FATE: Pillar Encoding and Frequency-Aware Training for Event-Based Object Detection

• URL: http://arxiv.org/abs/2606.17334v1
• Date: Mon, 15 Jun 2026 22:32:09 GMT
• Title: FATE: Pillar Encoding and Frequency-Aware Training for Event-Based Object Detection
• Abstract summary: Event cameras offer inherent advantages in high-speed and high-dynamic-range scenarios.<n>Current approaches partition the accumulation window into fixed temporal sub-bins.<n>We propose FATE, a unified framework built upon a novel spatial framework.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Event cameras are bio-inspired sensors that asynchronously capture logarithmic intensity changes, offering inherent advantages in high-speed and high-dynamic-range scenarios. However, the sparse and asynchronous nature of event streams poses a fundamental challenge for modern deep learning architectures. To enable compatibility with standard models, most existing approaches partition the accumulation window into fixed temporal sub-bins. While effective for spatial processing, this internal discretization discards fine-grained temporal structure and constrains inference to the low temporal frequencies imposed by training supervision. To address this limitation, we propose FATE, a unified framework built upon a novel Pillar Encoding (PE). While operating over discrete macro-accumulation windows dictated by the target frequency, PE avoids internal temporal sub-binning. It organizes events into spatial pillars and approximates their intra-window evolution via projection onto a continuous-time orthogonal polynomial basis. This formulation yields an L2-optimal representation that retains rich temporal dynamics in a dense pseudo-image, mitigating information loss under sparse event conditions. To fully leverage this representation, we introduce Frequency-Aware Training (FAT), a soft mean-teacher curriculum that generates temporally dense pseudo-labels, effectively bridging the mismatch between low-frequency supervision and high-frequency inference. Extensive experiments demonstrate that FATE generalizes across architectural paradigms and consistently outperforms strong baselines. It enables robust object detection at high temporal resolutions up to 200 Hz, while incurring minimal overhead in parameter count and inference latency

Related papers

• WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation [69.37452950816122]
  WaveZip is a joint signal-frequency-domain framework for efficient video inference.<n> experiments on long video understanding benchmarks demonstrate that WaveZip retains 99.6% of the full performance.
  arXiv  Detail & Related papers  (2026-07-25T16:05:22Z)
• EVAS: Efficient Multimodal Temporal Forgery Localization via Audio-Visual Synergy and Steered Boundary Calibration [14.088182834458843]
  We propose EVAS, an end-to-end framework for temporal forgery localization.<n>We introduce a Boundary-Aware Refinement strategy to achieve steered boundary calibration.<n> EVAS achieves state-of-the-art average localization accuracy and average recall across three benchmark datasets.
  arXiv  Detail & Related papers  (2026-07-05T19:33:21Z)
• Following the Flow: Advection-Consistent Modeling for Event-based Small Object Detection [2.925778409623925]
  Event cameras enable high-frequency visual perception with microsecond latency, offering advantages for dynamic scenes.<n>However, event-based small object detection remains challenging due to sparse asynchronous measurements and weak object responses that are easily disrupted by noise.<n>We propose a physics-guided advection-consistent framework, termed PACT, which formulates event evolution as a motion-driven feature transport process.
  arXiv  Detail & Related papers  (2026-06-21T07:56:34Z)
• SRENet: Spectral Re-Entry Network for Point Cloud Action Recognition [49.508770157706486]
  We propose SRENet to learn both global context and fine-grained temporal dynamics of motion from a frequency perspective for action recognition.<n>SRENet achieves state-of-the-art performance, validating the effectiveness of frequency modeling in point cloud-based action understanding.
  arXiv  Detail & Related papers  (2026-06-02T05:11:47Z)
• Rethinking Event-Based Object Dtection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning [65.08890312027314]
  Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range.<n>Event Dual Temporal-Relational Aggregation Detector (Ev-DTAD) integrates representation-level temporal encoding with model-level temporal-hypergraph reasoning.<n>We show that Ev-DTAD achieves a competitive accuracy-efficiency trade-off, validating the complementarity between compact temporal representation and temporal-hypergraph feature reasoning.
  arXiv  Detail & Related papers  (2026-05-09T09:20:34Z)
• Dynamic Pondering Sparsity-aware Mixture-of-Experts Transformer for Event Stream based Visual Object Tracking [44.11576998237289]
  RGB-based trackers are vulnerable to challenging imaging conditions, such as low illumination and fast motion.<n>Event cameras offer a promising alternative by capturing pixel-wise brightness changes, providing high dynamic range and high temporal resolution.<n>We propose an event sparsity-aware tracking framework that explicitly models event-density variations across multiple temporal scales.
  arXiv  Detail & Related papers  (2026-05-07T12:25:03Z)
• Real-Time Glottis Detection Framework via Spatial-decoupled Feature Learning for Nasal Transnasal Intubation [13.846515413602722]
  We propose Mobile GlottisNet, a lightweight and efficient glottis detection framework for embedded and edge devices.<n>The model incorporates structural awareness and spatial alignment mechanisms, enabling robust glottis localization under complex anatomical and visual conditions.<n> Experimental results demonstrate that the model, with a size of only 5MB on both our PID dataset and Clinical datasets, achieves inference speeds of over 62 FPS on devices and 33 FPS on edge platforms.
  arXiv  Detail & Related papers  (2026-03-08T13:36:18Z)
• Dualformer: Time-Frequency Dual Domain Learning for Long-term Time Series Forecasting [5.4806374384787695]
  Transformer-based models suffer from an inherent low-pass filtering effect that limits their effectiveness.<n>We propose Dualformer, a principled dual-domain framework that rethinks frequency modeling from a layer-wise perspective.<n>Tests conducted on eight widely used benchmarks demonstrate Dualformer's robustness and superior performance.
  arXiv  Detail & Related papers  (2026-01-22T05:51:56Z)
• FAIM: Frequency-Aware Interactive Mamba for Time Series Classification [87.84511960413715]
  Time series classification (TSC) is crucial in numerous real-world applications, such as environmental monitoring, medical diagnosis, and posture recognition.<n>We propose FAIM, a lightweight Frequency-Aware Interactive Mamba model.<n>We show that FAIM consistently outperforms existing state-of-the-art (SOTA) methods, achieving a superior trade-off between accuracy and efficiency.
  arXiv  Detail & Related papers  (2025-11-26T08:36:33Z)
• Event Signal Filtering via Probability Flux Estimation [58.31652473933809]
  Events offer a novel paradigm for capturing scene dynamics via asynchronous sensing, but their inherent randomness often leads to degraded signal quality.<n>Event signal filtering is thus essential for enhancing fidelity by reducing this internal randomness and ensuring consistent outputs across diverse acquisition conditions.<n>This paper introduces a generative, online filtering framework called Event Density Flow Filter (EDFilter)<n>Experiments validate EDFilter's performance across tasks like event filtering, super-resolution, and direct event-based blob tracking.
  arXiv  Detail & Related papers  (2025-04-10T07:03:08Z)
• FDDet: Frequency-Decoupling for Boundary Refinement in Temporal Action Detection [4.015022008487465]
  Large-scale pre-trained video encoders tend to introduce background clutter and irrelevant semantics, leading to context confusion and boundaries.<n>We propose a frequency-aware decoupling network that improves action discriminability by filtering out noisy semantics captured by pre-trained models.<n>Our method achieves state-of-the-art performance on temporal action detection benchmarks.
  arXiv  Detail & Related papers  (2025-04-01T10:57:37Z)
• Fast Window-Based Event Denoising with Spatiotemporal Correlation Enhancement [85.66867277156089]
  We propose window-based event denoising, which simultaneously deals with a stack of events. In spatial domain, we choose maximum a posteriori (MAP) to discriminate real-world event and noise. Our algorithm can remove event noise effectively and efficiently and improve the performance of downstream tasks.
  arXiv  Detail & Related papers  (2024-02-14T15:56:42Z)

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.