YangLiu

SAKDN. [IEEE T-IP 2021] Semantics-aware Adaptive Knowledge Distillation for Cross-modal Action Recognition

TCGL. [IEEE T-IP 2022] TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning

CMCIR. [IEEE T-PAMI 2023] Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering

JSRDA. [IEEE T-CSVT 2019] Hierarchically Learned View-Invariant Representations for Cross-View Action Recognition

CDFAG. Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition (Complexity 2018)

VisionGRU. VisionGRU: A Linear-Complexity RNN Model for Efficient Image Analysis

DIVAFN. [IEEE T-IP 2020] Deep Image-to-Video Adaptation and Fusion Networks for Action Recognition

TSTDDs. [IEEE SPL 2018] Global Temporal Representation based CNNs for Infrared Action Recognition

MIR. [MIR 2022] Causal Reasoning Meets Visual Representation Learning: A Prospective Study

yangliu9208.github.io. HTML

VCD. VCD: Visual Causality Discovery for Cross-Modal Question Reasoning

VCSR. [ACM MM 2023] Visual Causal Scene Refinement for Video Question Answering

HORLN. Hybrid-Order Representation Learning for Electricity Theft Detection (IEEE T-II 2022)