Search Results for author:
Found 59 papers, 15 papers with code
ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images
The task is to identify the inlier features and establish their consistent correspondences across the image set.
Partial Occlusion Handling for Visual Tracking via Robust Part Matching
The proposed part matching tracker (PMT) has a number of attractive properties.
Structural Sparse Tracking
Sparse representation has been applied to visual tracking by finding the best target candidate with minimal reconstruction error by use of target templates.
3D Part-Based Sparse Tracker With Automatic Synchronization and Registration
In this paper, we present a part-based sparse tracker in a particle filter framework where both the motion and appearance model are formulated in 3D.
In Defense of Sparse Tracking: Circulant Sparse Tracker
Sparse representation has been introduced to visual tracking by finding the best target candidate with minimal reconstruction error within the particle filter framework.
Structural Correlation Filter for Robust Visual Tracking
In this paper, we propose a novel structural correlation filter (SCF) model for robust visual tracking.
Multi-Task Correlation Particle Filter for Robust Object Tracking
In this paper, we propose a multi-task correlation particle filter (MCPF) for robust visual tracking.
Joint Pose and Expression Modeling for Facial Expression Recognition
First, the encoder-decoder structure of the generator can learn a generative and discriminative identity representation for face images.
Facial Expression Recognition
Facial Expression Recognition (FER)
+2
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.
Exploring Feature Representation and Training strategies in Temporal Action Localization
Temporal action localization has recently attracted significant interest in the Computer Vision community.
I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs
To effectively leverage the knowledge graph, we design a novel Two-Stream Graph Convolutional Network (TS-GCN) consisting of a classifier branch and an instance branch.
Ranked #5 on
Zero-Shot Action Recognition
on Olympics
RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
First, it can exploit pixel alignment and feature alignment jointly.
Cross-Modality Person Re-identification
Generative Adversarial Network
+2
Cross-modality Person re-identification with Shared-Specific Feature Transfer
In this paper, we tackle the above limitation by proposing a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and the modality-specific characteristics to boost the re-identification performance.
Cross-Modality Person Re-identification
Person Re-Identification
Graph Structured Network for Image-Text Matching
The GSMN explicitly models object, relation and attribute as a structured phrase, which not only allows to learn correspondence of object, relation and attribute separately, but also benefits to learn fine-grained correspondence of structured phrase.
Ranked #16 on
Cross-Modal Retrieval
on Flickr30k
Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image
As a result, it exploits more discriminative features for DR grading.
Task-Aware Part Mining Network for Few-Shot Learning
The task-aware part filters can adapt to any individual task and automatically mine task-related local parts even for an unseen task.
Meta-Attack: Class-Agnostic and Model-Agnostic Physical Adversarial Attack
To tackle these issues, we propose a class-agnostic and model-agnostic physical adversarial attack model (Meta-Attack), which is able to not only generate robust physical adversarial examples by simulating color and shape distortions, but also generalize to attacking novel images and novel DNN models by accessing a few digital and physical images.
Foreground Activation Maps for Weakly Supervised Object Localization
To the best of our knowledge, this is the first work that can achieve remarkable performance for both tasks by optimizing them jointly via FAM for WSOL.
Action Unit Memory Network for Weakly Supervised Temporal Action Localization
In this paper, we present an Action Unit Memory Network (AUMN) for weakly supervised temporal action localization, which can mitigate the above two challenges by learning an action unit memory bank.
Ranked #7 on
Weakly Supervised Action Localization
on THUMOS14
Weakly Supervised Action Localization
Weakly-supervised Temporal Action Localization
+1
Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer
To address these issues, we propose a novel end-to-end Part-Aware Transformer (PAT) for occluded person Re-ID through diverse part discovery via a transformer encoderdecoder architecture, including a pixel context based transformer encoder and a part prototype based transformer decoder.
Uncertainty Guided Collaborative Training for Weakly Supervised Temporal Action Detection
To alleviate this problem, we propose a novel Uncertainty Guided Collaborative Training (UGCT) strategy, which mainly includes two key designs: (1) The first design is an online pseudo label generation module, in which the RGB and FLOW streams work collaboratively to learn from each other.
Lesion-Aware Transformers for Diabetic Retinopathy Grading
First, to the best of our knowledge, this is the first work to formulate lesion discovery as a weakly supervised lesion localization problem via a transformer decoder.
Geometry Uncertainty Projection Network for Monocular 3D Object Detection
In this paper, we propose a Geometry Uncertainty Projection Network (GUP Net) to tackle the error amplification problem at both inference and training stages.
3D Object Detection From Monocular Images
Depth Estimation
+3
Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking
To address this issue, segmentation-based trackers have been proposed that employ per-pixel matching to improve the tracking performance of deformable objects effectively.
Motion-Modulated Temporal Fragment Alignment Network for Few-Shot Action Recognition
To address this issue, we propose an end-to-end Motion-modulated Temporal Fragment Alignment Network (MTFAN) by jointly exploring the task-specific motion modulation and the multi-level temporal fragment alignment for Few-Shot Action Recognition (FSAR).
A Keypoint-based Global Association Network for Lane Detection
Earlier works follow a top-down roadmap to regress predefined anchors into various shapes of lane lines, which lacks enough flexibility to fit complex shapes of lanes due to the fixed anchor shapes.
Ranked #4 on
Lane Detection
on TuSimple
(F1 score metric)
Cross-Modality Transformer for Visible-Infrared Person Re-Identification
To alleviate the above issues, we propose a novel Cross-Modality Transformer (CMT) to jointly explore a modality-level alignment module and an instance-level module for VI-ReID.
D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers
Second, the HKDL module can generate keypoint detectors in a hierarchical way, which is helpful for detecting keypoints with diverse levels of structures.
Camouflaged Instance Segmentation via Explicit De-Camouflaging
To address these challenges, we propose a novel De-camouflaging Network (DCNet) including a pixel-level camouflage decoupling module and an instance-level camouflage suppression module.
Domain Generalized Stereo Matching via Hierarchical Visual Transformation
In this way, we can prevent the model from exploiting the artifacts of synthetic stereo images as shortcut features, thereby estimating the disparity maps more effectively based on the learned robust and shortcut-invariant representation.
DualRel: Semi-Supervised Mitochondria Segmentation From a Prototype Perspective
Automatic mitochondria segmentation enjoys great popularity with the development of deep learning.
Query Refinement Transformer for 3D Instance Segmentation
Additionally, we design an affiliated transformer decoder that suppresses the interference of noise background queries and helps the foreground queries focus on instance discriminative parts to predict final segmentation results.
Ranked #2 on
3D Instance Segmentation
on ScanNet(v2)
Adaptive Template Transformer for Mitochondria Segmentation in Electron Microscopy Images
Mitochondria, as tiny structures within the cell, are of significant importance to study cell functions for biological and clinical analysis.
Rethinking the Correlation in Few-Shot Segmentation: A Buoys View
In this work, we rethink how to mitigate the false matches from the perspective of representative reference features (referred to as buoys), and propose a novel adaptive buoys correlation (ABC) network to rectify direct pairwise pixel-level correlation, including a buoys mining module and an adaptive correlation module.
Multimodal High-order Relation Transformer for Scene Boundary Detection
Scene boundary detection breaks down long videos into meaningful story-telling units and plays a crucial role in high-level video understanding.
Foreground-Background Distribution Modeling Transformer for Visual Object Tracking
To address the above limitations, we propose a novel foreground-background distribution modeling transformer for visual object tracking (F-BDMTrack), including a fore-background agent learning (FBAL) module and a distribution-aware attention (DA2) module in a unified transformer architecture.
Dynamic Generative Targeted Attacks With Pattern Injection
Concretely, the former adopts a dynamic convolution kernel and a static convolution kernel for the specific instance and the global dataset, respectively, which can inherit the advantages of both instance-specific and instance-agnostic attacks.
Alignment Before Aggregation: Trajectory Memory Retrieval Network for Video Object Segmentation
In this work, we reconcile the inherent tension of spatial and temporal information to retrieve memory frame information along the object trajectory, and propose a novel and coherent Trajectory Memory Retrieval Network (TMRN) to equip with the trajectory information, including a spatial alignment module and a temporal aggregation module.
Structured Epipolar Matcher for Local Feature Matching
Local feature matching is challenging due to textureless and repetitive patterns.
Adaptive Spot-Guided Transformer for Consistent Local Feature Matching
To deal with the above issues, we propose Adaptive Spot-Guided Transformer (ASTR) for local feature matching, which jointly models the local consistency and scale variations in a unified coarse-to-fine architecture.
SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondence
The key of our approach is to exploit an orientation estimation module with a domain adaptive discriminator to align the orientations of point cloud pairs, which significantly alleviates the mispredictions of symmetrical parts.
Ranked #2 on
3D Dense Shape Correspondence
on SHREC'19
(using extra training data)
Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization
Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training.
Ranked #2 on
Weakly Supervised Action Localization
on THUMOS’14
Multiple Instance Learning
Weakly Supervised Action Localization
+2
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation.
Free Lunch for Gait Recognition: A Novel Relation Descriptor
Gait recognition is to seek correct matches for query individuals by their unique walking patterns.
EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenes
Self-supervised monocular depth estimation holds significant importance in the fields of autonomous driving and robotics.
Ranked #1 on
Unsupervised Monocular Depth Estimation
on KITTI-C
(using extra training data)
GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection
It models the uncertainty propagation relationship of the geometry projection during training, improving the stability and efficiency of the end-to-end model learning.
Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation
In this paper, we rethink the importance of support information and propose a new query-centric FSS model Adversarial Mining Transformer (AMFormer), which achieves accurate query image segmentation with only rough support guidance or even weak support labels.
TIFace: Improving Facial Reconstruction through Tensorial Radiance Fields and Implicit Surfaces
This report describes the solution that secured the first place in the "View Synthesis Challenge for Human Heads (VSCHH)" at the ICCV 2023 workshop.
Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection
Semi-supervised 3D object detection from point cloud aims to train a detector with a small number of labeled data and a large number of unlabeled data.
Frequency Domain Modality-invariant Feature Learning for Visible-infrared Person Re-Identification
Visible-infrared person re-identification (VI-ReID) is challenging due to the significant cross-modality discrepancies between visible and infrared images.
Unifying Visual and Vision-Language Tracking via Contrastive Learning
Single object tracking aims to locate the target object in a video sequence according to the state specified by different modal references, including the initial bounding box (BBOX), natural language (NL), or both (NL+BBOX).
Joint Attention-Guided Feature Fusion Network for Saliency Detection of Surface Defects
To address these issues, we propose a joint attention-guided feature fusion network (JAFFNet) for saliency detection of surface defects based on the encoder-decoder network.
Multi-modal Attribute Prompting for Vision-Language Models
To address this issue, we propose a Multi-modal Attribute Prompting method (MAP) by jointly exploring textual attribute prompting, visual attribute prompting, and attribute-level alignment.
Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
Reinforcement Learning from Human Feedback (RLHF) is the prevailing approach to ensure Large Language Models (LLMs) align with human values.
BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation
To generate higher quality pseudo-labels and achieve more precise weakly supervised 3DIS results, we propose the Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation (BSNet), which devises a novel pseudo-labeler called Simulation-assisted Transformer.
Unsupervised Template-assisted Point Cloud Shape Correspondence Network
Unsupervised point cloud shape correspondence aims to establish point-wise correspondences between source and target point clouds.
Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation
(2) The second design is a Geometric-Aware Feature Aggregation module, which can efficiently integrate the local and global geometric information into keypoint features.
Image-to-Image Matching via Foundation Models: A New Perspective for Open-Vocabulary Semantic Segmentation
Open-vocabulary semantic segmentation (OVS) aims to segment images of arbitrary categories specified by class labels or captions.
