Search Results for author:
Found 89 papers, 38 papers with code
State Space Model for New-Generation Network Alternative to Transformers: A Survey
In this paper, we give the first comprehensive review of these works and also provide experimental comparisons and analysis to better demonstrate the features and advantages of SSM.
Long-term Frame-Event Visual Tracking: Benchmark Dataset and Baseline
Current event-/frame-event based trackers undergo evaluation on short-term tracking datasets, however, the tracking of real-world scenarios involves long-term tracking, and the performance of existing tracking algorithms in these scenarios remains unclear.
Uncertainty-aware Bridge based Mobile-Former Network for Event-based Pattern Recognition
The mainstream human activity recognition (HAR) algorithms are developed based on RGB cameras, which are easily influenced by low-quality images (e. g., low illumination, motion blur).
Full-frequency dynamic convolution: a physical frequency-dependent convolution for sound event detection
Recently, 2D convolution has been found unqualified in sound event detection (SED).
Unifying Graph Contrastive Learning via Graph Message Augmentation
Based on the proposed GMA, we then propose a unified graph contrastive learning, termed Graph Message Contrastive Learning (GMCL), that employs attribution-guided universal GMA for graph contrastive learning.
CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras
In this work, we formally propose the task of object tracking using unaligned neuromorphic and visible cameras.
Modality-missing RGBT Tracking: Invertible Prompt Learning and High-quality Benchmarks
To address this challenge, we propose a novel invertible prompt learning approach, which integrates the content-preserving prompts into a well-trained tracking model to adapt to various modality-missing scenarios, for robust RGBT tracking.
Nighttime Person Re-Identification via Collaborative Enhancement Network with Multi-domain Learning
To perform effective collaborative modeling between image relighting and person ReID tasks, we integrate the multilevel feature interactions in CENet.
Prototype-based Cross-Modal Object Tracking
In particular, we design a multi-modal prototype to represent target information by multi-kind samples, including a fixed sample from the first frame and two representative samples from different modalities.
Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale Dataset
Visual tracking often faces challenges such as invalid targets and decreased performance in low-light conditions when relying solely on RGB image sequences.
Cross-Covariate Gait Recognition: A Benchmark
Compared to existing datasets, CCGR has both population and individual-level diversity.
A Multi-Stage Adaptive Feature Fusion Neural Network for Multimodal Gait Recognition
In this paper, by considering the temporal and spatial characteristics of gait data, we propose a multi-stage feature fusion strategy (MSFFS), which performs multimodal fusions at different stages in the feature extraction process.
Unleashing the Power of CNN and Transformer for Balanced RGB-Event Video Recognition
It is intuitive to combine them for high-performance RGB-Event based video recognition, however, existing works fail to achieve a good balance between the accuracy and model parameters, as shown in Fig.~\ref{firstimage}.
Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion
In this paper, we formulate PAR as a vision-language fusion problem and fully exploit the relations between pedestrian images and attribute labels.
Structural Information Guided Multimodal Pre-training for Vehicle-centric Perception
To address this issue, we propose a novel vehicle-centric pre-training framework called VehicleMAE, which incorporates the structural information including the spatial structure from vehicle profile information and the semantic structure from informative high-level natural language descriptions for effective masked vehicle appearance reconstruction.
SequencePAR: Understanding Pedestrian Attributes via A Sequence Generation Paradigm
Then, a Transformer decoder is proposed to generate the human attributes by incorporating the visual features and attribute query tokens.
Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline
Tracking using bio-inspired event cameras has drawn more and more attention in recent years.
Illumination Distillation Framework for Nighttime Person Re-Identification and A New Benchmark
The illumination enhancement branch first estimates an enhanced image from the nighttime image using a nonlinear curve mapping method and then extracts the enhanced features.
SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition
Secondly, they adopt either Spiking Neural Networks (SNN) for energy-efficient recognition with suboptimal results, or Artificial Neural Networks (ANN) for energy-intensive, high-performance recognition.
Point-Voxel Absorbing Graph Representation Learning for Event Stream based Recognition
To address these issues, we propose a novel dual point-voxel absorbing graph representation learning for event stream data representation.
A Robust Feature Downsampling Module for Remote Sensing Visual Tasks
To address this problem, we propose a new and universal downsampling module named robust feature downsampling (RFD).
AMatFormer: Efficient Feature Matching via Anchor Matching Transformer
Second, AMatFormer adopts a shared FFN module to further embed the features of two images into the common domain and thus learn the consensus feature representations for the matching problem.
Dynamic Enhancement Network for Partial Multi-modality Person Re-identification
Many existing multi-modality studies are based on the assumption of modality integrity.
Multi-query Vehicle Re-identification: Viewpoint-conditioned Network, Unified Dataset and New Metric
Existing vehicle re-identification methods mainly rely on the single query, which has limited information for vehicle representation and thus significantly hinders the performance of vehicle Re-ID in complicated surveillance networks.
AGFormer: Efficient Graph Representation with Anchor-Graph Transformer
To alleviate the local receptive issue of GCN, Transformers have been exploited to capture the long range dependences of nodes for graph data representation and learning.
RGBT Tracking via Progressive Fusion Transformer with Dynamically Guided Learning
In addition, existing learning methods of RGBT trackers either fuse multimodal features into one for final classification, or exploit the relationship between unimodal branches and fused branch through a competitive learning strategy.
An end-to-end multi-scale network for action prediction in videos
Unlike most existing methods with offline feature generation, our method directly takes frames as input and further models motion evolution on two different temporal scales. Therefore, we solve the complexity problems of the two stages of modeling and the problem of insufficient temporal and spatial information of a single scale.
Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts
Most existing methods perform training on multiple source domains using a single model, and the same trained model is used on all unseen target domains.
Ranked #22 on
Domain Generalization
on DomainNet
Hand Hygiene Assessment via Joint Step Segmentation and Key Action Scorer
To address this issue, we design a multi-stage convolution-transformer network for step segmentation.
Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization
Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects.
Multi-spectral Vehicle Re-identification with Cross-directional Consistency Network and a High-quality Benchmark
In particular, we design a new cross-directional center loss to pull the modality centers of each identity close to mitigate cross-modality discrepancy, while the sample centers of each identity close to alleviate the sample discrepancy.
Error-Aware Spatial Ensembles for Video Frame Interpolation
However, none of the published VFI works considers the spatially non-uniform characteristics of the interpolation error (IE).
Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay
In this paper, we show through empirical results that adopting the data replay is surprisingly favorable.
Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Dataset
License plate recognition plays a critical role in many practical applications, but license plates of large vehicles are difficult to be recognized due to the factors of low resolution, contamination, low illumination, and occlusion, to name a few.
Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search
To track the target in a video, current visual trackers usually adopt greedy search for target object localization in each frame, that is, the candidate region with the maximum response score will be selected as the tracking result of each frame.
Past and Future Motion Guided Network for Audio Visual Event Localization
In recent years, audio-visual event localization has attracted much attention.
Tiny Object Tracking: A Large-scale Dataset and A Baseline
Tiny objects, frequently appearing in practical applications, have weak appearance and features, and receive increasing interests in meany vision tasks, such as object detection and segmentation.
Attribute-Based Progressive Fusion Network for RGBT Tracking
RGBT tracking usually suffers from various challenging factors of fast motion, scale variation, illumination variation, thermal crossover and occlusion, to name a few.
Ranked #3 on
Rgb-T Tracking
on GTOT
MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning
The learning objective of these methods is often hand-engineered and is not directly tied to the objective (i. e. incrementally learning new classes) during testing.
MutualFormer: Multi-Modality Representation Learning via Cross-Diffusion Attention
In this work, we re-think Transformer and extend it to MutualFormer for multi-modality data representation.
GAMnet: Robust Feature Matching via Graph Adversarial-Matching Network
Also, GAMnet exploits sparse GM optimization as correspondence solver which is differentiable and can also incorporate discrete one-to-one matching constraints approximately in natural in the final matching prediction.
Ranked #7 on
Graph Matching
on PASCAL VOC
(matching accuracy metric)
Test-Time Fast Adaptation for Dynamic Scene Deblurring via Meta-Auxiliary Learning
Therefore, we are able to exploit the internal information at test time via the auxiliary task to enhance the performance of deblurring.
Tracking by Joint Local and Global Search: A Target-aware Attention based Approach
In this paper, we propose a novel and general target-aware attention mechanism (termed TANet) and integrate it with tracking-by-detection framework to conduct joint local and global search for robust tracking.
LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking
RGBT tracking receives a surge of interest in the computer vision community, but this research field lacks a large-scale and high-diversity benchmark dataset, which is essential for both the training of deep RGBT trackers and the comprehensive evaluation of RGBT tracking methods.
Temporal Consistency Two-Stream CNN for Human Motion Prediction
In this paper, we propose a novel temporal fusion (TF) module to fuse the two-stream joints' information to predict human motion, including a temporal concatenation and a reinforcement trajectory spatial-temporal (TST) block, specifically designed to keep prediction temporal consistency.
Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking
In this paper, we propose to introduce more dynamics by devising a dynamic attention-guided multi-trajectory tracking strategy.
PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack
The studies on black-box adversarial attacks have become increasingly prevalent due to the intractable acquisition of the structural knowledge of deep neural networks (DNNs).
Image Enhancement using Fuzzy Intensity Measure and Adaptive Clipping Histogram Equalization
Image enhancement aims at processing an input image so that the visual content of the output image is more pleasing or more useful for certain applications.
Viewpoint-aware Progressive Clustering for Unsupervised Vehicle Re-identification
Comprehensive experiments against the state-of-the-art methods on two multi-viewpoint benchmark datasets VeRi and VeRi-Wild validate the promising performance of the proposed method in both with and without domain adaption scenarios while handling unsupervised vehicle Re-ID.
Duality-Gated Mutual Condition Network for RGBT Tracking
To deal with the tracking failure caused by sudden camera motion, which often occurs in RGBT tracking, we design a resampling strategy based on optical flow algorithms.
Ranked #11 on
Rgb-T Tracking
on RGBT234
RGBT Tracking via Multi-Adapter Network with Hierarchical Divergence Loss
In specific, we use the modified VGG-M as the generality adapter to extract the modality-shared target representations. To extract the modality-specific features while reducing the computational complexity, we design a modality adapter, which adds a small block to the generality adapter in each layer and each modality in a parallel manner.
Ranked #7 on
Rgb-T Tracking
on GTOT
Challenge-Aware RGBT Tracking
RGB and thermal source data suffer from both shared and specific challenges, and how to explore and exploit them plays a critical role to represent the target appearance in RGBT tracking.
Ranked #6 on
Rgb-T Tracking
on GTOT
All at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced Motion Modeling
Recent advances in high refresh rate displays as well as the increased interest in high rate of slow motion and frame up-conversion fuel the demand for efficient and cost-effective multi-frame video interpolation solutions.
Multi-interactive Encoder-decoder Network for RGBT Salient Object Detection
RGBT salient object detection (SOD) aims to segment the common prominent regions of visible and thermal infrared images.
Multi-interactive Dual-decoder for RGB-thermal Salient Object Detection
Then, we design a novel dual-decoder to conduct the interactions of multi-level features, two modalities and global contexts.
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 #33 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
M$^5$L: Multi-Modal Multi-Margin Metric Learning for RGBT Tracking
Classifying the confusing samples in the course of RGBT tracking is a quite challenging problem, which hasn't got satisfied solution.
FMT:Fusing Multi-task Convolutional Neural Network for Person Search
Person search is to detect all persons and identify the query persons from detected persons in the image without proposals and bounding boxes, which is different from person re-identification.
\emph{cm}SalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networks
Fusing complementary information of RGB and depth has been demonstrated to be effective for image salient object detection which is known as RGB-D salient object detection problem.
AttKGCN: Attribute Knowledge Graph Convolutional Network for Person Re-identification
Discriminative feature representation of person image is important for person re-identification (Re-ID) task.
GLMNet: Graph Learning-Matching Networks for Feature Matching
However, the matching graphs we feed to existing graph convolutional matching networks are generally fixed and independent of graph matching, which thus are not guaranteed to be optimal for the graph matching task.
Ranked #15 on
Graph Matching
on Willow Object Class
GmCN: Graph Mask Convolutional Network
Graph Convolutional Networks (GCNs) have shown very powerful for graph data representation and learning tasks.
Context-Aware Graph Attention Networks
In particular, CaGAT conducts context-aware learning on both node feature representation and edge (weight) representation simultaneously and cooperatively in a unified manner which can boost their respective performance in network training.
Semi-supervised Learning with Adaptive Neighborhood Graph Propagation Network
In this paper, we first re-interpret graph convolution operation in GCNs as a composition of feature propagation and (non-linear) transformation.
Learning Target-oriented Dual Attention for Robust RGB-T Tracking
RGB-Thermal object tracking attempt to locate target object using complementary visual and thermal infrared data.
Edge-guided Non-local Fully Convolutional Network for Salient Object Detection
To maintain the clear edge structure of salient objects, we propose a novel Edge-guided Non-local FCN (ENFNet) to perform edge guided feature learning for accurate salient object detection.
Learning Compact Target-Oriented Feature Representations for Visual Tracking
Many state-of-the-art trackers usually resort to the pretrained convolutional neural network (CNN) model for correlation filtering, in which deep features could usually be redundant, noisy and less discriminative for some certain instances, and the tracking performance might thus be affected.
Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation
These advantages of thermal infrared cameras make the segmentation of semantic objects in day and night.
Dense Feature Aggregation and Pruning for RGBT Tracking
In different modalities, we propose to prune the densely aggregated features of all modalities in a collaborative way.
Multi-Adapter RGBT Tracking
In a specific, the generality adapter is to extract shared object representations, the modality adapter aims at encoding modality-specific information to deploy their complementary advantages, and the instance adapter is to model the appearance properties and temporal variations of a certain object.
RGB-T Image Saliency Detection via Collaborative Graph Learning
In this paper, we propose an effective approach for RGB-T image saliency detection.
Improved Hard Example Mining by Discovering Attribute-based Hard Person Identity
In this paper, we propose Hard Person Identity Mining (HPIM) that attempts to refine the hard example mining to improve the exploration efficacy in person re-identification.
Pedestrian Attribute Recognition: A Survey
We also review some popular network architectures which have been widely applied in the deep learning community.
Multiple Graph Adversarial Learning
In this paper, we propose a novel Multiple Graph Adversarial Learning (MGAL) framework for multi-graph representation and learning.
Quality-Aware Multimodal Saliency Detection via Deep Reinforcement Learning
In this paper, we propose an efficient quality-aware deep neural network to model the weight of data from each domain using deep reinforcement learning (DRL).
Describe and Attend to Track: Learning Natural Language guided Structural Representation and Visual Attention for Object Tracking
To refine the states of the target and re-track the target when it is back to view from heavy occlusion and out of view, we elaborately design a novel subnetwork to learn the target-driven visual attentions from the guidance of both visual and natural language cues.
Graph Learning-Convolutional Networks
Recently, graph Convolutional Neural Networks (graph CNNs) have been widely used for graph data representation and semi-supervised learning tasks.
FANet: Quality-Aware Feature Aggregation Network for Robust RGB-T Tracking
This paper investigates how to perform robust visual tracking in adverse and challenging conditions using complementary visual and thermal infrared data (RGBT tracking).
Graph Diffusion-Embedding Networks
We present a novel graph diffusion-embedding networks (GDEN) for graph structured data.
Cross-Modal Ranking with Soft Consistency and Noisy Labels for Robust RGB-T Tracking
To address this problem, this paper presents a novel approach to suppress background effects for RGB-T tracking.
SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation
Based on the generated hard positive samples, we train a Siamese network for visual tracking and our experiments validate the effectiveness of the introduced algorithm.
Temporal Coherent and Graph Optimized Manifold Ranking for Visual Tracking
To address this problem, we propose a novel unified temporal coherence and graph optimized ranking model for weighted patch representation in visual tracking problem.
Graph Matching via Multiplicative Update Algorithm
As a fundamental problem in computer vision, graph matching problem can usually be formulated as a Quadratic Programming (QP) problem with doubly stochastic and discrete (integer) constraints.
Visual Tracking via Dynamic Graph Learning
First, the graph is initialized by assigning binary weights of some image patches to indicate the object and background patches according to the predicted bounding box.
Binary Constraint Preserving Graph Matching
There are three main contributions of the proposed method: (1) we propose a new graph matching relaxation model, called Binary Constraint Preserving Graph Matching (BPGM), which aims to incorporate the discrete binary mapping constraints more in graph matching relaxation.
A Unified RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and A Novel Approach
In particular, we introduce a weight for each modality to describe the reliability, and integrate them into the graph-based manifold ranking algorithm to achieve adaptive fusion of different source data.
SOLD: Sub-Optimal Low-rank Decomposition for Efficient Video Segmentation
In particular, the affinity matrix with the rank fixed can be decomposed into two sub-matrices of low rank, and then we iteratively optimize them with closed-form solutions.
Graph-Laplacian PCA: Closed-Form Solution and Robustness
Principal Component Analysis (PCA) is a widely used to learn a low-dimensional representation.
