Jun Li

45

Papers

186

Total Citations

Papers (45)

Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval

Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking

Guided Real Image Dehazing Using YCbCr Color Space

Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model

Compound Text-Guided Prompt Tuning via Image-Adaptive Cues

Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion

TraF-Align: Trajectory-aware Feature Alignment for Asynchronous Multi-agent Perception

Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video

UniAP: Unifying Inter- and Intra-Layer Automatic Parallelism by Mixed Integer Quadratic Programming

Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning

AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization

Efficient Self-Supervised Video Hashing with Selective State Spaces

Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation

Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation

Action Shuffle Alternating Learning for Unsupervised Action Segmentation

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection

Anchor-Constrained Viterbi for Set-Supervised Action Segmentation

Which Images To Label for Few-Shot Medical Landmark Detection?

Nested Collaborative Learning for Long-Tailed Visual Recognition

Industrial Style Transfer With Large-Scale Geometric Warping and Content Preservation

BEVHeight: A Robust Framework for Vision-Based Roadside 3D Object Detection

A Two-Streamed Network for Estimating Fine-Scaled Depth Maps From Single RGB Images

Cross-X Learning for Fine-Grained Visual Categorization

Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration

Regularizing Nighttime Weirdness: Efficient Self-Supervised Monocular Depth Estimation in the Dark

Creative Birds: Self-Supervised Single-View 3D Style Transfer

Multi-modal Masked Pre-training for Monocular Panoramic Depth Completion

RigNet: Repetitive Image Guided Network for Depth Completion

Weakly Supervised Energy-Based Learning for Action Segmentation

Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport

AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video Hashing

Advancing Multiple Instance Learning with Continual Learning for Whole Slide Imaging

DuCos: Duality Constrained Depth Super-Resolution via Foundation Model

RAGD: Regional-Aware Diffusion Model for Text-to-Image Generation

Learning Generalized Residual Exchange-Correlation-Uncertain Functional for Density Functional Theory

Harmonious Music-driven Group Choreography with Trajectory-Controllable Diffusion

Tri-Perspective View Decomposition for Geometry-Aware Depth Completion

Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance

ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering

Im2Struct: Recovering 3D Shape Structure From a Single RGB Image

Set-Constrained Viterbi for Set-Supervised Action Segmentation

Curvilinear Distance Metric Learning

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

Learning Contrastive Embedding in Low-Dimensional Space

Dual Entangled Polynomial Code: Three-Dimensional Coding for Distributed Matrix Multiplication