Jinqiao Wang

35

Papers

393

Total Citations

Papers (35)

AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models

Fluctuation-Based Adaptive Structured Pruning for Large Language Models

Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models

Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns

Chat-based Person Retrieval via Dialogue-Refined Cross-Modal Alignment

MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing

High-Speed Tracking With Multi-Kernel Correlation Filters

Semantic Alignment: Finding Semantically Consistent Ground-Truth for Facial Landmark Detection

Part-Aware Context Network for Human Parsing

Adaptive Class Suppression Loss for Long-Tail Object Detection

Improving Multiple Object Tracking With Single Object Tracking

C2AM Loss: Chasing a Better Decision Boundary for Long-Tail Object Detection

UniVIP: A Unified Framework for Self-Supervised Visual Pre-Training

ZBS: Zero-Shot Background Subtraction via Instance-Level Background Modeling and Foreground Selection

Relaxing From Vocabulary: Robust Weakly-Supervised Deep Learning for Vocabulary-Free Image Tagging

CoupleNet: Coupling Global Structure With Local Parts for Object Detection

Fast-deepKCF Without Boundary Effect

High-Performance Discriminative Tracking With Transformers

Identity-Guided Human Semantic Parsing for Person Re-Identification

Learning Feature Embeddings for Discriminant Model based Tracking

Occlusion-Aware Siamese Network for Human Pose Estimation

Large Batch Optimization for Object Detection: Training COCO in 12 Minutes

Adaptive Variance Based Label Distribution Learning For Facial Age Estimation

Blended Grammar Network for Human Parsing

Regularizing Vector Embedding in Bottom-Up Human Pose Estimation

PASS: Part-Aware Self-Supervised Pre-training for Person Re-identification

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection

PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability

Synthetic Data is an Elegant GIFT for Continual Vision-Language Models

Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring

Self-Supervised Representation Learning from Arbitrary Scenarios

Learning Adaptive Receptive Fields for Deep Image Parsing Network

MST: Masked Self-Supervised Transformer for Visual Representation

Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks

TaiSu: A 166M Large-scale High-Quality Dataset for Chinese Vision-Language Pre-training