Xin Tan

papers

658

total citations

papers (22)

Rethinking Efficient Lane Detection via Curve Modeling

CVPR 2022arXiv

192

citations

PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection

CVPR 2024arXiv

114

citations

COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction

CVPR 2024arXiv

citations

Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data

CVPR 2023arXiv

citations

Omni-Supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

CVPR 2021arXiv

citations

Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer

CVPR 2024arXiv

citations

DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input

AAAI 2025arXiv

citations

FastLGS: Speeding Up Language Embedded Gaussians with Feature Grid Mapping

AAAI 2025arXiv

citations

Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection

AAAI 2024

citations

Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation

AAAI 2024arXiv

citations

Large Continual Instruction Assistant

ICML 2025arXiv

citations

A Two-Stage Information Extraction Network for Incomplete Multi-View Multi-Label Classification

AAAI 2024

citations

Optimization over Disentangled Encoding: Unsupervised Cross-Domain Point Cloud Completion via Occlusion Factor Manipulation

ECCV 2022

citations

Domain-Hallucinated Updating for Multi-Domain Face Anti-spoofing

AAAI 2024

citations

Learning To Detect Mirrors From Videos via Dual Correspondences

CVPR 2023

citations

Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling

CVPR 2023

citations

Instance and Category Supervision are Alternate Learners for Continual Learning

ICCV 2023

citations

Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference

CVPR 2023

citations

Xin Tan

papers (22)

Rethinking Efficient Lane Detection via Curve Modeling

PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection

COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction

Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data

Omni-Supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer

DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input

FastLGS: Speeding Up Language Embedded Gaussians with Feature Grid Mapping

Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection

One-for-More: Continual Diffusion Model for Anomaly Detection

Continuous Piecewise-Affine Based Motion Model for Image Animation

Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception

MOS: Modeling Object-Scene Associations in Generalized Category Discovery

Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation

Large Continual Instruction Assistant

A Two-Stage Information Extraction Network for Incomplete Multi-View Multi-Label Classification

Optimization over Disentangled Encoding: Unsupervised Cross-Domain Point Cloud Completion via Occlusion Factor Manipulation

Domain-Hallucinated Updating for Multi-Domain Face Anti-spoofing

Learning To Detect Mirrors From Videos via Dual Correspondences

Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling

Instance and Category Supervision are Alternate Learners for Continual Learning

Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference

papers (22)

Rethinking Efficient Lane Detection via Curve Modeling

PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection

COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction

Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data

Omni-Supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer

DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input

FastLGS: Speeding Up Language Embedded Gaussians with Feature Grid Mapping

Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection

One-for-More: Continual Diffusion Model for Anomaly Detection

Continuous Piecewise-Affine Based Motion Model for Image Animation

Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception

MOS: Modeling Object-Scene Associations in Generalized Category Discovery

Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation

Large Continual Instruction Assistant

A Two-Stage Information Extraction Network for Incomplete Multi-View Multi-Label Classification

Optimization over Disentangled Encoding: Unsupervised Cross-Domain Point Cloud Completion via Occlusion Factor Manipulation

Domain-Hallucinated Updating for Multi-Domain Face Anti-spoofing

Learning To Detect Mirrors From Videos via Dual Correspondences

Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling

Instance and Category Supervision are Alternate Learners for Continual Learning

Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference