Multiple description coding, High efficiency video coding (HEVC), Human visual system, Error resilience
Visual object tracking, Transformer, Spatio-temporal modeling, graph attention network, Trajectory-aware network, Video representation learning
Neural network, Inter frame coding, Versatile Video Coding (VVC), Prediction mode
Point cloud compression, Graph neural network, Spatial-gate feed-forward network
Video compression, Deformable convolution, Motion correction, Self-attention, Conditional encoding
Light field; super-resolution; state space model;mamba