Kaiqi Huang

papers

212

total citations

papers (12)

Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition

ICCV 2021arXiv

citations

PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution

CVPR 2024arXiv

citations

PanopticDepth: A Unified Framework for Depth-Aware Panoptic Segmentation

CVPR 2022arXiv

citations

InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation

NEURIPS 2022arXiv

citations

Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness

ICML 2024arXiv

citations

ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking

ICCV 2025arXiv

citations

A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship

NEURIPS 2023

citations

Kaiqi Huang

papers (12)

Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition

PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution

PanopticDepth: A Unified Framework for Depth-Aware Panoptic Segmentation

InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation

Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness

ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking

TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient

LLM Data Selection and Utilization via Dynamic Bi-level Optimization

DDAE: Towards Deep Dynamic Vision BERT Pretraining

Composing Good Shots by Exploiting Mutual Relations

Learning to Learn Cropping Models for Different Aspect Ratio Requirements

A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship

papers (12)

Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition

PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution

PanopticDepth: A Unified Framework for Depth-Aware Panoptic Segmentation

InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation

Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness

ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking

TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient

LLM Data Selection and Utilization via Dynamic Bi-level Optimization

DDAE: Towards Deep Dynamic Vision BERT Pretraining

Composing Good Shots by Exploiting Mutual Relations

Learning to Learn Cropping Models for Different Aspect Ratio Requirements

A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship