Generation via Dual-Spectrogram Guided Diffusion Model
Particularly, to improve the synthesis quality and azimuth accuracy of the spatial sound events simultaneously, we propose to use two kinds of acoustic features.
OpenFly: A Versatile Toolchain and Large-scale Benchmark for Aerial Vision-Language Navigation
Particularly, 3D GS supports real-to-sim rendering, further enhancing the realism of the dataset.
Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learning
Humans possess delicate dynamic balance mechanisms that enable them to maintain stability across diverse terrains and under extreme conditions.
Improve LLM-as-a-Judge Ability as a General Ability
Furthermore, our training method enhances the general capabilities of the model by constructing complicated judge task, and the judge signals provided by our model have significantly enhanced the downstream DPO training performance of our internal models in our test to optimize policy model with Judge Model.
Leader and Follower: Interactive Motion Generation under Trajectory Constraints
To generate interactive motion following specified trajectories, this paper decouples complex motion into a Leader - Follower dynamic, inspired by role allocation in partner dancing.
AudioSpa: Spatializing Sound Events with Text
Additionally, we propose a binaural source localization model to assess the quality of the generated audio.
Exploring the Potential of Encoder-free Architectures in 3D LMMs
In this paper, we present the first comprehensive investigation into the potential of encoder-free architectures to overcome the challenges of encoder-based 3D Large Multimodal Models (LMMs).
UniForm: A Unified Multi-Task Diffusion Transformer for Audio-Video Generation
With the rise of diffusion models, audio-video generation has been revolutionized.
Dual-Bounded Nonlinear Optimal Transport for Size Constrained Min Cut Clustering
Min cut is an important graph partitioning method.
SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
Specifically, we introduce Ego3D Position Encoding to inject 3D information into the input observations of the visual-language-action model, and propose Adaptive Action Grids to represent spatial robot movement actions with adaptive discretized action grids, facilitating learning generalizable and transferrable spatial action knowledge for cross-robot control.
Ranked #2 on
Robot Manipulation
on SimplerEnv-Widow X
(using extra training data)
Graph Feedback Bandits on Similar Arms: With and Without Graph Structures
In this paper, we study the stochastic multi-armed bandit problem with graph feedback.
Enhancing Intelligibility for Generative Target Speech Extraction via Joint Optimization with Target Speaker ASR
Nevertheless, these methods often overlook speech intelligibility, leading to alterations or loss of semantic content in the re-synthesized speech.
Online Preference Alignment for Language Models via Count-based Exploration
Then, we reformulate our objective to direct preference optimization with an exploration term, where the UCB-term can be converted to a count-based exploration bonus.
FGAseg: Fine-Grained Pixel-Text Alignment for Open-Vocabulary Semantic Segmentation
The core of FGAseg is a Pixel-Level Alignment module that employs a cross-modal attention mechanism and a text-pixel alignment loss to refine the coarse-grained alignment from CLIP, achieving finer-grained pixel-text semantic alignment.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+1
A Greedy Strategy for Graph Cut
To reduce the computational complexity of GGC, only mergers between clusters and their neighbors are considered.
VAST 1.0: A Unified Framework for Controllable and Consistent Video Generation
Generating high-quality videos from textual descriptions poses challenges in maintaining temporal coherence and control over subject motion.
Enhance Vision-Language Alignment with Noise
It therefore implies a new scheme to learn beneficial noise distribution that can be employed to fine-tune VL models.
Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?
Inspired by the theoretical conclusions and the idea of positive-incentive noise, we propose a novel GCL algorithm, Error-PAssing-based Graph Contrastive Learning (EPAGCL), which uses both edge adding and edge dropping as its augmentations.
G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation
Our results demonstrate the effectiveness of G3Flow in enhancing real-time dynamic semantic feature understanding for robotic manipulation policies.
Open-Vocabulary Octree-Graph for 3D Scene Understanding
Open-vocabulary 3D scene understanding is indispensable for embodied agents.
Night-to-Day Translation via Illumination Degradation Disentanglement
Specifically, our method comprises a degradation disentanglement module and a degradation-aware contrastive learning module.
AI Flow at the Network Edge
This article presents AI Flow, a framework that streamlines the inference process by jointly leveraging the heterogeneous resources available across devices, edge nodes, and cloud servers, making intelligence flow across networks.
Autonomous Decision Making for UAV Cooperative Pursuit-Evasion Game with Reinforcement Learning
This paper proposes a deep reinforcement learning-based model for decision-making in multi-role UAV cooperative pursuit-evasion game, to address the challenge of enabling UAV to autonomously make decisions in complex game environments.
Fast Semi-supervised Learning on Large Graphs: An Improved Green-function Method
In the graph-based semi-supervised learning, the Green-function method is a classical method that works by computing the Green's function in the graph space.
Clustering Based on Density Propagation and Subcluster Merging
We propose the DPSM method, a density-based node clustering approach that automatically determines the number of clusters and can be applied in both data space and graph space.
Physics in Next-token Prediction
We discovered the underlying physics in Next-token Prediction (NTP).
FreeGaussian: Guidance-free Controllable 3D Gaussian Splats with Flow Derivatives
Reconstructing controllable Gaussian splats from monocular video is a challenging task due to its inherently insufficient constraints.
Efficient Diffusion as Low Light Enhancer
In this paper, we identify two primary factors contributing to performance degradation: fitting errors and the inference gap.
Aerial Vision-and-Language Navigation via Semantic-Topo-Metric Representation Guided LLM Reasoning
Aerial Vision-and-Language Navigation (VLN) is a novel task enabling Unmanned Aerial Vehicles (UAVs) to navigate in outdoor environments through natural language instructions and visual cues.
SurANet: Surrounding-Aware Network for Concealed Object Detection via Highly-Efficient Interactive Contrastive Learning Strategy
In this paper, considering that the surrounding environment information can be well utilized to identify the concealed objects, and thus, we propose a novel deep Surrounding-Aware Network, namely SurANet, for COD tasks, which introduces surrounding information into feature extraction and loss function to improve the discrimination.
Personalized Quantum Federated Learning for Privacy Image Classification
A personalized quantum federated learning algorithm for privacy image classification is proposed to enhance the personality of the client model in the case of an imbalanced distribution of images.
Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model
To this end, we establish a causal framework for ST predictions, termed CaPaint, which targets to identify causal regions in data and endow model with causal reasoning ability in a two-stage process.
Semi-LLIE: Semi-supervised Contrastive Learning with Mamba-based Low-light Image Enhancement
Despite the impressive advancements made in recent low-light image enhancement techniques, the scarcity of paired data has emerged as a significant obstacle to further advancements.
COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models
Specifically, a Proposal-Execution-Feedback-Adjustment (PEFA) mechanism is designed to decompose and assign actions for individual robots, where a centralized task assigner makes a task planning proposal to decompose the complex task into subtasks, and then assigns subtasks to robot executors.
AlignBot: Aligning VLM-powered Customized Task Planning with User Reminders Through Fine-Tuning for Household Robots
To validate the effectiveness of AlignBot, experiments are conducted in real-world household environments, which are constructed within the laboratory to replicate typical household settings.
Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding
To the best of our knowledge, this marks the first successful attempt of DER in VTG.
PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting
The self-attention mechanism in Transformer architecture, invariant to sequence order, necessitates positional embeddings to encode temporal order in time series prediction.
Ranked #1 on
Time Series Forecasting
on Traffic (720)
Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise
Inspired by the theoretical study, a framework that develops a $\pi$-noise generator to learn the beneficial noise (instead of estimation) as data augmentations for contrast is proposed.
ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model
In this paper, we propose a novel approach, ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model, which aims to comprehensively distill the knowledge from a large teacher CLIP model into a smaller student model, ensuring comparable performance with significantly reduced parameters.
KOI: Accelerating Online Imitation Learning via Hybrid Key-state Guidance
Within the intervals between semantic key states, optical flow is employed to capture motion key states to understand the mechanisms of "how to do".
Play to the Score: Stage-Guided Dynamic Multi-Sensory Fusion for Robotic Manipulation
Humans possess a remarkable talent for flexibly alternating to different senses when interacting with the environment.
Cross-Scan Mamba with Masked Training for Robust Spectral Imaging
Current CNN-based methods are limited in modeling long-range dependencies, while Transformer-based models face high computational complexity.
SentenceVAE: Enable Next-sentence Prediction for Large Language Models with Faster Speed, Higher Accuracy and Longer Context
Current large language models (LLMs) primarily utilize next-token prediction method for inference, which significantly impedes their processing speed.
Diffusion-driven lensless fiber endomicroscopic quantitative phase imaging towards digital pathology
Lensless fiber endomicroscope is an emerging tool for in-vivo microscopic imaging, where quantitative phase imaging (QPI) can be utilized as a label-free method to enhance image contrast.
Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
This work provides a theoretical foundation for understanding and improving PEFT-CL models, offering insights into the interplay between feature representation, task orthogonality, and generalization, contributing to the development of more efficient continual learning systems.
RB-SQL: A Retrieval-based LLM Framework for Text-to-SQL
Large language models (LLMs) with in-context learning have significantly improved the performance of text-to-SQL task.
52B to 1T: Lessons Learned via Tele-FLM Series
Large Language Models (LLMs) represent a significant stride toward Artificial General Intelligence.
LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Control
This paper scales object-level reconstruction to complex scenes, advancing interactive scene reconstruction.
Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
We cast the dynamics learning as an auto-regressive sequence modeling problem over discrete tokens by leveraging the expressive Transformer architecture, in order to model complex local dynamics across different agents and provide accurate and consistent long-term imaginations.
Technique Report of CVPR 2024 PBDL Challenges
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies.
Learning Manipulation by Predicting Interaction
To this end, we propose a general pre-training pipeline that learns Manipulation by Predicting the Interaction (MPI) and enhances the visual representation. Given a pair of keyframes representing the initial and final states, along with language instructions, our algorithm predicts the transition frame and detects the interaction object, respectively.
SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation
In this paper, we propose SAM-E, a novel architecture for robot manipulation by leveraging a vision-foundation model for generalizable scene understanding and sequence imitation for long-term action reasoning.
U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation
To address this issue, we leverage the inherent capabilities of the model itself to discover the optimal equilibrium in multimodal fusion and introduce U3M: An Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation.
Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration
In this paper, we propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans.
Adaptive Fuzzy C-Means with Graph Embedding
Fuzzy clustering algorithms can be roughly categorized into two main groups: Fuzzy C-Means (FCM) based methods and mixture model based methods.
Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning
In this paper, we propose a novel representation-based approach to measure the domain gap, where the representation is learned through a contrastive objective by sampling transitions from different domains.
Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning
Finally, we extend Reg-MAIDS to multi-player general-sum MGs and prove that it can learn either the Nash equilibrium or coarse correlated equilibrium in a sample efficient manner.
Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning
We further provide theoretical analysis, which shows that the optimality gap of our method is only related to the expected data coverage of the shared dataset, thus resolving the distribution shift issue in data sharing.
Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer
Emotion recognition aims to discern the emotional state of subjects within an image, relying on subject-centric and contextual visual cues.
Robust Capped lp-Norm Support Vector Ordinal Regression
Adhering to this concept, we introduce a new model, Capped $\ell_{p}$-Norm Support Vector Ordinal Regression(CSVOR), that is robust to outliers.
Tele-FLM Technical Report
Large language models (LLMs) have showcased profound capabilities in language understanding and generation, facilitating a wide array of applications.
CNN2GNN: How to Bridge CNN with GNN
Notably, due to extracting the intra-sample representation of a single instance and the topological relationship among the datasets simultaneously, the performance of distilled ``boosted'' two-layer GNN on Mini-ImageNet is much higher than CNN containing dozens of layers such as ResNet152.
LEAF: Unveiling Two Sides of the Same Coin in Semi-supervised Facial Expression Recognition
LEAF introduces a hierarchical expression-aware aggregation strategy that operates at three levels: semantic, instance, and category.
Facial Expression Recognition
Facial Expression Recognition (FER)
Dynamic Proxy Domain Generalizes the Crowd Localization by Better Binary Segmentation
Then, based on the theory, we design a DPD algorithm which is composed by a training paradigm and proxy domain generator to enhance the domain generalization of the confidence-threshold learner.
CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learning
Zero-shot learning (ZSL) enables the recognition of novel classes by leveraging semantic knowledge transfer from known to unknown categories.
VFMM3D: Releasing the Potential of Image by Vision Foundation Model for Monocular 3D Object Detection
Therefore, an effective solution involves transforming monocular images into LiDAR-like representations and employing a LiDAR-based 3D object detector to predict the 3D coordinates of objects.
StreakNet-Arch: An Anti-scattering Network-based Architecture for Underwater Carrier LiDAR-Radar Imaging
In this paper, we introduce StreakNet-Arch, a novel signal processing architecture designed for Underwater Carrier LiDAR-Radar (UCLR) imaging systems, to address the limitations in scatter suppression and real-time imaging.
Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding
The adapter incorporates prior spatial knowledge from the source modality to guide the local feature aggregation of 3D tokens, compelling the semantic adaption of any-modality transformers.
Regularized Conditional Diffusion Model for Multi-Task Preference Alignment
Sequential decision-making is desired to align with human intents and exhibit versatility across various tasks.
HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation
In this paper, we propose a novel hybrid pseudo-labeling framework for unsupervised event-based semantic segmentation, HPL-ESS, to alleviate the influence of noisy pseudo labels.
Deep Contrastive Graph Learning with Clustering-Oriented Guidance
Graph Convolutional Network (GCN) has exhibited remarkable potential in improving graph-based clustering.
Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training
In the pre-training stage, we employ a discrete diffusion model with a mask-and-replace diffusion strategy to predict future video tokens in the latent space.
QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems
Subsequently, QuanTest formulates the problem of generating test inputs that maximize the quantum entanglement adequacy and capture incorrect behaviors of the QNN system as a joint optimization problem and solves it in a gradient-based manner to generate quantum adversarial examples.
Motion-Aware Video Frame Interpolation
Subsequently, a cross-scale motion structure is presented to estimate and refine intermediate flow maps by the extracted features.
GQHAN: A Grover-inspired Quantum Hard Attention Network
In response to the dilemma of HAM and QML, a Grover-inspired Quantum Hard Attention Mechanism (GQHAM) consisting of a Flexible Oracle (FO) and an Adaptive Diffusion Operator (ADO) is proposed.
NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial Images
Considering the absence of a dataset for this task, a large-scale Dataset (NWPU-MOC) is collected, consisting of 3, 416 scenes with a resolution of 1024 $\times$ 1024 pixels, and well-annotated using 14 fine-grained object categories.
Community Detection in the Multi-View Stochastic Block Model
This paper considers the problem of community detection on multiple potentially correlated graphs from an information-theoretical perspective.
TeleChat Technical Report
Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe.
Frequency Domain Nuances Mining for Visible-Infrared Person Re-identification
Specifically, we propose a novel Frequency Domain Nuances Mining (FDNM) method to explore the cross-modality frequency domain information, which mainly includes an amplitude guided phase (AGP) module and an amplitude nuances mining (ANM) module.
SMC-NCA: Semantic-guided Multi-level Contrast for Semi-supervised Temporal Action Segmentation
However, learning the representation of each frame by unsupervised contrastive learning for action segmentation remains an open and challenging problem.
Calibration-free quantitative phase imaging in multi-core fiber endoscopes using end-to-end deep learning
Quantitative phase imaging (QPI) through multi-core fibers (MCFs) has been an emerging in vivo label-free endoscopic imaging modality with minimal invasiveness.
DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image Enhancement
To solve this issue, previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features, limiting the generalization and adaptability of the model.
A Novel Normalized-Cut Solver with Nearest Neighbor Hierarchical Initialization
To address the problems, we propose a novel N-Cut solver designed based on the famous coordinate descent method.
Eliminating Quantization Errors in Classification-Based Sound Source Localization
To address this, we propose an Unbiased Label Distribution (ULD) to eliminate quantization error in training targets.
GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting
This strategy is essential to extend 3D Gaussian representation to reconstruct the whole scene rather than synthesize a static object in existing methods.
Implicit Event-RGBD Neural SLAM
To address these challenges, we propose EN-SLAM, the first event-RGBD implicit neural SLAM framework, which effectively leverages the high rate and high dynamic range advantages of event data for tracking and mapping.
Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMs
Generalizable articulated object manipulation is essential for home-assistant robots.
Diffusion-Based Adversarial Purification for Speaker Verification
Recently, automatic speaker verification (ASV) based on deep learning is easily contaminated by adversarial attacks, which is a new type of attack that injects imperceptible perturbations to audio signals so as to make ASV produce wrong decisions.
Discretize Relaxed Solution of Spectral Clustering via a Non-Heuristic Algorithm
Unfortunately, the goal of the existing methods is not to find a discrete solution that minimizes the original objective.
Distance Weighted Trans Network for Image Completion
The challenge of image generation has been effectively modeled as a problem of structure priors or transformation.
Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models
To this end, we introduce Point-PEFT, a novel framework for adapting point cloud pre-trained models with minimal learnable parameters.
QKSAN: A Quantum Kernel Self-Attention Network
Self-Attention Mechanism (SAM) excels at distilling important information from the interior of data to improve the computational efficiency of models.
Disentangled Contrastive Image Translation for Nighttime Surveillance
Targeting the surveillance scenes, we develop a disentangled representation, which is an auxiliary pretext task that separates surveillance scenes into the foreground and background with contrastive learning.
Sequential Attention Source Identification Based on Feature Representation
Snapshot observation based source localization has been widely studied due to its accessibility and low cost.
Hierarchical Matching and Reasoning for Multi-Query Image Retrieval
Afterwards, the VR module is developed to excavate the potential semantic correlations among multiple region-query pairs, which further explores the high-level reasoning similarity.
Variational Positive-incentive Noise: How Noise Benefits Models
From the experiments, it is shown that the proposed VPN generator can improve the base models.
Learning Geometric Transformation for Point Cloud Completion
It exploits the repetitive geometric structures in common 3D objects to recover the complete shapes, which contains three sub-networks: geometric patch network, structure transformation network, and detail refinement network.
Ranked #4 on
Point Cloud Completion
on ShapeNet
Image Reconstruction for Accelerated MR Scan with Faster Fourier Convolutional Neural Networks
To address this problem, we propose the following: (1) a novel convolutional operator called Faster Fourier Convolution (FasterFC) to replace the two consecutive convolution operations typically used in convolutional neural networks (e. g., U-Net, ResNet).
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
Specifically, we propose Multi-Task Diffusion Model (\textsc{MTDiff}), a diffusion-based method that incorporates Transformer backbones and prompt learning for generative planning and data synthesis in multi-task offline settings.
On the Value of Myopic Behavior in Policy Reuse
Leveraging learned strategies in unfamiliar scenarios is fundamental to human intelligence.
Imbalanced Aircraft Data Anomaly Detection
Anomaly detection in temporal data from sensors under aviation scenarios is a practical but challenging task: 1) long temporal data is difficult to extract contextual information with temporal correlation; 2) the anomalous data are rare in time series, causing normal/abnormal imbalance in anomaly detection, making the detector classification degenerate or even fail.
Behavior Contrastive Learning for Unsupervised Skill Discovery
Under mild assumptions, our objective maximizes the MI between different behaviors based on the same skill, which serves as an upper bound of the previous MI objective.
Transformer-based stereo-aware 3D object detection from binocular images
In this paper, we explore the model design of Transformers in binocular 3D object detection, focusing particularly on extracting and encoding task-specific image correspondence information.
Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One
It extremely limits the application of stochastic optimization algorithms so that the training of GNN is usually time-consuming.
One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field
Talking head generation aims to generate faces that maintain the identity information of the source image and imitate the motion of the driving image.
VTAE: Variational Transformer Autoencoder with Manifolds Learning
This weak projection, however, can be addressed by a Riemannian metric, and we show that geodesics computation and accurate interpolations between data samples on the Riemannian manifold can substantially improve the performance of deep generative models.
Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction
This paper addresses the problem of rolling shutter correction in complex nonlinear and dynamic scenes with extreme occlusion.
Ranked #2 on
Rolling Shutter Correction
on BS-RSC
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
In this paper, we propose ViewRefer, a multi-view framework for 3D visual grounding exploring how to grasp the view knowledge from both text and 3D modalities.
Propagate And Calibrate: Real-time Passive Non-line-of-sight Tracking
In contrast, we propose a purely passive method to track a person walking in an invisible room by only observing a relay wall, which is more in line with real application scenarios, e. g., security.
Fully Self-Supervised Depth Estimation from Defocus Clue
We show that our framework circumvents the needs for the depth and AIF image ground-truth, and receives superior predictions, thus closing the gap between the theoretical success of DFD works and their applications in the real world.
Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search
We hope that our simple intra-image contrastive learning can provide more paradigms on weakly supervised person search.
USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval
(2) It limits the scale of negative sample pairs by employing the mini-batch based end-to-end training mechanism.
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding
In this paper, we propose ViewRefer, a multi-view framework for 3D visual grounding exploring how to grasp the view knowledge from both text and 3D modalities.
Positive-incentive Noise
After introducing the task entropy, the noise can be classified into two kinds, Positive-incentive noise (Pi-noise or $\pi$-noise) and pure noise, according to whether the noise can reduce the complexity of the task.
On the Global Solution of Soft k-Means
This paper presents an algorithm to solve the Soft k-Means problem globally.
Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects
The mainstream crowd counting methods regress density map and integrate it to obtain counting results.
Search to Pass Messages for Temporal Knowledge Graph Completion
In particular, we develop a generalized framework to explore topological and temporal information in TKGs.
Ranked #1 on
Link Prediction
on GDELT
Deep Learning Based Stage-wise Two-dimensional Speaker Localization with Large Ad-hoc Microphone Arrays
To further boost the estimation accuracy, we introduce a node selection algorithm that strategically filters the most reliable nodes.
Meta-Causal Feature Learning for Out-of-Distribution Generalization
Causal inference has become a powerful tool to handle the out-of-distribution (OOD) generalization problem, which aims to extract the invariant features.
Learning in Audio-visual Context: A Review, Analysis, and New Perspective
A comprehensive survey that can systematically organize and analyze studies of the audio-visual field is expected.
Memorizing Complementation Network for Few-Shot Class-Incremental Learning
Few-shot Class-Incremental Learning (FSCIL) aims at learning new concepts continually with only a few samples, which is prone to suffer the catastrophic forgetting and overfitting problems.
class-incremental learning
Few-Shot Class-Incremental Learning
+3
Low-Light Hyperspectral Image Enhancement
The illumination enhancement branch is adopted to enlighten the low-frequency component with reduced resolution.
Deep Manifold Learning with Graph Mining
Admittedly, Graph Convolution Network (GCN) has achieved excellent results on graph datasets such as social networks, citation networks, etc.
QSAN: A Near-term Achievable Quantum Self-Attention Network
Self-Attention Mechanism (SAM) is good at capturing the internal connections of features and greatly improves the performance of machine learning models, espeacially requiring efficient characterization and feature extraction of high-dimensional data.
Spatio-temporal Gait Feature with Global Distance Alignment
In this paper, we try to enhance the discrimination of spatio-temporal gait features from two aspects: effective extraction of spatio-temporal gait features and reasonable refinement of extracted features.
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning
We theoretically validate that it is equivalent to the existing matrix completion models.
Relation Regularized Scene Graph Generation
Inspired by this observation, in this article, we propose a relation regularized network (R2-Net), which can predict whether there is a relationship between two objects and encode this relation into object feature refinement and better SGG.
New Tight Relaxations of Rank Minimization for Multi-Task Learning
Multi-task learning has been observed by many researchers, which supposes that different tasks can share a low-rank common yet latent subspace.
Adaptive Shrink-Mask for Text Detection
It weakens the coupling of texts to shrink-masks, which improves the robustness of detection results.
AnchorGAE: General Data Clustering via $O(n)$ Bipartite Graph Convolution
The core problems mainly come from two aspects: (1) the graph is unavailable in the most clustering scenes so that how to construct high-quality graphs on the non-graph data is usually the most important part; (2) given n samples, the graph-based clustering methods usually consume at least $\mathcal O(n^2)$ time to build graphs and the graph convolution requires nearly $\mathcal O(n^2)$ for a dense graph and $\mathcal O(|\mathcal{E}|)$ for a sparse one with $|\mathcal{E}|$ edges.
Audio-visual Representation Learning for Anomaly Events Detection in Crowds
The second is an audio CNN for encoding Log Mel-Spectrogram of audio signals.
LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
The rapid development in visual crowd analysis shows a trend to count people by positioning or even detecting, rather than simply summing a density map.
Hierarchical Multimodal Transformer to Summarize Videos
To integrate the two kinds of information, they are encoded in a two-stream scheme, and a multimodal fusion mechanism is developed based on the hierarchical transformer.
Ranked #17 on
Supervised Video Summarization
on TvSum
Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification
In addition, due to domain gaps between different datasets, the performance is dramatically decreased when re-ID models pre-trained on label-rich datasets (source domain) are directly applied to other unlabeled datasets (target domain).
Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer
To this end, we propose a Dilated Convolutional Swin Transformer (DCST) for congested crowd scenes.
VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint.
Deep Contrastive Graph Representation via Adaptive Homotopy Learning
In particular, in this paper, we apply AH to contrastive learning (AHCL) such that it can be effectively transferred from weak-supervised learning (given label priori) to unsupervised learning, where soft labels of contrastive learning are directly and adaptively learned.
Non-Gradient Manifold Neural Network
Moreover, by unifying the flexible Stiefel manifold and adaptive support vector machine, we devise the novel decision layer which efficiently fits the manifold structure of the data and label information.
Local $K$-means: An Efficient Optimization Algorithm And Its Generalization
We also developed a general model that unified LKM, KSUMS, and SC, and discussed the connection among them.
EA-Net: Edge-Aware Network for Flow-based Video Frame Interpolation
Specifically, in the flow estimation stage, three edge-aware mechanisms are developed to emphasize the frame edges in estimating flow maps, so that the edge-maps are taken as the auxiliary information to provide more guidance to boost the flow accuracy.
AudioVisual Video Summarization
Motivated by this, we propose to jointly exploit the audio and visual information for the video summarization task, and develop an AudioVisual Recurrent Network (AVRN) to achieve this.
Reconstructive Sequence-Graph Network for Video Summarization
Then, the videos are summarized by exploiting both the local and global dependencies among shots.
Spatial-Spectral Clustering with Anchor Graph for Hyperspectral Image
In order to better handle the high dimensionality problem and preserve the spatial structures, this paper proposes a novel unsupervised approach called spatial-spectral clustering with anchor graph (SSCAG) for HSI data clustering.
Auto-weighted Multi-view Feature Selection with Graph Optimization
In this paper, we focus on the unsupervised multi-view feature selection which tries to handle high dimensional data in the field of multi-view learning.
Spatial-spectral Hyperspectral Image Classification via Multiple Random Anchor Graphs Ensemble Learning
Graph-based semi-supervised learning methods, which deal well with the situation of limited labeled data, have shown dominant performance in practical applications.
Entropy Minimizing Matrix Factorization
Considering that the outliers are usually much less than the normal samples, a new entropy loss function is established for matrix factorization, which minimizes the entropy of the residue distribution and allows a few samples to have large approximation errors.
Feature Weighted Non-negative Matrix Factorization
Non-negative Matrix Factorization (NMF) is one of the most popular techniques for data representation and clustering, and has been widely used in machine learning and data analysis.
Enhanced Principal Component Analysis under A Collaborative-Robust Framework
Principal component analysis (PCA) frequently suffers from the disturbance of outliers and thus a spectrum of robust extensions and variations of PCA have been developed.
Multi-channel Deep Supervision for Crowd Counting
To obtain the accurate supervision information of different channels, the MDSNet employs an auxiliary network called SupervisionNet (SN) to generate abundant supervision maps based on existing groundtruth.
Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks
To this end, the generator of Weather GAN is composed of an initial translation module, an attention module and a weather-cue segmentation module.
Ensemble and Random Collaborative Representation-Based Anomaly Detector for Hyperspectral Imagery
To alleviate this problem, we proposed a novel ensemble and random collaborative representation-based detector (ERCRD) for HAD, which comprises two closely related stages.
Sparse PCA via $l_{2,p}$-Norm Regularization for Unsupervised Feature Selection
However, real-world data contain a large number of noise samples and features, making the similarity matrix constructed by original data cannot be completely reliable.
Learning Independent Instance Maps for Crowd Localization
Furthermore, to improve the segmentation quality for different density regions, we present a differentiable Binarization Module (BM) to output structured instance maps.
Efficient Clustering Based On A Unified View Of $K$-means And Ratio-cut
In particular, over 15x and 7x speed-up can be obtained with respect to $k$-means on the synthetic dataset of 1 million samples and the benchmark dataset (CelebA) of 200k samples, respectively [GitHub].
Learning Feature Sparse Principal Subspace
This paper presents new algorithms to solve the feature-sparsity constrained PCA problem (FSPCA), which performs feature selection and PCA simultaneously.
Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model
To address this problem, we here propose a novel multiview latent-attention and dynamic discriminative model that jointly learns view-specific and view-shared sub-structures, where the former captures unique dynamics of each view whilst the latter encodes the interaction between the views.
Ranked #4 on
Question Answering
on MultiTQ
Embedding Graph Auto-Encoder for Graph Clustering
Driven by theoretical analysis about relaxed k-means, we design a specific GAE-based model for graph clustering to be consistent with the theory, namely Embedding Graph Auto-Encoder (EGAE).
Low Rank Regularization: A Review
Low rank regularization, in essence, involves introducing a low rank or approximately low rank assumption for matrix we aim to learn, which has achieved great success in many fields including machine learning, data mining and computer version.
