This work considers combine multi-tricks with highway network to achieve traffic flow prediction accurately.

[BMVC 2023 ] Official code for "STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition"

Topic-Aware Abstractive Summarization

Deep Reinforced Model for Abstractive Summarization

AQuaMoHo is a ML-driven framework to annotate air quality at any location from a low-cost Thermo-Hygrometer

🎯 Production-ready implementation of video prediction models using PyTorch. Features Enhanced ConvLSTM with temporal attention, PredRNN with spatiotemporal memory, and Transformer-based architecture.