[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition

Timeception for Complex Action Recognition, CVPR 2019 (Oral Presentation)

【AAAI'2021】MVFNet: Multi-View Fusion Network for Efficient Video Recognition

Efficient 3D Backbone Network for Temporal Modeling

【ICCV'2023】What Can Simple Arithmetic Operations Do for Temporal Modeling?

ICCV 19 Grouped Spatial-Temporal Aggretation for Efficient Action Recognition

【ACMMM'2021】DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning

Code for "Long Horizon Forecasting With Temporal Point Processes", WSDM 2021

the PyTorch implementation of chunk-level attention-based temporal aggregation framework for sequence-to-one recognition tasks

The PyTorch implementation of the additional temporal modeling on the DeepEmoCluster framework

a research project to explore how AI can be trained and coded to see the near- and far-future by exploring synthetic prescience through the FFFBF algorithm

TETUP: Code for "Towards Explainable Temporal User Profiling with LLMs" (ExUM 2025). This project proposes a content-based recommendation framework that generates short-term and long-term user profiles using LLMs, enabling interpretable and personalized recommendations with temporal awareness.

Deep learning framework for multi-horizon financial time series forecasting using RNN, GRU, and LSTM. Incorporates hyperparameter optimization, visualization, and multivariate sequence prediction across Open, High, Low, Close, and Volume indicators.

Ontology Design Pattern for persistent identifiers with time-varying referents. Includes complete implementations for financial derivatives (futures rolling) and aviation operations (flight tracking) with RDF/OWL ontologies, SPARQL queries, and test suites.

RecurVid is a fast, recursive image-to-video generation model that creates high-quality short videos through next-frame prediction and progressive synthesis.

A modern implementation of ECCV 2018 paper: "Hierarchical Relational Networks for Group Activity Recognition and Retrieval".