Yu Kong

16

Papers

61

Total Citations

Papers (16)

Prompting Language-Informed Distribution for Compositional Zero-Shot Learning

Facial Affective Behavior Analysis with Instruction Tuning

H-MoRe: Learning Human-centric Motion Representation for Action Analysis

Deep Sequential Context Networks for Action Prediction

Residual Dense Network for Image Super-Resolution

GateHUB: Gated History Unit With Background Suppression for Online Action Detection

OpenTAL: Towards Open Set Temporal Action Localization

Learning of Global Objective for Network Flow in Multi-Object Tracking

Catch Missing Details: Image Reconstruction With Frequency Augmented Variational Autoencoder

DRIVE: Deep Reinforced Accident Anticipation With Visual Explanation

Explainable Video Entailment With Grounded Visual Evidence

Evidential Deep Learning for Open Set Action Recognition

Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting

Group Activity Prediction with Sequential Relational Anticipation Model

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads

Bilinear Heterogeneous Information Machine for RGB-D Action Recognition