Chao Li

38

Papers

18

Total Citations

Papers (38)

Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models

Spherical World-Locking for Audio-Visual Localization in Egocentric Videos

Teacher-guided Edge Discriminator for Personalized Graph Masked Autoencoder

STEPS: Sequential Probability Tensor Estimation for Text-to-Image Hard Prompt Search

Beyond Mandatory Federations: Balancing Egoism, Utilitarianism and Egalitarianism in Mixed-Motive Games

Optimistic Value Instructors for Cooperative Multi-Agent Reinforcement Learning

SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective

KernelWarehouse: Rethinking the Design of Dynamic Convolution

Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View

Enhancing Vision Transformer: Amplifying Non-Linearity in Feedforward Network Module

tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs)

Co-Saliency Detection via Looking Deep and Wide

Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval

Adversarial Defense Through Network Profiling Based Path Extraction

Non-Local Meets Global: An Integrated Paradigm for Hyperspectral Denoising

Collaborative Spatiotemporal Feature Learning for Video Action Recognition

Single Image Reflection Removal Through Cascaded Refinement

Ego4D: Around the World in 3,000 Hours of Egocentric Video

Learning Neural Duplex Radiance Fields for Real-Time View Synthesis

A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection

Leveraging Weak Semantic Relevance for Complex Video Event Classification

Image Inpainting With Learnable Bidirectional Attention Maps

Adversarial Attack on Deep Cross-Modal Hamming Retrieval

Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View

FDViT: Improve the Hierarchical Architecture of Vision Transformer

RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World

Generative Action Description Prompts for Skeleton-based Action Recognition

Topology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction

Spatiotemporal Self-Attention Modeling with Temporal Patch Shift for Action Recognition

Egocentric Activity Recognition and Localization on a 3D Map

Guaranteed Matrix Completion Under Multiple Linear Transformations

Hyperspectral Pansharpening via Diffusion Models with Iteratively Zero-Shot Guidance

Bridging Traffic State and Trajectory for Dynamic Road Network and Trajectory Representation Learning

Lightweight Yet Fine-Grained: A Graph Capsule Convolutional Network with Subspace Alignment for Shared-Account Sequential Recommendation

Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks

Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control

RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization

Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation