Cross-Modal Retrieval

Geospatial and urban applications increasingly require models to compare heterogeneous evidence across street-view imagery, remote-sensing observations, text descriptions, region proposals, and temporal change cues. However, existing multimodal embedding models and benchmarks are still largely designed and evaluated around general-purpose image-text matching, leaving unclear whether unified embedding space can support heterogeneous geospatial tasks involving spatial relationships, fine-grained semantics, and temporal changes. To address this gap, we make three key contributions. First, we introduce GeoMEB, a large-scale multimodal embedding benchmark that standardizes 45 urban evaluation tasks across retrieval, visual question answering, change detection, classification, and visual grounding, together with training collections comprising 1.32M examples and 286K evaluation queries. Second, we present Geo-Embed, a unified embedding model that adapts a shared vision-language backbone to instruction-conditioned query-target matching over heterogeneous geospatial inputs, including single images, multiple images, text, regions, and masks. On GeoMEB, Geo-Embed achieves the strongest overall performance among representative multimodal embedders, with a 15.3% relative improvement over the strongest baseline. These results motivate future geospatial embedders that organize training and evaluation around explicit query-target relations, including semantic, cross-view, region-level, and temporal correspondence.

Adapting CLIP for zero-shot sketch-based image retrieval (ZS-SBIR) via prompt learning faces a fundamental tension: the model must bridge the sketch-photo domain gap through task-specific adaptation, yet the added flexibility risks overfitting to seen training categories and eroding CLIP's zero-shot generalization. We present SeCo-SBIR, a semantically consistent prompt learning framework that resolves this tension from both sides. First, a text-guided multi-modal prompting strategy routes learnable prompt vectors through CLIP's text encoder and projects the resulting intermediate representations into the visual encoder at every layer via learnable coupling functions. Because the text encoder has already learned robust, abstract category-level semantics from large-scale language supervision, this mechanism injects transferable semantic knowledge directly into the visual pathway - adapting the model to the sketch-photo domain while inherently favoring generalization to unseen classes. Second, a perturbation-based consistency constraint addresses the residual overfitting risk from the learnable coupling functions by aligning the adapted model with a frozen CLIP reference branch using an asymmetric InfoNCE objective - augmented inputs feed the frozen branch while clean inputs feed the trainable branch - anchoring the learned representations to CLIP's generalizable feature space. Together with lightweight adapters and a multi-objective loss combining triplet, NT-Xent, and classification terms, SeCo-SBIR achieves state-of-the-art results on all three standard ZS-SBIR benchmarks across categorical, generalized, and across-dataset settings.

Scientific formulae are a fundamental component of scholarly communication, yet their dual nature -- as structured syntax and carriers of semantics -- remains underexplored in scholarly information retrieval. Although prior studies show that jointly modeling syntactic and semantic modalities improves retrieval performance, the relationship between their underlying representations has not been systematically investigated. In this work, we empirically study cross-modal correspondence between formula syntax and semantics. We find that their native representation spaces exhibit extremely weak observable correspondence despite strong latent correlation, indicating a substantial representation mismatch between the two modalities. We further evaluate whether this mismatch can be reduced using standard representation learning and alignment techniques. We represent syntactic structure using graph-based encoders and semantic information using text-based encoders, then apply contrastive learning to induce a shared representation space. Results show that the learned alignment substantially improves cross-modal retrieval, suggesting that explicit representation learning can recover correspondence absent from the original representation spaces.

Identifying the Inflamed'' immunophenotype in Gastric Adenocarcinoma predicts immunotherapy response but requires an expensive 10-gene RNA signature. While deep learning on standard H\&E slides offers a scalable alternative, conventional binary classifiers oversimplify continuous RNA data and introduce label noise. To resolve this, we propose VITA (VIrtual Transcriptomic Approximation). By aligning H\&E and RNA into a joint latent space during training, VITA requires only standard H\&E at inference to retrieve morphologically similar historical cases and approximate the continuous RNA signature. Achieving 0.72 classification accuracy and a 0.66 Spearman correlation, VITA provides a cost-effective virtual transcriptomics'' pre-screening tool that preserves the continuous phenotypic spectrum without requiring genomic sequencing.

Universal multimodal embedding (UME) maps heterogeneous multimodal inputs into a shared embedding space. Existing UME models either form embeddings through single forward encoding or add computation through explicit rationale tokens and latent autoregressive states. Although token expansion can improve complex matching, serial generation increases retrieval latency and makes the final embedding depend on generated intermediate states. This raises a different question: can useful computation be expanded along model depth while keeping the token workspace fixed? We analyze positive-negative similarity separation at every layer of independently trained UME models and observe a shared progression: early layers contextualize multimodal inputs, a contiguous middle-to-late stage forms retrieval-discriminative features, and the final layers map them into the embedding space. Based on this finding, we propose ReLoop-UME, which executes the early layers once, recurrently reuses a parameter-shared retrieval-forming block, and applies the final mapping layers after the last loop. Learnable Retrieval Registers provide persistent retrieval-specific states that accumulate and exchange evidence across loops, with the final register serving as the embedding readout. On MMEB-V2 and MRMR, ReLoop-UME consistently improves retrieval across different backbones while running 44.9x faster than UME-R1 and 1.5x faster than PLUME.

Operational Earth observation increasingly calls for answering queries such as find the image pairs where a new building appeared.'' This means searching an archive of before-and-after (bi-temporal) satellite image pairs and ranking each pair by how well it matches a natural-language description of the change. The component that performs this match, the fusion module that combines the before'' and ``after'' views, must be run at query time across many candidate pairs, so its speed largely sets the cost of every search. We present a controlled comparison of how to build that module. Using one fixed image encoder (a frozen CLIP model) and one training recipe for all variants, we evaluate eight designs drawn from three families: attention, state-space models (Mamba), and learned compression (our Temporal Bottleneck Fusion, TBF). Each design is tested on two benchmarks (LEVIR-CC and Dubai-CC) with ten random seeds, so the reported differences are statistically grounded. We outline three findings: first, a training-free two-stage search (a cheap difference model that shortlists candidates, followed by attention fusion that re-ranks them) matches or exceeds full-fusion recall on LEVIR-CC while cutting query cost $10$-$15\times$, with comparable R@1/R@5 on Dubai-CC; second, the linear-time scan of Mamba, attractive on paper, gives no speed benefit at the patch counts typical of vision transformers ($L{=}196$): the scan is limited by memory bandwidth, whereas attention maps cleanly onto parallel hardware; and third, compressing the fused representation (TBF) reduces parameters by $2.3\times$ and latency by $1.6\times$ for a change-only BLEU-1 cost of $0.007$, although more aggressive compression quietly discards change-relevant detail that aggregate metrics fail to reveal.

Multimodal drug discovery enables drug representation learning beyond chemical structure by incorporating cellular responses such as gene expression and cell morphology. However, direct fusion and instance-level contrastive alignment may mix mechanism-related signals with modality-specific noise and incorrectly separate structurally dissimilar but biologically related compounds. This limitation can obscure transferable mechanism patterns required for predicting the properties of unseen compounds. We introduce PMRD, a pharmacological response domain-guided framework for multimodal zero-shot drug property prediction. PMRD separates mechanism-consistent factors from modality-specific information and constructs a consensus response domain across three modalities. Mechanism candidate augmentation identifies locally stable factors, while retrieval-geometry attribution dynamically reweights the alignment and augmentation objectives according to whether their updates preserve inter-drug discriminability.This feedback suppresses training signals that conflict with mechanism-discriminative retrieval. PMRD further combines complementary representations through reliability-aware multiview retrieval. Experiments on public datasets show improved zero-shot property prediction and more biologically coherent drug neighborhoods. Hard-negative analysis further indicates fewer conflicts between structurally dissimilar but response-related compounds. These results support PMRD as an effective framework for mechanism-aware multimodal drug representation learning.\footnote{The code will be released upon publication.}

Semantic hashing methods for generating short binary hash codes that allow efficient approximate nearest neighbor search in high-dimensional data spaces have gained extensive consideration in recent years. Deep learning-based methods offer better semantic capturing capabilities than traditional approaches relying on manual feature engineering. Moreover, they enable a data-driven approach to semantic hashing across diverse data modalities, yielding high-quality cross-modal hash codes within a shared Hamming space. Previous work investigated the properties of this Hamming space and introduced a loss function based on predefined so-called semantic channels with fixed width and Hamming distances derived from label similarities. However, this formulation also introduced discontinuities into the loss landscape, complicating optimization. Based on these observations, we propose a newly designed loss function, Dynamic Semantic Channel Hashing (DSCH), using dynamically sized and positioned semantic channels in order to avoid loss landscape discontinuities. Furthermore, we endorse the use of tie-aware Mean Average Precision (mAP) as evaluation metric as it addresses the ambiguity in sample retrieval ordering, which emerges from the discreteness of hash code distances. Finally, multiple experimental settings conducted on two popular datasets and incorporating two different model architectures provide strong evidence that training using the DSCH objective outperforms training using other state-of-the-art loss functions. In a total of 35 out of 40 cross-modal and intra-modal retrieval tasks, models trained with DSCH achieve significantly higher tie-aware mAP scores across all four tested hash code lengths, showing compelling results across model architecture and used dataset. The mAP score uplifts are consistent and amount up to 1.75 percentage points compared to the respective second best.

Multimodal embedding spaces in models like CLIP enable powerful capabilities such as semantic similarity retrieval and cross-modal zero-shot classification. These embeddings compress high-level semantics into a single vector, which comes at the cost of primarily expressing a dominant semantics like main object while suppressing other important attributes such as camera angle or color tone. We propose a text-conditioned transformation of visual embeddings that makes such attributes explicitly accessible. Given a natural language description of an attribute category (e.g., "color" or "art style"), a network generates an affine transformation that emphasizes the specified attribute. Conditioning on text enables it to learn many attributes simultaneously, accessing them at inference time through an intuitive interface. The network is trained to align transformed embeddings with the frozen latent space, enabling retrieval using existing large-scale embeddings without any re-encoding. When applied to a full set, the same mechanism transforms the latent space for attribute disentanglement tasks such as multi-clustering. By operating directly in latent space, our method provides a unified and efficient framework for controlling embedding spaces, demonstrating state-of-the-art performance across both attribute-based retrieval and multi-attribute organization tasks with near-zero inference cost. Project page: https://joefioresi718.github.io/ControlEmbed_webpage/

Text-based person retrieval faces a critical but under-explored challenge: the inherent uncertainty of query granularity in real-world scenarios. This paper introduces a new paradigm, Text-based Person Retrieval with Any Granularity, and provides a systematic solution. First, we formalize a five-level granularity spectrum and construct UFine6926-MG, a high-quality multi-grained dataset annotated comprehensively at all granularities via a novel Multi-grained Text Annotation Engine. Second, acknowledging that coarse queries naturally correspond to multiple valid candidates, we propose MG-Eval, a holistic evaluation benchmark with progressively detailed texts and cross-identity labels that reflect real-world semantics, alongside tailored evaluation metrics and protocols. Third, after a comprehensive diagnosis reveals the systemic limitations of existing research, we propose the Cross-modal Multi-grained Aligning and Matching (CMAM) framework. CMAM achieves granularity-aware retrieval through: 1) orthogonal-expert perception to disentangle granularity-specific features; 2) probabilistic alignment to model many-to-many matches under query uncertainty; and 3) granularity-consistent reasoning to steer feature learning via joint cross-modal granularity verification. Experiments demonstrate that CMAM significantly outperforms state-of-the-art methods across all granularity levels. This work establishes a foundational benchmark and a robust baseline, paving the way for more practical person retrieval systems.

This paper proposes the Distribution-Alignment Bridge (DAB), a framework that reconceptualizes text-to-video retrieval as a distribution alignment task rather than traditional deterministic point matching. By modeling both text and video embeddings as Gaussian distributions defined by mean and variance, DAB explicitly accounts for modality-specific uncertainty. We employ a deterministic, diffusion-inspired bridge to iteratively refine text distributions toward their target video distributions through a truncated refinement process. This approach unifies probabilistic embedding and distributional transformation into a cohesive, end-to-end trainable system. To optimize cross-modal similarity, we introduce a distribution-aware contrastive loss based on Kullback-Leibler divergence. Extensive evaluations on MSR-VTT, MSVD, and VATEX benchmarks confirm that DAB significantly outperforms existing probabilistic and diffusion-based baselines, while providing calibrated uncertainty-aware ranking through bridge-induced distributional margins.

Real-world fashion search involves interactive retrieval across multiple turns. However, existing multi-turn retrieval methods are built on a restrictive assumption that every interaction follows the same attribute-editing paradigm, leaving heterogeneous intent transitions unexplored. Moreover, existing approaches often rely on textification to bridge multimodal queries and visual retrieval, which may lose fine-grained visual cues. To address these gaps, we introduce DIM-Fashion, a benchmark of 26K multi-turn sessions constructed from 13 fashion retrieval datasets across 7 tasks, featuring diverse intent transitions and rollback behaviors. We further propose FashionAM, an MLLM-VLP framework that directly aligns multimodal conversational queries with a fashion-oriented gallery embedding space, avoiding intermediate textification. Extensive experiments demonstrate the effectiveness of FashionAM over existing approaches. The dataset and code will be made publicly available upon acceptance.

Large pretrained vision models have substantially improved appearance-based 3D shape retrieval, but they still confuse shapes that look similar while differing in geometry. Although geometry-aware features can reduce these errors, naive fusion of geometry and appearance may hurt retrieval when the two modalities are already well aligned. We propose GATE-3D, a lightweight query-adaptive reranking method that incorporates geometry without retraining the retrieval backbone. For each query, GATE-3D predicts how much a geometry-aware score should adjust the appearance-based ranking using features that capture disagreement between the two modalities. This selective design lets geometry contribute where it helps and stay silent where it would hurt. Experiments on three open-set 3D retrieval benchmarks show that GATE-3D improves over appearance-only retrieval and is more robust than always-on fusion. On the primary benchmark, it improves mAP@10 by 2.00 points over appearance-only retrieval (p=0.041); it also improves leave-one-category-out generalization and reduces geometric false positives by 10.8%. GATE-3D achieves competitive zero-shot results against DAC-based baselines. We further find that simple linear routing is more effective than a small MLP in the low-data regime, suggesting that cross-modal disagreement features matter more than model capacity for adaptive routing.

Visible-Infrared Person Re-Identification (VI-ReID) operates under a closed-world assumption, where queries and galleries are from heterogeneous modalities. However, in open-world scenarios, both sets are likely to contain homogeneous and heterogeneous modality images. A query may consist of visible-only, infrared-only, or mixed-modality images, while galleries present multi-modal images over long-term collection. Under these conditions, VI-ReID methods, built on a heterogeneous-modality retrieval paradigm, suffer from three trustworthiness challenges: matching conflicts due to high homogeneous-modality similarity, interference from modality uncertainty, and robustness degradation induced by unknown modality combinations. They fail to meet the requirements of trustworthy visual recognition in reliability, consistency, and dynamic adaptability. To address these challenges, we formalize the Visible-Infrared Modality-Incomplete Re-Identification (VIMI-ReID) task. We reorganize existing datasets to construct the SYSU-VIMI and RegDB-VIMI benchmarks. The unpredictable modality combinations and inherent similarity of homogeneous-modality samples in VIMI-ReID cause a significant performance drop in existing VI-ReID methods. We propose the Modality Adaptive Matching Transformer (MAMT). It employs a Divergence Transformer Module (DTM) and a Shared Transformer Module (STM) to extract modality-specific and modality-shared features, respectively. Guided by a divergence loss, the DTM enriches modality-specific features with modality-style information to enhance discriminability within the same modality. A Modality Adaptive Matching Module (MAM) dynamically fuses features according to the query-gallery modality relationship, enabling stable matching under arbitrary and uncertain modality conditions. Extensive experiments on the VIMI benchmarks demonstrate the effectiveness and adaptability of MAMT.

A single embedding space that covers text, images, video, and audio lets one index serve every query a user can pose. Embedding models built on vision-language backbones now lead text/image/video retrieval benchmarks but lack audio entirely, while audio-text retrieval is led by specialist systems that serve no other modality. We present the Fusion Embedding family, which adds audio to a frozen vision-language embedding base whose parameters are never updated: generation 1 (fusion-embedding-1) trains only a 16.4M-parameter connector between a frozen audio tower and the frozen base, and generation 2 (fusion-embedding-2) adds modality-gated deep adapters (44.2M parameters) whose branch never executes on text, image, or video inputs: their outputs are bit-for-bit those of the released base, verified after every training run. Because the base already binds text, images, and video, aligning audio to text alone makes audio-image retrieval emerge, with zero paired audio-visual training data. Alongside the recipe we map its design space with controlled negative results (rewriting training captions with an LLM, substituting a leaderboard-stronger audio tower, and widening the connector each reduce retrieval) and with training-protocol findings that we expect to transfer to any frozen decoder-LM embedding backbone. Both generations train in hours on a single GPU. Weights, code, and the evaluation harness are openly released.

EEG-based visual decoding provides a non-invasive pathway for interpreting visual semantics. However, existing methods often overlook the perceptual asymmetry between foreground and background in complex scenes, leading to background interference and semantic misalignment. EEG signals also exhibit rapid temporal dynamics and nonstationary spatial patterns, making it difficult to capture the time-varying brain connectivity associated with focal visual attention. To address these limitations, we propose FSDBN, a unified framework for robust EEG-visual decoding. FSDBN introduces Semantic-Consistent Saliency Alignment to separate semantically relevant foreground regions from background noise under joint saliency and semantic constraints. It further employs Semantic-Prior Dynamic Gating Foreground Fusion to adaptively regulate the contributions of foreground and background features. In parallel, EEG signals are modeled as adaptive spatiotemporal brain networks whose functional connectivity dynamically reorganizes to capture neural responses to salient foregrounds. Experiments on zero-shot brain-to-image retrieval demonstrate that FSDBN achieves 69.0 percent top-1 accuracy and 92.2 percent top-5 accuracy, outperforming previous state-of-the-art methods. Code is available at https://github.com/LiuYiheng1/FSDBN-EEG.

Multimodal models such as CLIP learn a shared embedding space for cross-modal retrieval, but continual adaptation to sequentially arriving data can disrupt the cross-modal alignment acquired from earlier phases. Conventional continual-learning methods return a single checkpoint, which commits every retrieval direction to the same stability-plasticity trade-off. We propose AlphaWiSE, a post-hoc weight-space interpolation method that composes two frozen source checkpoints. For each aligned parameter tensor identified by its checkpoint key, AlphaWiSE fits one scalar interpolation coefficient shared by all tensor entries. The coefficients are fitted on a smaller exemplar memory and used to materialize one interpolated checkpoint. The deployed model has the same architecture and parameter count as either source checkpoint, which does not require additional inference time. Extensive experiments on audio-image-text retrieval show consistent improvements over strong continual-learning baselines across multiple retrieval directions and evaluation metrics.

Understanding music requires understanding localized relationships across data modalities, e.g., how time in performance audio maps onto position in a score image. Yet supervision for such local correspondences is difficult to obtain-in practice, we often only have access to coarser global supervision like paired segments of audio and images. To address this gap, we propose FuSiLi (Fused Sinkhorn-Localized Similarity), a similarity score for multimodal contrastive learning operating directly on local image patch and audio frame features via Sinkhorn-based soft alignment. We show that FuSiLi (i) effectively learns local relationships, (ii) requires only global supervision, and (iii) retains the global alignment capabilities of conventional contrastive approaches. We fine-tune pretrained CLIP and CLAP encoders on pairs of raw sheet music images and audio using a hybrid contrastive objective combining FuSiLi with conventional global similarity. We evaluate on cross-modal retrieval and frame-level alignment tasks against a range of global and local baselines, showing that our approach outperforms them on local alignment while remaining competitive on retrieval.

Sign Language Retrieval (SLRet) enables efficient access to sign language content but remains fragile in fine-grained scenarios where visually similar signs must be distinguished. We show that this limitation does not stem from model capacity, but from ineffective hard negative supervision. Specifically, we formulate fine-grained retrieval failures as a negative distribution mismatch: semantically distinct yet visually confusable signs are rarely treated as hard negatives, while existing text-based mining strategies fail to capture such visual ambiguity. To address this issue, we propose Sign-Aware Hard Negative Mining (SAN), which constructs hard negatives based on visual confusability in the sign embedding space rather than linguistic similarity. Experiments on PHOENIX-2014T demonstrate that SAN substantially improves fine-grained retrieval performance while preserving coarse-grained accuracy, highlighting the importance of aligning negative supervision with visual ambiguity in sign language retrieval.

Fully characterizing a crystalline material requires integrating heterogeneous data sources -- atomic structures, diffraction patterns, electronic density of states, and natural language -- each of which captures a different facet of the same physical object. In practice, however, these modalities are stored and analyzed in isolation, making it difficult to relate or query materials across representational boundaries. We present MatBind, a contrastive learning framework that aligns four materials modalities -- crystal structure, powder X-ray diffraction (pXRD) simulated from structures, density of states (DOS), and text -- into a unified embedding space using crystal structure as the central physical anchor. The framework induces alignment between modalities never explicitly paired during training, enabling emergent zero-shot cross-modal retrieval as a direct consequence of the shared representation. The learned embedding space organizes materials according to physically meaningful properties without explicit supervision, and retrieval performance improves systematically when modalities are combined at query time. These results demonstrate that treating heterogeneous materials data as complementary projections of a single physical reality, rather than as isolated data sources, is not a practical choice but is consistent with the underlying physics.

Images tell us what a scene looks like, but rarely what it would feel like to be there. While recent datasets pair visual scenes with electronic-nose measurements, aligning smell signals with images remains challenging because many olfactory cues arise from contextual environmental factors that are not directly visible in pixels. We introduce SCENT, a multimodal framework that uses language guidance as a semantic bridge between vision and olfaction. Our approach leverages Vision-Language Models (VLMs) to generate scene descriptors capturing objects, environmental context, and plausible ambient smell cues suggested by the visual scene. These descriptors provide semantic guidance for learning olfactory representations. We train a smell encoder that maps electronic-nose signals into a shared embedding space aligned with both visual and textual representations, and introduce a languageguided latent decomposition that separates object-specific odors from contextual environmental contributions. Experiments on the New York Smells dataset demonstrate that SCENT significantly improves crossmodal retrieval compared to vision-only baselines, achieving state-of-theart performance on smell-to-image and smell-to-text retrieval tasks. In addition, our framework produces interpretable olfactory representations that enable the disentanglement of complex smell mixtures. Our results reveal the importance of contextual semantic information for grounding olfactory perception in multimodal learning and pave the way for future research in this area.

We present VTMR, a two-stage framework for Video-To-Music Recommendation. In Stage1, VTMR aligns comprehensive video and music signals in a joint audio-visual-text representation space and efficiently retrieves semantically compatible candidates using coarse global embeddings. In Stage2, it reranks the retrieved candidates by attending to the temporal sequences of both video and music, thereby capturing fine-grained temporal correspondence. Evaluated on the video-to-music recommendation task, the multimodal retrieval stage improves R@10 from 14.2 to 15.9 and Median Rank from 75 to 58 over the strongest baseline; the temporal reranker further boosts R@10 to 18.3 and Median Rank to 46, demonstrating complementary gains from richer query encoding and temporal alignment. A human preference study confirms that VTMR is on par with a commercial baseline in overall preference, while outperforming a generative baseline in music quality.

Crossmodal correspondences between sound and taste are well established in psychology and neuroscience, but largely absent from content-based multimedia retrieval. We formalise taste-from-audio prediction as a content-based music information retrieval benchmark over a perceptually validated multi-source corpus, comparing ten frozen audio encoders from the four HEAR families under a shared multi-task regression head, with gated late-fusion as a configurable variant. In order to assess the effectiveness of the models, we compute absolute error and rank correlation. The strongest systems predict the five tastes within a macro RMSE of 0.134; on held-out real music their error is less than half a single rater's deviation from the consensus (RMSE 0.13 vs. 0.28), so the model tracks the group consensus more closely than an average human rater, and well below the previous state of the art baseline (0.219). On absolute error the encoders are statistically flat, with a single VGGish matching the best fusion, but gated late-fusion's advantage is confined to rank correlation (macro Pearson r 0.724 vs. 0.666). Operationalised as a content-based retrieval index, the predicted taste space ranks a 309-item pool far more faithfully than a CLAP-text baseline, which sits at chance; ridge probes and an audio-bandstop knockout read the strongest representations against documented sound-taste correspondences.

Unsupervised cross-modal hashing enables efficient retrieval of semantically related instances across different modalities without requiring manual semantic annotation. However, existing unsupervised methods rely heavily on large-scale image-text pairs. Collecting such data can be costly, particularly in scenarios where well-aligned pairs are scarce due to privacy and specialized constraints. More critically, existing methods tend to overfit to seen training data, restricting their generalization performance on unseen categories that the constrained training data cannot cover. To address these limitations, we propose Attribute-Prompted Kernel Hashing (APKH), a novel data-efficient approach that constructs a compact, modality-aligned Hamming space driven by the generalized attribute priors of vision-language foundation models. Specifically, APKH introduces two core modules: Context-optimized Attribute Kernel Mapping (CAKM) and Kernel-Smoothed Contrastive Alignment (KSCA). CAKM formulates cross-modal alignment through hyperspherical Radial Basis Function kernel mapping, optimizing dynamic attribute kernels via prompt learning to capture modality-invariant semantics. Furthermore, KSCA extends conventional point-to-point contrastive learning by modeling limited paired data as continuous kernel distributions. This explicit smoothing of the modality gap alleviates overfitting to sparse pairwise correlations. Extensive experiments demonstrate that APKH outperforms state-of-the-art hashing methods in the challenging cross-modal retrieval tasks from seen to unseen categories under data-constrained scenarios.

Compared to supervised cross-modal hashing (CMH), unsupervised CMH reduces the reliance on manual labeling by learning binary codes from unlabeled image-text pairs. However, existing unsupervised CMH methods often rely on large-scale image-text pairs, which are costly to collect. To address this limitation, we propose Global-Neighborhood Alignment Hashing (GNAH), a novel approach that preserves the semantic structure of vision-language foundation models within a compact binary Hamming space using only a limited number of image-text pairs. Specifically, GNAH captures global structural information from the continuous latent space and transfers it into the binary Hamming space through a Prototype-Anchored Global Alignment module. In addition, GNAH extends conventional pairwise contrastive learning by modeling stochastic neighborhood relationships via a Contrastive Stochastic Neighborhood Alignment module, thereby alleviating overfitting to sparse pairwise correlations. Extensive experiments demonstrate that GNAH consistently outperforms existing unsupervised cross-modal retrieval methods under data-constrained settings, offering a practical solution for real-world CMH applications.

Text-to-image person re-identification (TIPR) retrieves target persons using natural language descriptions. However, existing methods largely overlook resolution variance in real-world surveillance. They characterize cross-resolution TIPR through two coupled failure modes: Evidence Reliability Collapse (ERC), where degraded visual tokens become unreliable for grounding fine-grained text, and Ranking Distribution Drift (RDD), where mixed-resolution galleries distort similarity neighborhoods and destabilize retrieval rankings. To address this challenge, we propose Cross-Resolution Semantic Transfer (CRST), a CLIP-style framework with three modules: resolution-conditioned reasoning, text-guided refinement and CR-RDA. Resolution-conditioned reasoning estimates token reliability to suppress corrupted evidence. Text-guided refinement injects semantic priors to recover discriminative cues. CR-RDA transfers HR neighborhood geometry to stabilize LR ranking under mixed resolutions. Experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid show that CRST improves ultra-low-resolution Rank-1 and mAP on average by 5.7% and 5.3%, while stabilizing mixed-resolution retrieval without sacrificing high-resolution accuracy.The code will be made publicly available.

Multimodal foundation models have advanced rapidly thanks to large optical benchmarks, but comparable resources for synthetic aperture radar (SAR) remain limited. Existing SAR--optical datasets largely rely on low-resolution, intensity-only Ground Range Detected~(GRD) products and do not preserve complex-valued SAR measurements or native acquisition geometry, which restricts physically grounded multimodal learning. In particular, large-scale public datasets combining very-high-resolution (VHR) SAR SLC, aligned optical imagery, and natural-language descriptions are still lacking. We present a VHR SAR--optical--text dataset built from open-access Umbra spotlight acquisitions distributed as Sensor Independent Complex Data (SICD). From around 2,500 worldwide scenes (VV/HH, 20cm--2m native resolution), we standardize all SAR data to an 80cm slant-range grid via band-limited FFT resampling and tile the imagery into 1024 by 1024 patches. For each SAR patch, we retrieve a high-resolution optical tile and warp it into the SAR grid using local coordinate correspondences for local pixel-level alignment. We further generate three caption variants (SHORT/MID/LONG) per sample to support vision--language training and evaluation. Our dataset contains 119,566 triplets (complex and amplitude slant-range SAR patch, aligned optical patch, natural-language description) covering 257 locations across 72 countries and a broad range of land types and infrastructures. We release fixed train/validation/test splits and the full preprocessing and baseline code to enable reproducible benchmarks for multimodal alignment on cross-modal retrieval and conditional generation in native SAR geometry. The dataset is publicly available on the Hugging Face Hub at https://huggingface.co/datasets/ONERA/SARLO-80.

Leveraging Multimodal Large Language Models (MLLMs) via contrastive learning has become a mainstream paradigm for improving the performance of Universal Multimodal Retrieval (UMR). However, previous works have ignored the grain blindness when adapting the contrastive paradigm into retrieval tasks. Grain blindness refers to the tendency of the model to overlook grain-level information contained in the query, which is crucial for effectively handling complex queries. This stems from contrastive learning treating samples as a binary classification (positive/negative), while ignoring the different information carried by each negative sample. To address this, we argue that negatives should be treated differently according to their similarity to the positive sample, enabling the model to learn distinct grain information from each negative. In this paper, we introduce a simple but effective framework, called ELVA, a novel rule-based RL framework that mitigates grain blindness through ranking-driven MLLMs. 1) Instead of relying on reward models, we extend Reinforcement Learning with Verifiable Rewards (RLVR) to retrieval tasks, allowing the model to explore new ranking behaviors without explicit ranking labels. 2) By utilizing rule-based rewards, our approach jointly optimizes the ranking of negative samples while enlarging the similarity gap between positive and negative. To more precisely measure grain blindness, we further introduce MRBench, a new benchmark specifically designed for multi-grain query scenarios. ELVA achieves state-of-the-art results across standard retrieval benchmarks, and its notable 13.1% improvement on MRBench further demonstrates its effectiveness in alleviating grain blindness.

In today's media-driven world, the exponential growth of video content across domains such as surveillance, education, and entertainment has made retrieving semantically relevant videos via natural language queries increasingly critical. Early video retrieval systems relied on handcrafted features or shallow cross-modal mappings, limiting their ability to capture complex semantics and temporal dynamics. While large-scale vision-language models have improved cross-modal alignment, challenges remain in modeling fine-grained temporal dependencies and nuanced linguistic structures. In this paper, we introduce DREAM: Dual-path Representation Enhancement and Alignment Model, a novel multimodal framework that addresses these limitations through enhanced visual and textual encoding. DREAM incorporates a hybrid language modeling strategy that combines masked and permuted language modeling objectives to capture both local and global linguistic semantics. On the visual side, we design a hierarchical vision encoder with cascaded group attention, which integrates spatial and temporal information through multi-stage token interaction and coarse-to-fine attention refinement. We validate DREAM through comprehensive evaluations on the widely-used MSRVTT, MSVD and LSMDC benchmark datasets, where it achieves new state-of-the-art R1 scores of 49.4%, 49.7% and 27.3%, respectively. Qualitative analyses further show the model's ability to maintain coherent attention across frames and align complex queries with dynamic video content. These findings underscore the effectiveness of hierarchical attention and dual-objective textual modeling in enabling robust, context-aware video retrieval, and pave the way for future research in advancing cross-modal representation learning.

Omni-modal retrieval promises a single embedding space for text, image, video, document, and audio inputs, but building such a unified retriever is difficult since these modalities differ in data distribution, architecture, and optimization dynamics. In this work, we present Conan-embedding-v3, a decouple--fuse--recover framework for omni-modal retrieval. Conan-embedding-v3 first trains modality specialists independently and fuses their task vectors into a single dense backbone, a strategy we call Decoupled Specialist Fusion. We show that this fusion composes visual, video, and document retrieval capabilities, but also exposes a failure mode for projector-based modalities: when audio is attached through an external encoder and projector, fusing the backbone leaves the projector calibrated to the audio-specialist backbone, causing a large audio retrieval regression despite copying all audio-specific modules unchanged. We call this failure Projector Drift. To repair it, Conan-embedding-v3 applies Projector Recovery (i.e., full-parameter fine-tuning of the projector while keeping the backbone frozen) followed by balanced multi-modal rehearsal. The resulting model supports these retrieval pathways in one backbone, achieving 74.9 scores on MMEB while obtaining 55.61 on the 30-task MAEB audio suite.