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

• URL: http://arxiv.org/abs/2604.16240v1
• Date: Fri, 17 Apr 2026 17:00:03 GMT
• Title: CollideNet: Hierarchical Multi-scale Video Representation Learning with Disentanglement for Time-To-Collision Forecasting
• Abstract summary: Time-to-Collision (TTC) forecasting is a critical task in collision prevention.<n>We introduce a novel hierarchical transformer-based architecture called CollideNet.<n>In the spatial stream, CollideNet aggregates information for each video frame simultaneously at multiple resolutions.
• Score: 32.71774009477647
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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/.

Related papers

• StableDPT: Temporal Stable Monocular Video Depth Estimation [14.453483279783908]
  We propose a novel approach that adapts any state-of-the-art image-based (depth) estimation model for video processing.<n>Our architecture builds upon an off-the-shelf Vision Transformer (ViT) encoder and enhances the Dense Prediction Transformer (DPT) head.<n> Evaluations on multiple benchmark datasets demonstrate improved temporal consistency, competitive state-of-the-art performance and on top 2x faster processing in real-world scenarios.
  arXiv  Detail & Related papers  (2026-01-06T08:02:14Z)
• Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events [71.2439653098351]
  Continuous space-time video super-STVSR has garnered increasing interest for its capability to reconstruct high-resolution and high-frame-rate videos at arbitrary temporal scales.<n>We present EvEnhancer, a novel approach that marries unique properties of high temporal and high dynamic range encapsulated in event streams.<n>Our method achieves state-of-the-art performance on both synthetic and real-world datasets, while maintaining generalizability at OOD scales.
  arXiv  Detail & Related papers  (2025-10-04T15:23:07Z)
• Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression [59.632286735304156]
  We propose a spatial decomposition and temporal fusion based inter prediction for learned video compression. With the SDD-based motion model and long short-term temporal fusion, our proposed learned video can obtain more accurate inter prediction contexts.
  arXiv  Detail & Related papers  (2024-01-29T03:30:21Z)
• A Unified Framework for Event-based Frame Interpolation with Ad-hoc Deblurring in the Wild [72.0226493284814]
  We propose a unified framework for event-based frame that performs deblurring ad-hoc.<n>Our network consistently outperforms previous state-of-the-art methods on frame, single image deblurring, and the joint task of both.
  arXiv  Detail & Related papers  (2023-01-12T18:19:00Z)
• Temporally Consistent Transformers for Video Generation [80.45230642225913]
  To generate accurate videos, algorithms have to understand the spatial and temporal dependencies in the world. No established benchmarks on complex data exist for rigorously evaluating video generation with long temporal dependencies. We introduce the Temporally Consistent Transformer (TECO), a generative model that substantially improves long-term consistency while also reducing sampling time.
  arXiv  Detail & Related papers  (2022-10-05T17:15:10Z)
• Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training [31.115226660100294]
  We propose a framework to feed the unlabeled video frames together with the labeled images into an image shadow detection network training. We then derive the spatial and temporal consistency constraints accordingly for enhancing generalization in the pixel-wise classification. In addition, we design a Scale-Aware Network for multi-scale shadow knowledge learning in images.
  arXiv  Detail & Related papers  (2022-06-17T14:29:51Z)
• Adaptive graph convolutional networks for weakly supervised anomaly detection in videos [42.3118758940767]
  We propose a weakly supervised adaptive graph convolutional network (WAGCN) to model the contextual relationships among video segments. We fully consider the influence of other video segments on the current segment when generating the anomaly probability score for each segment.
  arXiv  Detail & Related papers  (2022-02-14T06:31:34Z)
• Temporal-attentive Covariance Pooling Networks for Video Recognition [52.853765492522655]
  existing video architectures usually generate global representation by using a simple global average pooling (GAP) method. This paper proposes a attentive Covariance Pooling( TCP- TCP), inserted at the end of deep architectures, to produce powerful video representations. Our TCP is model-agnostic and can be flexibly integrated into any video architectures, resulting in TCPNet for effective video recognition.
  arXiv  Detail & Related papers  (2021-10-27T12:31:29Z)
• Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos [78.45050529204701]
  We propose a novel framework to pursue discriminative and robust representation by modeling cross-scale spatial-temporal correlation. CTL utilizes a CNN backbone and a key-points estimator to extract semantic local features from human body. It explores a context-reinforced topology to construct multi-scale graphs by considering both global contextual information and physical connections of human body.
  arXiv  Detail & Related papers  (2021-04-15T14:32:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.