Action-Aligned Retrieval with Pairwise Multimodal Reranking for Text-Based Person Anomaly Search

• URL: http://arxiv.org/abs/2608.23503v1
• Date: Mon, 24 Aug 2026 17:04:34 GMT
• Title: Action-Aligned Retrieval with Pairwise Multimodal Reranking for Text-Based Person Anomaly Search
• Abstract summary: Text-based person anomaly search requires distinguishing individuals based on fine-grained, context-dependent behaviors rather than mere appearance.<n>Existing methods struggle to capture these context-conditioned actions.<n>We propose a unified three-stage coarse-to-fine framework that combines action-aligned retrieval with pairwise multimodal reranking.
• Score: 10.617164505348283
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-based person anomaly search requires distinguishing individuals based on fine-grained, context-dependent behaviors rather than mere appearance. Existing methods struggle to capture these context-conditioned actions, frequently relying on isolated skeletal geometry, discarding raw query details during reformulation, or utilizing absolute pointwise scoring for multimodal verification. To address these limitations, we propose \textbf{ActPair}, a unified three-stage coarse-to-fine framework that combines action-aligned retrieval with pairwise multimodal reranking to bridge the pose-semantic gap. First, we fine-tune a vision-language model (VLM) with an action-aligned multi-task objective that encourages the representations to encode action-discriminative semantics. Second, we perform parallel late-fusion retrieval using the original query and a large language model (LLM)-generated context-grounded rewrite, retaining complementary details from both semantic views. Finally, we propose an efficient off-the-shelf reranking module that leverages a pivot-promote algorithm to perform direct pairwise visual comparisons, mitigating residual spatial and compositional ambiguities without the prohibitive inference costs of exhaustive evaluation. Extensive experiments demonstrate that our framework achieves the best results among the compared methods on the Pedestrian Anomaly Behavior (PAB) public test and transfers effectively to an unseen, non-anomaly-specific dataset.

Related papers

• Generative Universal Multimodal Retrieval with Dual-role Identifiers [1.0981910170846492]
  We propose DrIG, a novel Generative framework for universal multimodal retrieval featuring Dual-role Identifiers.<n>DrIG consistently outperforms state-of-the-art generative multimodal baselines across diverse tasks, while hybrid reranking achieves a favorable efficiency-effectiveness trade-off against strong dense retrievers.
  arXiv  Detail & Related papers  (2026-08-13T09:10:09Z)
• FaLCon: Facet-Anchored Retrieval with Late Consensus for Sim2Real Text-Based Person Anomaly Search [0.8609344172589112]
  Text-based person anomaly search requires retrieving real-world pedestrian images from detailed natural-language descriptions.<n>This Sim2Real setting is particularly challenging because visually similar candidates may differ only in subtle actions, object interactions, or appearance attributes.<n>We propose an anchor-constrained coarse-to-fine retrieval framework that combines global semantic matching with fine-grained verification.
  arXiv  Detail & Related papers  (2026-08-10T11:42:52Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval [0.5999777817331317]
  Cross-modal image-text retrieval is challenging because of the diverse possible associations between content from different modalities.<n>Traditional methods learn a single-vector embedding to represent semantics of each sample.<n>Set-based approaches, which represent each sample with multiple embeddings, offer a promising alternative.
  arXiv  Detail & Related papers  (2025-06-26T17:55:34Z)
• Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contexts [67.67746334493302]
  Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous tasks, yet they often rely on external context to handle complex tasks.<n>We propose a tri-encoder sequential retriever that models this process as a Markov Decision Process (MDP)<n>We show that our method consistently and significantly outperforms baselines, underscoring the importance of explicitly modeling inter-example dependencies.
  arXiv  Detail & Related papers  (2025-04-15T17:35:56Z)
• Boundary-Driven Table-Filling with Cross-Granularity Contrastive Learning for Aspect Sentiment Triplet Extraction [8.011606196420757]
  The Aspect Sentiment Triplet Extraction task is one of the most prominent subtasks in fine-grained sentiment analysis.<n>Most existing approaches frame triplet extraction as a 2D table-filling process in an end-to-end manner.<n>We propose boundary-driven table-filling with cross-granularity contrastive learning (BTF-CCL) to enhance the semantic consistency between sentence-level representations and word-level representations.
  arXiv  Detail & Related papers  (2025-02-04T02:23:45Z)
• Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints [15.541287957548771]
  We propose a Coarse-to-fine Consistency Constraints Visual Grounding architecture.<n>It integrates implicit and explicit modeling approaches within a two-stage framework.<n>It significantly outperforms state-of-the-art REC and RIS methods by a substantial margin.
  arXiv  Detail & Related papers  (2025-01-12T04:30:13Z)
• CART: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling [53.97609687516371]
  Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data.<n>Traditional solutions utilize a single-tower or dual-tower framework to explicitly compute the score between queries and candidates.<n>We propose a generative cross-modal retrieval framework (CART) based on coarse-to-fine semantic modeling.
  arXiv  Detail & Related papers  (2024-06-25T12:47:04Z)
• Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person Retrieval [66.61856014573742]
  Text-based person retrieval (TPR) is a challenging task that involves retrieving a specific individual based on a textual description. Previous methods have attempted to align text and image samples in a modal-shared space. We propose an effective bi-directional one-to-many embedding paradigm that offers a clear optimization direction for each sample.
  arXiv  Detail & Related papers  (2024-06-09T03:06:55Z)
• Cross-Modal Coordination Across a Diverse Set of Input Modalities [0.0]
  Cross-modal retrieval is the task of retrieving samples of a given modality by using queries of a different one. This paper proposes two approaches to the problem: the first is based on an extension of the CLIP contrastive objective to an arbitrary number of input modalities. The second departs from the contrastive formulation and tackles the coordination problem by regressing the cross-modal similarities towards a target.
  arXiv  Detail & Related papers  (2024-01-29T17:53:25Z)
• Learnable Pillar-based Re-ranking for Image-Text Retrieval [119.9979224297237]
  Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Re-ranking, a popular post-processing practice, has revealed the superiority of capturing neighbor relations in single-modality retrieval tasks. We propose a novel learnable pillar-based re-ranking paradigm for image-text retrieval.
  arXiv  Detail & Related papers  (2023-04-25T04:33:27Z)
• Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning [53.68371566336254]
  We argue that the key to better performance lies in meaningful latent modality structures instead of perfect modality alignment. Specifically, we design 1) a deep feature separation loss for intra-modality regularization; 2) a Brownian-bridge loss for inter-modality regularization; and 3) a geometric consistency loss for both intra- and inter-modality regularization.
  arXiv  Detail & Related papers  (2023-03-10T14:38:49Z)
• Unsupervised Summarization by Jointly Extracting Sentences and Keywords [12.387378783627762]
  RepRank is an unsupervised graph-based ranking model for extractive multi-document summarization. We show that salient sentences and keywords can be extracted in a joint and mutual reinforcement process using our learned representations. Experiment results with multiple benchmark datasets show that RepRank achieved the best or comparable performance in ROUGE.
  arXiv  Detail & Related papers  (2020-09-16T05:58:00Z)

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.