# CollideNet: Hierarchical Multi-scale Video Representation Learning with Disentanglement for Time-To-Collision Forecasting

arXiv: https://arxiv.org/abs/2604.16240 · HTML: https://mlsanity.com/paper/2604.16240/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 70 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting](https://mlsanity.com/paper/2205.14415/) (2022)
- [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https://mlsanity.com/paper/2405.14616/) (2024)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition](https://mlsanity.com/paper/1708.07632/) (2017)
- [Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning](https://mlsanity.com/paper/2008.00334/) (2020)
- [DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving](https://mlsanity.com/paper/2304.01168/) (2023)
- [Learning Spatio-Temporal Representation with Local and Global Diffusion](https://mlsanity.com/paper/1906.05571/) (2019)
- [Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting](https://mlsanity.com/paper/2206.04038/) (2022)
- [Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB](https://mlsanity.com/paper/1804.02675/) (2018)
- [Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction](https://mlsanity.com/paper/2011.02763/) (2020)
- [Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization](https://mlsanity.com/paper/1705.06560/) (2017)
- [Preformer: Predictive Transformer with Multi-Scale Segment-wise Correlations for Long-Term Time Series Forecasting](https://mlsanity.com/paper/2202.11356/) (2022)
- [Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition](https://mlsanity.com/paper/2307.06947/) (2023)
- [Dynamic Mode Decomposition for Real-Time Background/Foreground Separation in Video](https://mlsanity.com/paper/1404.7592/) (2014)
- [HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling with Self-Distillation for Long-Term Forecasting](https://mlsanity.com/paper/2401.05012/) (2024)
- [Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers](https://mlsanity.com/paper/2303.11251/) (2023)
- [Factorization Vision Transformer: Modeling Long Range Dependency with Local Window Cost](https://mlsanity.com/paper/2312.08614/) (2023)

## Abstract (arXiv)

Time-to-Collision (TTC) forecasting is a critical task in collision prevention, requiring precise temporal prediction and comprehending both local and global patterns encapsulated in a video, both spatially and temporally. To address the multi-scale nature of video, we introduce a novel spatiotemporal hierarchical transformer-based architecture called CollideNet, specifically catered for effective TTC forecasting. In the spatial stream, CollideNet aggregates information for each video frame simultaneously at multiple resolutions. In the temporal stream, along with multi-scale feature encoding, CollideNet also disentangles the non-stationarity, trend, and seasonality components. Our method achieves state-of-the-art performance in comparison to prior works on three commonly used public datasets, setting a new state-of-the-art by a considerable margin. We conduct cross-dataset evaluations to analyze the generalization capabilities of our method, and visualize the effects of disentanglement of the trend and seasonality components of the video data. We release our code at https://github.com/DeSinister/CollideNet/.