Liang Wang

65

Papers

1,110

Total Citations

Papers (65)

Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval

Generative Representational Instruction Tuning

Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition

Learning to Rank in Generative Retrieval

Text-Guided Molecule Generation with Diffusion Language Model

Rethinking Graph Masked Autoencoders through Alignment and Uniformity

Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables

PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts

Free Lunch for Gait Recognition: A Novel Relation Descriptor

MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra

Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain

Learning Fine-Grained Alignment for Aerial Vision-Dialog Navigation

Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows

S²DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion

EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow

Percentile Risk-Constrained Budget Pacing for Guaranteed Display Advertising in Online Optimization

M3: Multimodal Memory Modelling for Video Captioning

Language-Driven Temporal Activity Localization: A Semantic Matching Reinforcement Learning Model

An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition

Box-Driven Class-Wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation

Cross-Modal Cross-Domain Moment Alignment Network for Person Search

Temporal Modulation Network for Controllable Space-Time Video Super-Resolution

Rethinking the Heatmap Regression for Bottom-Up Human Pose Estimation

Locate Then Segment: A Strong Pipeline for Referring Image Segmentation

Global2Local: Efficient Structure Search for Video Action Segmentation

DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models

Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation

Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels

A Deep Visual Correspondence Embedding Model for Stereo Matching Costs

Look and Think Twice: Capturing Top-Down Visual Attention With Feedback Convolutional Neural Networks

Conditional High-Order Boltzmann Machine: A Supervised Learning Model for Relation Learning

Referring Expression Generation and Comprehension via Attributes

ACMM: Aligned Cross-Modal Memory for Few-Shot Image and Sentence Matching

Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization

Towards Part-aware Monocular 3D Human Pose Estimation: An Architecture Search Approach

Prediction and Recovery for Adaptive Low-Resolution Person Re-Identification

Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations

Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution

Incremental Cross-View Mutual Distillation for Self-Supervised Medical CT Synthesis

Bridging Gait Recognition and Large Language Models Sequence Modeling

Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning

Domain-Level Disentanglement Framework Based on Information Enhancement for Cross-Domain Cold-Start Recommendation

Robust Graph Based Social Recommendation Through Contrastive Multi-View Learning

Attribute-Guided Pedestrian Retrieval: Bridging Person Re-ID with Internal Attribute Variability

Investigating Compositional Challenges in Vision-Language Models for Visual Grounding

Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process

Hierarchical Recurrent Neural Network for Skeleton Based Action Recognition

Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks

Instance-Aware Image and Sentence Matching With Selective Multimodal LSTM

See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-Identification

A Dataset for Benchmarking Image-Based Localization

Multistage Adversarial Losses for Pose-Based Human Image Synthesis

Mask-Guided Contrastive Attention Model for Person Re-Identification

Learning Semantic Concepts and Order for Image and Sentence Matching

Towards Playing Full MOBA Games with Deep Reinforcement Learning

Unfolding the Alternating Optimization for Blind Super Resolution

Landmark-RxR: Solving Vision-and-Language Navigation with Fine-Grained Alignment Supervision

Learning Diverse Policies in MOBA Games via Macro-Goals

MACK: Multimodal Aligned Conceptual Knowledge for Unpaired Image-text Matching

Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning

Uncovering Neural Scaling Laws in Molecular Representation Learning

Frequency-Enhanced Data Augmentation for Vision-and-Language Navigation

Combating Bilateral Edge Noise for Robust Link Prediction

GSLB: The Graph Structure Learning Benchmark

OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling