Xiang Wang

49

Papers

441

Total Citations

Papers (49)

InstructVideo: Instructing Video Diffusion Models with Human Feedback

Towards 3D Molecule-Text Interpretation in Language Models

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation

A Recipe for Scaling up Text-to-Video Generation with Text-free Videos

Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model

Language Representations Can be What Recommenders Need: Findings and Potentials

Text-to-Image Generation for Abstract Concepts

Reinforced Lifelong Editing for Language Models

HR-Pro: Point-Supervised Temporal Action Localization via Hierarchical Reliability Propagation

SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN

Improving Object Proposals With Multi-Thresholding Straddling Expansion

Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features

Temporal Context Aggregation Network for Temporal Action Proposal Refinement

Self-Supervised Learning for Semi-Supervised Temporal Action Proposal

Invariant Grounding for Video Question Answering

Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation

Learning From Untrimmed Videos: Self-Supervised Video Representation Learning With Hierarchical Consistency

Hybrid Relation Guided Set Matching for Few-Shot Action Recognition

Revisiting Domain Generalized Stereo Matching Networks From a Feature Consistency Perspective

MoLo: Motion-Augmented Long-Short Contrastive Learning for Few-Shot Action Recognition

Enlarging Instance-Specific and Class-Specific Information for Open-Set Action Recognition

OadTR: Online Action Detection With Transformers

Space-time Prompting for Video Class-incremental Learning

Discovering Spatio-Temporal Rationales for Video Question Answering

RLIPv2: Fast Scaling of Relational Language-Image Pre-Training

Geometric Alignment and Prior Modulation for View-Guided Point Cloud Completion on Unseen Categories

Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity

PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation

DreamRelation: Relation-Centric Video Customization

FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion

Intermediate Connectors and Geometric Priors for Language-Guided Affordance Segmentation on Unseen Object Categories

Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters

On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders

LASO: Language-guided Affordance Segmentation on 3D Object

Auctionformer: A Unified Deep Learning Algorithm for Solving Equilibrium Strategies in Auction Games

Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets

Beyond Lazy Training for Over-parameterized Tensor Decomposition

Understanding Deflation Process in Over-parametrized Tensor Decomposition

Towards Multi-Grained Explainability for Graph Neural Networks

Incorporating Bias-aware Margins into Contrastive Loss for Collaborative Filtering

Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning

Empowering Collaborative Filtering with Principled Adversarial Contrastive Loss

VideoComposer: Compositional Video Synthesis with Motion Controllability

Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift

Understanding Contrastive Learning via Distributionally Robust Optimization

Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion

Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules

Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis