Qiang Wang

papers

1,098

total citations

papers (28)

VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding

AAAI 2024arXiv

citations

Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models

ICML 2024arXiv

citations

RCL: Recurrent Continuous Localization for Temporal Action Detection

CVPR 2022arXiv

citations

Learning a Structured Latent Space for Unsupervised Point Cloud Completion

CVPR 2022arXiv

citations

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

ICLR 2025arXiv

citations

TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses

ICCV 2023arXiv

citations

Rethinking Performance Estimation in Neural Architecture Search

CVPR 2020arXiv

citations

CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning

AAAI 2024arXiv

citations

ParZC: Parametric Zero-Cost Proxies for Efficient NAS

AAAI 2025arXiv

citations

EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching

ECCV 2022arXiv

citations

DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype

AAAI 2025arXiv

citations

Dynamic Integration of Task-Specific Adapters for Class Incremental Learning

CVPR 2025arXiv

citations

Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need

CVPR 2025arXiv

citations

Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation

ICCV 2025arXiv

citations

Learning Endogenous Attention for Incremental Object Detection

CVPR 2025

citations

BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking

NEURIPS 2023

citations

All-Day Multi-Camera Multi-Target Tracking

CVPR 2025

citations

Flexible Sharpness-Aware Personalized Federated Learning

AAAI 2025

citations

UASNet: Uncertainty Adaptive Sampling Network for Deep Stereo Matching

ICCV 2021

citations

DOCTR: Disentangled Object-Centric Transformer for Point Scene Understanding

AAAI 2024arXiv

citations

Discovering Syntactic Interaction Clues for Human-Object Interaction Detection

CVPR 2024

citations

Traceable Federated Continual Learning

CVPR 2024

citations

OAMaskFlow: Occlusion-Aware Motion Mask for Scene Flow

AAAI 2025

citations

EDNet: Efficient Disparity Estimation With Cost Volume Combination and Attention-Based Spatial Residual

CVPR 2021arXiv

citations

Qiang Wang

papers (28)

FlowFormer: A Transformer Architecture for Optical Flow

Multiple Object Tracking With Correlation Learning

Residual Denoising Diffusion Models

MmAP: Multi-Modal Alignment Prompt for Cross-Domain Multi-Task Learning

VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding

Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models

RCL: Recurrent Continuous Localization for Temporal Action Detection

Learning a Structured Latent Space for Unsupervised Point Cloud Completion

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses

Rethinking Performance Estimation in Neural Architecture Search

CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning

ParZC: Parametric Zero-Cost Proxies for Efficient NAS

EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching

DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype

Dynamic Integration of Task-Specific Adapters for Class Incremental Learning

Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need

Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation

Learning Endogenous Attention for Incremental Object Detection

BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking

All-Day Multi-Camera Multi-Target Tracking

Flexible Sharpness-Aware Personalized Federated Learning

UASNet: Uncertainty Adaptive Sampling Network for Deep Stereo Matching

DOCTR: Disentangled Object-Centric Transformer for Point Scene Understanding

Discovering Syntactic Interaction Clues for Human-Object Interaction Detection

Traceable Federated Continual Learning

OAMaskFlow: Occlusion-Aware Motion Mask for Scene Flow

EDNet: Efficient Disparity Estimation With Cost Volume Combination and Attention-Based Spatial Residual

papers (28)

FlowFormer: A Transformer Architecture for Optical Flow

Multiple Object Tracking With Correlation Learning

Residual Denoising Diffusion Models

MmAP: Multi-Modal Alignment Prompt for Cross-Domain Multi-Task Learning

VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding

Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models

RCL: Recurrent Continuous Localization for Temporal Action Detection

Learning a Structured Latent Space for Unsupervised Point Cloud Completion

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses

Rethinking Performance Estimation in Neural Architecture Search

CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning

ParZC: Parametric Zero-Cost Proxies for Efficient NAS

EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching

DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype

Dynamic Integration of Task-Specific Adapters for Class Incremental Learning

Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need

Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation

Learning Endogenous Attention for Incremental Object Detection

BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking

All-Day Multi-Camera Multi-Target Tracking

Flexible Sharpness-Aware Personalized Federated Learning

UASNet: Uncertainty Adaptive Sampling Network for Deep Stereo Matching

DOCTR: Disentangled Object-Centric Transformer for Point Scene Understanding

Discovering Syntactic Interaction Clues for Human-Object Interaction Detection

Traceable Federated Continual Learning

OAMaskFlow: Occlusion-Aware Motion Mask for Scene Flow

EDNet: Efficient Disparity Estimation With Cost Volume Combination and Attention-Based Spatial Residual