Qiang Wang

33

Papers

142

Total Citations

Papers (33)

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

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

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

ParZC: Parametric Zero-Cost Proxies for Efficient NAS

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

Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation

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

DOCTR: Disentangled Object-Centric Transformer for Point Scene Understanding

Residual Denoising Diffusion Models

Discovering Syntactic Interaction Clues for Human-Object Interaction Detection

Traceable Federated Continual Learning

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

Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking

Fast Online Object Tracking and Segmentation: A Unifying Approach

SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks

Rethinking Performance Estimation in Neural Architecture Search

Multiple Object Tracking With Correlation Learning

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

RCL: Recurrent Continuous Localization for Temporal Action Detection

Learning a Structured Latent Space for Unsupervised Point Cloud Completion

Robust Object Tracking Based on Temporal and Spatial Deep Networks

Anchor Diffusion for Unsupervised Video Object Segmentation

UASNet: Uncertainty Adaptive Sampling Network for Deep Stereo Matching

TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses

FlowFormer: A Transformer Architecture for Optical Flow

EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching

All-Day Multi-Camera Multi-Target Tracking

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

Dynamic Integration of Task-Specific Adapters for Class Incremental Learning

Learning Endogenous Attention for Incremental Object Detection

OAMaskFlow: Occlusion-Aware Motion Mask for Scene Flow

Flexible Sharpness-Aware Personalized Federated Learning

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