Shengjin Wang

papers

2,352

total citations

papers (27)

CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions

ECCV 2020arXiv

103

citations

Do Different Tracking Tasks Require Different Appearance Models?

NEURIPS 2021arXiv

100

citations

Multi-Target Domain Adaptation With Collaborative Consistency Learning

CVPR 2021arXiv

citations

Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection

CVPR 2021arXiv

citations

Towards Discriminative Representation Learning for Unsupervised Person Re-Identification

ICCV 2021arXiv

citations

Self-Supervised Learning via Maximum Entropy Coding

NEURIPS 2022arXiv

citations

Uni3DETR: Unified 3D Detection Transformer

NEURIPS 2023arXiv

citations

GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs

ECCV 2022arXiv

citations

Noisy Boundaries: Lemon or Lemonade for Semi-Supervised Instance Segmentation?

CVPR 2022arXiv

citations

Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification

NEURIPS 2021arXiv

citations

Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-Identification

ICCV 2023arXiv

citations

Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval

ECCV 2022arXiv

citations

R(Det)2: Randomized Decision Routing for Object Detection

CVPR 2022arXiv

citations

LIBA: Language Instructed Multi-granularity Bridge Assistant for 3D Visual Grounding

AAAI 2025

citations

Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic

ICLR 2024arXiv

citations

Risk-Aware Self-Consistent Imitation Learning for Trajectory Planning in Autonomous Driving

ECCV 2024

citations

Partial Off-Policy Learning: Balance Accuracy and Diversity for Human-Oriented Image Captioning

ICCV 2021

citations

A2-FPN: Attention Aggregation Based Feature Pyramid Network for Instance Segmentation

CVPR 2021

citations

Exploring Pose-Aware Human-Object Interaction via Hybrid Learning

CVPR 2024

citations

G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding

CVPR 2024

citations

Disentangled Representation for Age-Invariant Face Recognition: A Mutual Information Minimization Perspective

ICCV 2021

citations

OSKDet: Orientation-Sensitive Keypoint Localization for Rotated Object Detection

CVPR 2022

citations

HSI-GPT: A General-Purpose Large Scene-Motion-Language Model for Human Scene Interaction

CVPR 2025

citations

Shengjin Wang

papers (27)

Towards Real-Time Multi-Object Tracking

Video Super-Resolution with Recurrent Structure-Detail Network

Video Super-Resolution With Temporal Group Attention

Detecting Everything in the Open World: Towards Universal Object Detection

CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions

Do Different Tracking Tasks Require Different Appearance Models?

Multi-Target Domain Adaptation With Collaborative Consistency Learning

Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection

Towards Discriminative Representation Learning for Unsupervised Person Re-Identification

Self-Supervised Learning via Maximum Entropy Coding

Uni3DETR: Unified 3D Detection Transformer

GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs

Noisy Boundaries: Lemon or Lemonade for Semi-Supervised Instance Segmentation?

Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification

Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-Identification

Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval

R(Det)2: Randomized Decision Routing for Object Detection

LIBA: Language Instructed Multi-granularity Bridge Assistant for 3D Visual Grounding

Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic

Risk-Aware Self-Consistent Imitation Learning for Trajectory Planning in Autonomous Driving

Partial Off-Policy Learning: Balance Accuracy and Diversity for Human-Oriented Image Captioning

A2-FPN: Attention Aggregation Based Feature Pyramid Network for Instance Segmentation

Exploring Pose-Aware Human-Object Interaction via Hybrid Learning

G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding

Disentangled Representation for Age-Invariant Face Recognition: A Mutual Information Minimization Perspective

OSKDet: Orientation-Sensitive Keypoint Localization for Rotated Object Detection

HSI-GPT: A General-Purpose Large Scene-Motion-Language Model for Human Scene Interaction

papers (27)

Towards Real-Time Multi-Object Tracking

Video Super-Resolution with Recurrent Structure-Detail Network

Video Super-Resolution With Temporal Group Attention

Detecting Everything in the Open World: Towards Universal Object Detection

CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions

Do Different Tracking Tasks Require Different Appearance Models?

Multi-Target Domain Adaptation With Collaborative Consistency Learning

Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection

Towards Discriminative Representation Learning for Unsupervised Person Re-Identification

Self-Supervised Learning via Maximum Entropy Coding

Uni3DETR: Unified 3D Detection Transformer

GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs

Noisy Boundaries: Lemon or Lemonade for Semi-Supervised Instance Segmentation?

Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification

Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-Identification

Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval

R(Det)2: Randomized Decision Routing for Object Detection

LIBA: Language Instructed Multi-granularity Bridge Assistant for 3D Visual Grounding

Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic

Risk-Aware Self-Consistent Imitation Learning for Trajectory Planning in Autonomous Driving

Partial Off-Policy Learning: Balance Accuracy and Diversity for Human-Oriented Image Captioning

A2-FPN: Attention Aggregation Based Feature Pyramid Network for Instance Segmentation

Exploring Pose-Aware Human-Object Interaction via Hybrid Learning

G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding

Disentangled Representation for Age-Invariant Face Recognition: A Mutual Information Minimization Perspective

OSKDet: Orientation-Sensitive Keypoint Localization for Rotated Object Detection

HSI-GPT: A General-Purpose Large Scene-Motion-Language Model for Human Scene Interaction