LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation

• URL: http://arxiv.org/abs/2604.18274v2
• Date: Mon, 27 Apr 2026 02:45:59 GMT
• Title: LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation
• Abstract summary: LiquidTAD is a framework that distills the exponential relaxation prior to liquid neural dynamics into a parallel temporal operator.<n>LiquidTAD achieves accuracy competitive with strong baselines while substantially lowering the model footprint.
• Score: 2.3837169660687123
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Temporal Action Detection (TAD) requires precise localization of action boundaries within long, untrimmed video sequences. While current high-performing methods achieve strong accuracy, they are often characterized by excessive parameter counts, substantial computational overhead, and a reliance on specialized operators that hinder deployment across diverse hardware platforms. This paper presents LiquidTAD, a framework that distills the exponential relaxation prior of liquid neural dynamics into a parallel temporal operator, rather than reproducing full Liquid Neural Network (LNN) dynamics. By introducing a Parallel Liquid-inspired Relaxation mechanism, sequential ODE solving is avoided through a fully vectorized, non-recursive formulation built entirely upon standard neural operations, enabling hardware-agnostic deployment with linear complexity with respect to the temporal length. A complementary Hierarchical Decay-Rate Sharing Strategy further adapts this relaxation prior across feature pyramid levels, stabilizing optimization and implicitly compensating for temporal compression in deeper layers. Experimental evaluations on THUMOS-14 and ActivityNet-1.3 demonstrate that LiquidTAD achieves accuracy competitive with strong baselines while substantially lowering the model footprint. Specifically, on THUMOS-14, LiquidTAD achieves 69.46\% average mAP with only 10.82M parameters and 27.17G FLOPs, reducing the parameter count by over 60\% compared with ActionFormer.

Related papers

• High-fidelity Modeling of Full-scale Pressurized Water Reactor Flow Fields for Machine Learning Applications [3.8347851078346427]
  This work presents a high-fidelity computational fluid dynamics (CFD) and data-driven modeling framework for assembly-level flow characterization in a pressurized water reactor.<n>A full lower-plenum and core-inlet domain was constructed using publicly available geometry and operating conditions, enabling transient simulations with pump-induced swirl boundary conditions.<n>Results show that cold-leg swirl and lower-plenum transport generate strongly heterogeneous assembly-wise inlet flow distributions, particularly near the lower core region.<n>A 3D convolutional-based inpainting model successfully recon-structed missing assembly-level mass flow rates from partial observations
  arXiv  Detail & Related papers  (2026-05-23T22:50:23Z)
• FASTER: Rethinking Real-Time Flow VLAs [82.58822112377923]
  Real-time execution is crucial for deploying Vision-Language-Action (VLA) models in the physical world.<n>We show that reaction time follows a uniform distribution determined jointly by the Time to First Action (TTFA) and the execution horizon.<n>We propose Fast Action Sampling for ImmediaTE Reaction (FASTER) to overcome this issue.
  arXiv  Detail & Related papers  (2026-03-19T17:51:37Z)
• TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration [64.32072516882947]
  Diffusion Policy excels in embodied control but suffers from high inference latency and computational cost.<n>We propose Temporal-aware Reinforcement-based Speculative Diffusion Policy (TS-DP)<n>TS-DP achieves up to 4.17 times faster inference with over 94% accepted drafts, reaching an inference frequency of 25 Hz.
  arXiv  Detail & Related papers  (2025-12-13T07:53:14Z)
• Periodicity-Enforced Neural Network for Designing Deterministic Lateral Displacement Devices [4.743321030941228]
  This paper introduces a periodicity-enforced surrogate modeling approach that incorporates periodic layers, neural network components that guarantee exact periodicity without penalty terms or output modifications.<n>The proposed method employs three sub-networks to predict steady-state, non-dimensional velocity and pressure fields rather than directly predicting critical diameters or particle trajectories.
  arXiv  Detail & Related papers  (2025-11-21T20:14:16Z)
• PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching [51.98089287914147]
  textbfPick-and-textbflay textbfMemory (PM) construction module for dynamic bfStereo matching, dubbed as bftextPPMStereo.<n>Inspired by the two-stage decision-making process in humans, we propose a textbfPick-and-textbflay textbfMemory (PM) construction module for dynamic bfStereo matching, dubbed as bftextPPMStereo.
  arXiv  Detail & Related papers  (2025-10-23T03:52:39Z)
• HAD: Hierarchical Asymmetric Distillation to Bridge Spatio-Temporal Gaps in Event-Based Object Tracking [80.07224739976911]
  Event cameras offer exceptional temporal resolution and a range (modal)<n> RGB cameras excel at capturing rich texture with high resolution, whereas event cameras offer exceptional temporal resolution and a range (modal)
  arXiv  Detail & Related papers  (2025-10-22T13:15:13Z)
• Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency [60.74505433956616]
  continuous-time consistency model (sCM) is theoretically principled and empirically powerful for accelerating academic-scale diffusion.<n>We first develop a parallelism-compatible FlashAttention-2 JVP kernel, enabling sCM training on models with over 10 billion parameters and high-dimensional video tasks.<n>We propose the score-regularized continuous-time consistency model (rCM), which incorporates score distillation as a long-skip regularizer.
  arXiv  Detail & Related papers  (2025-10-09T16:45:30Z)
• UTAL-GNN: Unsupervised Temporal Action Localization using Graph Neural Networks [0.0]
  Fine-grained action localization in untrimmed sports videos presents a significant challenge due to rapid and subtle motion transitions.<n>Existing supervised and weakly supervised solutions often rely on extensive datasets and high-capacity models, making them computationally intensive and less adaptable to real-world scenarios.<n>Our approach pre-trains an Attention-based Spatio-Temporal Graph Convolutional Network (ASTGCN) on a pose-sequence denoising annotated with blockwise partitions.<n>Our method achieves a mean Average Precision (mAP) of 82.66% and average latency localization of 29.09 ms on the DSV Diving dataset
  arXiv  Detail & Related papers  (2025-08-27T07:51:02Z)
• YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception [58.06752127687312]
  We propose YOLOv13, an accurate and lightweight object detector.<n>We propose a Hypergraph-based Adaptive Correlation Enhancement (HyperACE) mechanism.<n>We also propose a Full-Pipeline Aggregation-and-Distribution (FullPAD) paradigm.
  arXiv  Detail & Related papers  (2025-06-21T15:15:03Z)
• MesaNet: Sequence Modeling by Locally Optimal Test-Time Training [67.45211108321203]
  We introduce a numerically stable, chunkwise parallelizable version of the recently proposed Mesa layer.<n>We show that optimal test-time training enables reaching lower language modeling perplexity and higher downstream benchmark performance than previous RNNs.
  arXiv  Detail & Related papers  (2025-06-05T16:50:23Z)
• Physics-informed Multiple-Input Operators for efficient dynamic response prediction of structures [0.07916635054977067]
  MIONet predicts structural responses continuously over both space and time.<n>Model is validated on both a simple beam and the KW-51 bridge, achieving FEM level accuracy within seconds.
  arXiv  Detail & Related papers  (2025-05-11T18:45:58Z)
• Hybrid machine learning models based on physical patterns to accelerate CFD simulations: a short guide on autoregressive models [3.780691701083858]
  This study presents an innovative integration of High-Order Singular Value Decomposition with Long Short-Term Memory (LSTM) architectures to address the complexities of reduced-order modeling (ROM) in fluid dynamics.<n>The methodology is tested across numerical and experimental data sets, including two- and three-dimensional (2D and 3D) cylinder wake flows, spanning both laminar and turbulent regimes.<n>The results demonstrate that HOSVD outperforms SVD in all tested scenarios, as evidenced by using different error metrics.
  arXiv  Detail & Related papers  (2025-04-09T10:56:03Z)
• AMR-Transformer: Enabling Efficient Long-range Interaction for Complex Neural Fluid Simulation [33.63726923336252]
  We propose AMR-Transformer, an efficient and accurate neural CFD-solving pipeline.<n>It integrates a novel adaptive mesh refinement scheme with a Navier-Stokes constraint-aware fast pruning module.<n>Our approach achieves an order-of-magnitude improvement in accuracy over baseline models.
  arXiv  Detail & Related papers  (2025-03-13T11:16:42Z)
• Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints [51.83081671798784]
  Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability.<n>DiT's practical application suffers from inherent dynamic feature instability, leading to error amplification during cached inference.<n>We propose Skip-DiT, an image and video generative DiT variant enhanced with Long-Skip-Connections (LSCs) - the key efficiency component in U-Nets.
  arXiv  Detail & Related papers  (2024-11-26T17:28:10Z)
• Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting [26.141054975797868]
  We propose a novel Adaptive Multi-Scale Decomposition (AMD) framework for time series forecasting.<n>Our framework decomposes time series into distinct temporal patterns at multiple scales, leveraging the Multi-Scale Decomposable Mixing (MDM) block.<n>Our approach effectively models both temporal and channel dependencies and utilizes autocorrelation to refine multi-scale data integration.
  arXiv  Detail & Related papers  (2024-06-06T05:27:33Z)
• Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution [57.71199089609161]
  Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. We propose an efficient Transformerbased model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects.
  arXiv  Detail & Related papers  (2023-01-05T13:59:29Z)
• Real-time simulation of parameter-dependent fluid flows through deep learning-based reduced order models [0.2538209532048866]
  Reduced order models (ROMs) provide reliable approximations to parameter-dependent fluid dynamics problems in rapid times. Deep learning (DL)-based ROMs overcome all these limitations by learning in a non-intrusive way both the nonlinear trial manifold and the reduced dynamics. The resulting POD-DL-ROMs are shown to provide accurate results in almost real-time for the flow around a cylinder benchmark, the fluid-structure interaction between an elastic beam attached to a fixed, rigid block and a laminar incompressible flow, and the blood flow in a cerebral aneurysm.
  arXiv  Detail & Related papers  (2021-06-10T13:07:33Z)
• Liquid Time-constant Networks [117.57116214802504]
  We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
  arXiv  Detail & Related papers  (2020-06-08T09:53:35Z)

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.