SpikeTAD: Spiking Neural Networks for End-to-End Temporal Action Detection

• URL: http://arxiv.org/abs/2606.12033v1
• Date: Wed, 10 Jun 2026 12:57:05 GMT
• Title: SpikeTAD: Spiking Neural Networks for End-to-End Temporal Action Detection
• Abstract summary: Spiking Neural Networks (SNNs) have shown bioplausibility and low power advantages over Artificial Neural Networks (ANNs)<n>We propose the first SNN-based end-to-end temporal action detection architecture coined as SpikeTAD.<n>SpikeTAD achieves an average mAP of 67.2% in THUMOS14 and 37.42% in ActivityNet-1.3, demonstrating the feasibility of a low-power TAD model.
• Score: 24.33424613315401
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video understanding is a crucial part of computer vision, with numerous application scenarios. With the increasing popularity of mobile devices, an increasing number of efforts are trying to deploy video understanding models on them. However, existing video understanding models are difficult to deploy due to their large size and prohibitive power consumption. Spiking Neural Networks (SNNs) have shown bioplausibility and low power advantages over Artificial Neural Networks (ANNs), especially on neuromorphic chips which are regarded as essential components of future mobile devices. However, excessively long conversion time-steps and severe performance degradation problems limit their application. To solve the problems above, we explore the application of SNNs on temporal action detection (TAD), which is an important task in video understanding, and propose the first SNN-based end-to-end TAD architecture coined as SpikeTAD. While maintaining extremely low power consumption, SpikeTAD achieves an average mAP of 67.2% in THUMOS14 and 37.42% in ActivityNet-1.3, demonstrating the feasibility of a low-power TAD model. Our code is available at https://github.com/MCG-NJU/SpikeTAD.

Related papers

• DBHN-Net: Dual-Branch Hybrid Neural Network For Low-Complexity Monaural Speech Enhancement [64.23650268245822]
  This work propose a DualBranch Hybrid Neural (DBHN) Network.<n>A dual-branch network integrating ANN and SNN was designed, where the SNN branch reduces power consumption while the ANN branch addresses information loss.<n>Results show that the proposed model maintains superior performance across three public datasets while achieving an average fold reduction in computational complexity.
  arXiv  Detail & Related papers  (2026-06-04T09:16:26Z)
• Fire on Motion: Optimizing Video Pass-bands for Efficient Spiking Action Recognition [21.25634534419545]
  Spiking neural networks (SNNs) have gained traction in vision due to their energy efficiency, bio-plausibility, and inherent temporal processing.<n>However, SNNs still underperform on dynamic video tasks compared to artificial neural networks (ANNs)
  arXiv  Detail & Related papers  (2026-01-30T07:47:23Z)
• Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks [86.28783985254431]
  Spiking neural networks (SNNs) are emerging as a promising alternative to traditional artificial neural networks (ANNs)<n>We propose SpikeSR, which achieves state-of-the-art performance across various remote sensing benchmarks such as AID, DOTA, and DIOR.
  arXiv  Detail & Related papers  (2025-03-06T09:06:06Z)
• Activation-wise Propagation: A Universal Strategy to Break Timestep Constraints in Spiking Neural Networks for 3D Data Processing [29.279985043923386]
  We introduce Activation-wise Membrane Potential Propagation (AMP2), a novel state update mechanism for spiking neurons.<n>Inspired by skip connections in deep networks, AMP2 incorporates the membrane potential of neurons into network, eliminating the need for iterative updates.<n>Our method achieves significant improvements across various 3D modalities, including 3D point clouds and event streams.
  arXiv  Detail & Related papers  (2025-02-18T11:52:25Z)
• Spiking Two-Stream Methods with Unsupervised STDP-based Learning for Action Recognition [1.9981375888949475]
  Deep Convolutional Neural Networks (CNNs) are currently the state-of-the-art methods for video analysis. We use Convolutional Spiking Neural Networks (CSNNs) trained with the unsupervised Spike Timing-Dependent Plasticity (STDP) rule for action classification. We show that two-stream CSNNs can successfully extract information from videos despite using limited training data.
  arXiv  Detail & Related papers  (2023-06-23T20:54:44Z)
• Spiking Neural Network for Ultra-low-latency and High-accurate Object Detection [18.037802439500858]
  Spiking Neural Networks (SNNs) have garnered widespread interest for their energy efficiency and brain-inspired event-driven properties. Recent methods like Spiking-YOLO have expanded the SNNs to more challenging object detection tasks. They often suffer from high latency and low detection accuracy, making them difficult to deploy on latency sensitive mobile platforms.
  arXiv  Detail & Related papers  (2023-06-21T04:21:40Z)
• Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs [74.83613252825754]
  "smart ecosystems" are being formed where sensing happens concurrently rather than standalone. This is shifting the on-device inference paradigm towards deploying neural processing units (NPUs) at the edge. We propose a novel early-exit scheduling that allows preemption at run time to account for the dynamicity introduced by the arrival and exiting processes.
  arXiv  Detail & Related papers  (2022-09-27T15:04:01Z)
• LaneSNNs: Spiking Neural Networks for Lane Detection on the Loihi Neuromorphic Processor [12.47874622269824]
  We present a new SNN-based approach, called LaneSNN, for detecting the lanes marked on the streets using the event-based camera input. We implement and map the learned SNNs models onto the Intel Loihi Neuromorphic Research Chip. For the loss function, we develop a novel method based on the linear composition of Weighted binary Cross Entropy (WCE) and Mean Squared Error (MSE) measures.
  arXiv  Detail & Related papers  (2022-08-03T14:51:15Z)
• FPGA-optimized Hardware acceleration for Spiking Neural Networks [69.49429223251178]
  This work presents the development of a hardware accelerator for an SNN, with off-line training, applied to an image recognition task. The design targets a Xilinx Artix-7 FPGA, using in total around the 40% of the available hardware resources. It reduces the classification time by three orders of magnitude, with a small 4.5% impact on the accuracy, if compared to its software, full precision counterpart.
  arXiv  Detail & Related papers  (2022-01-18T13:59:22Z)
• Making DensePose fast and light [78.49552144907513]
  Existing neural network models capable of solving this task are heavily parameterized. To enable Dense Pose inference on the end device with current models, one needs to support an expensive server-side infrastructure and have a stable internet connection. In this work, we target the problem of redesigning the DensePose R-CNN model's architecture so that the final network retains most of its accuracy but becomes more light-weight and fast.
  arXiv  Detail & Related papers  (2020-06-26T19:42:20Z)
• Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention [84.83632045374155]
  Attentive video modeling is essential for action recognition in unconstrained videos. What-Where-When (W3) video attention module models all three facets of video attention jointly. Experiments show that our attention model brings significant improvements to existing action recognition models.
  arXiv  Detail & Related papers  (2020-04-02T21:48:11Z)

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.