Shiwei Zhang

32

Papers

247

Total Citations

Papers (32)

InstructVideo: Instructing Video Diffusion Models with Human Feedback

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

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

Enhancing Zero-shot Object Counting via Text-guided Local Ranking and Number-evoked Global Attention

CountSE: Soft Exemplar Open-set Object Counting

FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing

Check Locate Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation

DreamVideo: Composing Your Dream Videos with Customized Subject and Motion

TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection

Self-Supervised Learning for Semi-Supervised Temporal Action Proposal

Self-Supervised Motion Learning From Static Images

TCTrack: Temporal Contexts for Aerial Tracking

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

Hybrid Relation Guided Set Matching for Few-Shot Action Recognition

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

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

LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook

Support-Set Based Cross-Supervision for Video Grounding

OadTR: Online Action Detection With Transformers

Space-time Prompting for Video Class-incremental Learning

Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning

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

Open-World Semantic Segmentation for LIDAR Point Clouds

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

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

SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models

DreamRelation: Relation-Centric Video Customization

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

VideoComposer: Compositional Video Synthesis with Motion Controllability

FaceComposer: A Unified Model for Versatile Facial Content Creation