LightAIR: Lightweight Action Inversion and Riemannian Rectification for Text-based Person Anomaly Search

• URL: http://arxiv.org/abs/2608.09152v1
• Date: Mon, 10 Aug 2026 05:59:07 GMT
• Title: LightAIR: Lightweight Action Inversion and Riemannian Rectification for Text-based Person Anomaly Search
• Abstract summary: We propose a lightweight action inversion and rectification network (LightAIR) for Person Anomaly Search.<n>Experiments on the widely used TPAS and TIPR datasets demonstrate that LightAIR significantly outperforms existing state-of-the-art methods.
• Score: 47.5045602470916
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional Text-based Person Search (TPS) is typically limited to matching static appearance attributes, severely neglecting dynamic action information. The Text-based Person Anomaly Search (TPAS) task bridges this gap, requiring models to locate micro-level specific abnormal behaviors while matching macro-level appearance of pedestrians. However, current TPAS methods face fundamental limitations: external explicit pose estimators are fragile in unconstrained surveillance scenarios, and implicit learning encounters visual decoupling failure under pixel-level entanglement, causing dominant appearance information to easily swallow and contaminate subtle action features. Furthermore, performing contrastive optimization on hard negative samples (``same appearance, different actions'') in conventional Euclidean spaces induces severe shortcut learning. To address these, we propose the Lightweight Action Inversion and Riemannian rectification network (LightAIR). First, it introduces textual semantic priors as anchors via a lightweight action inversion operator to extract pure action features, thereby overcoming visual-inherent coupling. Subsequently, it employs orthogonal null-space projection to constrain appearance features within the orthogonal complement space of action features, guaranteeing strict forward decoupling. Finally, we designed a gradient rectification module that computes the Riemannian gradient to constrain the backpropagation trajectory, forcing the gradient flow to update strictly along the tangent space that preserves decoupling properties, thereby cutting off harmful shortcuts. Extensive experiments on the widely used TPAS and TIPR datasets demonstrate that LightAIR significantly outperforms existing state-of-the-art methods. Codes are available at https://github.com/rainy-london/LightAIR

Related papers

• Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection [7.184018933441995]
  Vision-language models offer a promising approach for zero-shot anomaly detection (ZSAD)<n>Normal and anomalous text prototypes exhibit a high semantic overlap.<n>We propose Proximity-CLIP, a framework that visually calibrates the semantic margin to guide visual adaptation.
  arXiv  Detail & Related papers  (2026-09-07T08:48:27Z)
• ExACT: Exemplar-Driven Calibrated Refinement for Training-Free Visual Grounding in Remote Sensing Images [51.53960096934913]
  Remote sensing visual grounding (RSVG) aims to locate specific objects in high-resolution RS imagery using free-form natural language descriptions.<n>Recent advances in multimodal large language models (MLLMs) show great potential for such open-vocabulary RSVG.<n>We propose Exemplar-driven Calibrated Refinement (ExACT), a training-free framework driven by a one-shot visual prompting mechanism.
  arXiv  Detail & Related papers  (2026-06-27T13:50:39Z)
• Need We Teach Foundation Models What is a Generative Image? Gradient-Free Generative Artifact Detection via Analytic Spectral Adaptation [3.881211374324378]
  Adapting foundation models to detect generative artifacts via gradient-based updates compromises their intrinsic representations.<n>We propose a gradient-free methodology reframing detection from binary classification to an out-of-distribution (OOD) anomaly measurement problem.
  arXiv  Detail & Related papers  (2026-06-03T13:04:23Z)
• ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both [55.182037225013836]
  ATLAS is a framework in which a single discrete 'word', termed as a functional token, serves both as an agentic operation and a latent visual reasoning unit.<n> ATLAS achieves superior performance on challenging benchmarks while maintaining clear interpretability.
  arXiv  Detail & Related papers  (2026-05-14T17:59:55Z)
• Exploring the Limits of End-to-End Feature-Affinity Propagation for Single-Point Supervised Infrared Small Target Detection [6.7126559398433665]
  Single-point supervised infrared small target detection (IRSTD) drastically reduces dense annotation costs.<n>Current state-of-the-art (SOTA) methods achieve high precision by recovering mask supervision through explicit, offline pseudo-label construction.<n>We study a minimalist alternative: generating point-to-mask supervision online through in-batch, point-anchored feature-affinity propagation.
  arXiv  Detail & Related papers  (2026-05-01T15:08:46Z)
• ORSIFlow: Saliency-Guided Rectified Flow for Optical Remote Sensing Salient Object Detection [16.437554336020757]
  Optical Remote Sensing Image Salient Object Detection (ORSI-SOD) remains challenging due to complex backgrounds, low contrast, irregular object shapes, and large variations in object scale.<n>We propose ORSIFlow, a saliency-guided rectified flow framework that reformulates ORSI-SOD as a deterministic latent flow generation problem.<n>To enhance saliency awareness, we design a Salient Feature Discriminator for global semantic discrimination and a Salient Feature Calibrator for precise boundary refinement.
  arXiv  Detail & Related papers  (2026-03-30T15:33:26Z)
• Towards Controllable Low-Light Image Enhancement: A Continuous Multi-illumination Dataset and Efficient State Space Framework [2.977173671229414]
  We introduce Controllable Low-light Enhancement (CLE), a holistic framework supported by Light100.<n>To resolve the conflict between luminance control and chromatic fidelity, a noise-decoupled supervision strategy is employed.<n>Our approach achieves competitive performance and robust controllability, providing a real-world multi-illumination alternative.
  arXiv  Detail & Related papers  (2026-03-26T10:40:08Z)
• Benchmarking Visual Feature Representations for LiDAR-Inertial-Visual Odometry Under Challenging Conditions [11.85572971097983]
  This paper introduces a hybrid approach that integrates direct photometric methods with descriptor-based feature matching.<n>The experimental results reveal that the proposed hybrid approach outperforms the conventional sparse-direct method.
  arXiv  Detail & Related papers  (2026-03-19T07:56:49Z)
• Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation [51.743225614196774]
  Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language reasoning.<n>They remain vulnerable to hallucination, where generated content deviates from visual evidence.<n>Recent vision enhancement methods attempt to address this issue by reinforcing visual tokens during decoding.<n>We propose Adaptive Visual Reinforcement (AIR), a training-free framework for MLLMs.
  arXiv  Detail & Related papers  (2026-02-27T14:18:51Z)
• Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection [52.5174167737992]
  Video anomaly detection (VAD) aims to identify abnormal events in videos.<n>We propose SteerVAD, which advances MLLM-based VAD by shifting from passively reading to actively steering and rectifying internal representations.<n>Our method achieves state-of-the-art performance among tuning-free approaches requiring only 1% of training data.
  arXiv  Detail & Related papers  (2026-02-27T13:48:50Z)
• Visual Prompt Tuning in Null Space for Continual Learning [51.96411454304625]
  Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL) This paper aims to learn each task by tuning the prompts in the direction orthogonal to the subspace spanned by previous tasks' features. In practice, an effective null-space-based approximation solution has been proposed to implement the prompt gradient projection.
  arXiv  Detail & Related papers  (2024-06-09T05:57:40Z)

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.