arXiv subjects

Sajid Javed

Publications and source records attributed to Sajid Javed.

At least 19 recordsLinked to original sources

arXiv2026

CheXGround: Anatomical Region Tokens for Grounded Longitudinal Chest X-ray Interpretation

Recent radiology multi-modal language models have made substantial progress in chest X-ray report generation, visual question answering, and temporal reasoning. While longitudinal chest X-ray interpretation compares sequential examinations to describe change, visual grounding aims to connect clinical language with localized image evidence. Although longitudinal modeling and visual grounding have each advanced radiology language models, how localized visual evidence can support longitudinal interpretation remains under-explored. We introduce CheXGround, a region-grounded longitudinal chest X-ray language model that represents paired studies through corresponding anatomical regions. CheXGround extracts anatomical regions from current and prior radiographs, encodes them as temporally enhanced Region-of-Interest (ROI) tokens, and combines them with global temporal image context during generation. To connect these region tokens with clinical text, we propose Temporal Region--Phrase Alignment, a pretraining objective that aligns temporal anatomical representations with localized report phrases. We evaluate CheXGround on single-study and longitudinal Visual Question Answering (VQA), longitudinal findings generation, temporal grounded VQA, and anatomical grounding. Across these tasks, CheXGround improves clinical language quality, temporal reasoning, and localization accuracy over recent baselines. Our results suggest that organizing longitudinal evidence at the anatomical level is a strong representation for grounded radiology language modeling. Project page: https://adonaydem.github.io/chexground-website

cs.CV↗

arXiv2026

Uncertainty-Aware Decision Making in Multimodal Large Language Models

Multimodal large language models (MLLMs) increasingly answer questions whose correctness depends on visual, textual, temporal, acoustic, document, chart, or embodied evidence. Their failures are therefore not only linguistic. A fluent answer may conceal poor input quality, a perceptual error, weak grounding, conflict between modalities, unstable reasoning, distribution shift, or a question that is not answerable from the supplied evidence. This survey organizes the literature on uncertainty-aware MLLMs around a decision-centered framework: uncertainty sources give rise to observable signals, signals must be calibrated or controlled for risk, and calibrated uncertainty should determine the system action. We review work on token and logit uncertainty, semantic disagreement, perturbation instability, grounding and attribution scores, verbalized confidence, verifier and judge scores, conformal prediction, selective answering, abstention, clarification, retrieval, self-checking, and escalation. The central argument is that uncertainty should not be evaluated only as a confidence number; it should be evaluated by whether it improves behavior under insufficient, conflicting, shifted, or high-risk multimodal evidence. We position this survey against text-only uncertainty and abstention surveys, broad MLLM surveys, MLLM hallucination surveys, and safety-oriented reviews. We conclude with open problems in source-aware decomposition, action-aware benchmarks, calibration under shift, black-box uncertainty estimation, broader modality coverage, reproducible reporting, and human-centered uncertainty communication.

cs.CL↗

arXiv2026

From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology

Vision Transformers (ViTs) and their hierarchical variants have achieved strong performance in Computational Pathology (CPath). However, most are pre-trained on single-resolution Whole Slide Images (WSIs), limiting their generalization across arbitrary resolutions. Gigapixel WSIs inherently contain diagnostic patterns at multiple scales, including cellular morphologies, tissue architectures, and global context, mirroring how expert pathologists examine WSIs. We introduce Multi-Resolution Pyramid Transformer (MRPT), a model that hierarchically aggregates multi-resolution information from cellular to tissue and WSI levels. MRPT employs a biologically meaningful Consecutive Cross-Resolution Attention (CCRA) mechanism to capture scale-independent interactions and enforces multi-resolution semantic consistency by aligning embeddings across resolutions, yielding robust and generalizable WSI representations. Pre-trained in a multi-resolution self-supervised manner on 624M patches, 2.4M regions, and 36K WSIs, MRPT learns rich coarse-to-fine histopathology features. Extensive experiments on 34 diverse datasets show that MRPT surpasses recent foundation models and Multimodal Large Language Models (MLLMs) in cancer subtype classification, tissue phenotyping, and Visual Question Answering (VQA) for WSI understanding.

cs.CV↗

arXiv2026

SENTRY: SAM2-Enhanced Neighbor-Aware and Temporally Reasoned Memory for Visual Tracking

We revisit the memory update mechanism in SAM2-based visual object tracking and identify confidence-only mask selection as the dominant cause of drift under occlusion, rapid motion, and distractors. We introduce SENTRY, a training-free, plug-and-play, refine-before-write module that validates each memory update for short-horizon temporal consistency before committing it. SENTRY aggregates diverse segmentation hypotheses per frame, backtracks them into short tracklets, and uses neighbor-aware cycle-consistent matching against recent trajectories to favor temporally and geometrically consistent masks. It leaves the base architecture untouched, replacing confidence-driven writes with consistency-validated ones. For fair evaluation, we re-evaluate major open-source SAM2-based trackers across all available scales and datasets, filling gaps in prior reports. Integrated into five strong baselines, SENTRY delivers consistent gains across nine benchmarks, achieving new zero-shot SOTA on LaSOT, LaSOT_ext, GOT-10k, VOT20, VOT22, and DiDi. Despite these checks, the SAM2-L version runs at 32.8 FPS on an A100, and across compatible hosts adds only about 0.4--0.6 GB VRAM. Our results provide the first unified all-scale evaluation of SAM2-based trackers and show that enforcing temporal validity at write time stabilizes memory-augmented tracking without retraining. Project page: https://hamadya.github.io/SENTRY/page/

cs.CV↗

arXiv2026

SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation

Open-vocabulary segmentation models such as SAM3 perform well across broad categories via text prompting, yet degrade when target classes are visually underrepresented in pretraining or depart from canonical depictions-limitations text prompts cannot resolve spatially. We present SegRAG, a training-free retrieval-augmented segmentation framework that grounds SAM3 with class-specific point prompts derived from a curated DINOv3 feature bank. Offline, dense patch-level descriptors are extracted from annotated references and filtered by Intra-Class Cohesion Distillation (ICCD), retaining only prototypes that reliably retrieve within-class foreground. At inference, Topographic Similarity Grounding (TSG) computes a cosine-similarity landscape against retrieved prototypes, identifies coherent high-confidence regions via connected-component analysis, and extracts peak locations through non-maximum suppression. The resulting point prompts are delivered jointly with class-name text in a single SAM3 forward pass. On four standard benchmarks, SegRAG consistently outperforms the text-only baseline, gaining up to +3.92 mIoU on LVIS. On AgML agricultural benchmarks under zero-shot domain transfer, it raises mean IoU from 25.27 to 59.24 (+33.97) and recovers individual classes from zero to over 95 mIoU. Ablations confirm that ICCD, TSG, and joint prompting each contribute independently and compound when combined. Code is available at (https://github.com/boudiafA/SegRAG).

cs.CV↗

arXiv2026

MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding

Whole Slide Images (WSIs) exhibit hierarchical structure, where diagnostic information emerges from cellular morphology, regional tissue organization, and global context. Existing Computational Pathology (CPath) Multimodal Large Language Models (MLLMs) typically compress an entire WSI into a single embedding, which hinders fine-grained grounding and ignores how pathologists synthesize evidence across different scales. We introduce \textbf{MLLM-HWSI}, a Hierarchical WSI-level MLLM that aligns visual features with pathology language at four distinct scales, cell as word, patch as phrase, region as sentence, and WSI as paragraph to support interpretable evidence-grounded reasoning. MLLM-HWSI decomposes each WSI into multi-scale embeddings with scale-specific projectors and jointly enforces (i) a hierarchical contrastive objective and (ii) a cross-scale consistency loss, preserving semantic coherence from cells to the WSI. We compute diagnostically relevant patches and aggregate segmented cell embeddings into a compact cellular token per-patch using a lightweight \textit{Cell-Cell Attention Fusion (CCAF)} transformer. The projected multi-scale tokens are fused with text tokens and fed to an instruction-tuned LLM for open-ended reasoning, VQA, report, and caption generation tasks. Trained in three stages, MLLM-HWSI achieves new SOTA results on 13 WSI-level benchmarks across six CPath tasks. By aligning language with multi-scale visual evidence, MLLM-HWSI provides accurate, interpretable outputs that mirror diagnostic workflows and advance holistic WSI understanding. Code is available at: \href{https://github.com/BasitAlawode/HWSI-MLLM}{GitHub}.

cs.CV↗

arXiv2026

AgriChat: A Multimodal Large Language Model for Agriculture Image Understanding

The deployment of Multimodal Large Language Models (MLLMs) in agriculture is currently stalled by a critical trade-off: the existing literature lacks the large-scale agricultural datasets required for robust model development and evaluation, while current state-of-the-art models lack the verified domain expertise necessary to reason across diverse taxonomies. To address these challenges, we propose the Vision-to-Verified-Knowledge (V2VK) pipeline, a novel generative AI-driven annotation framework that integrates visual captioning with web-augmented scientific retrieval to autonomously generate the AgriMM benchmark, effectively eliminating biological hallucinations by grounding training data in verified phytopathological literature. The AgriMM benchmark contains over 3,000 agricultural classes and more than 607k VQAs spanning multiple tasks, including fine-grained plant species identification, plant disease symptom recognition, crop counting, and ripeness assessment. Leveraging this verifiable data, we present AgriChat, a specialized MLLM that presents broad knowledge across thousands of agricultural classes and provides detailed agricultural assessments with extensive explanations. Extensive evaluation across diverse tasks, datasets, and evaluation conditions reveals both the capabilities and limitations of current agricultural MLLMs, while demonstrating AgriChat's superior performance over other open-source models, including internal and external benchmarks. The results validate that preserving visual detail combined with web-verified knowledge constitutes a reliable pathway toward robust and trustworthy agricultural AI. The code and dataset are publicly available at https://github.com/boudiafA/AgriChat .

cs.CV↗

arXiv2026

SPARROW: Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded Video MLLMs

Multimodal large language models (MLLMs) have advanced from image-level reasoning to pixel-level grounding, but extending these capabilities to videos remains challenging as models must achieve spatial precision and temporally consistent reference tracking. Existing video MLLMs often rely on a static segmentation token ([SEG]) for frame-wise grounding, which provides semantics but lacks temporal context, causing spatial drift, identity switches, and unstable initialization when objects move or reappear. We introduce SPARROW, a pixel-grounded video MLLM that unifies spatial accuracy and temporal stability through two key components: (i) Target-Specific Tracked Features (TSF), which inject temporally aligned referent cues during training, and (ii) a dual-prompt design that decodes box ([BOX]) and segmentation ([SEG]) tokens to fuse geometric priors with semantic grounding. SPARROW is supported by a curated referential video dataset of 30,646 videos and 45,231 Q&A pairs and operates end-to-end without external detectors via a class-agnostic SAM2-based proposer. Integrated into three recent open-source video MLLMs (UniPixel, GLUS, and VideoGLaMM), SPARROW delivers consistent gains across six benchmarks, improving up to +8.9 J&F on RVOS, +5 mIoU on visual grounding, and +5.4 CLAIR on GCG. These results demonstrate that SPARROW substantially improves referential stability, spatial precision, and temporal coherence in pixel-grounded video understanding. Project page: https://risys-lab.github.io/SPARROW

cs.CV↗

arXiv2026

MUOT_3M: A 3 Million Frame Multimodal Underwater Benchmark and the MUTrack Tracking Method

Underwater Object Tracking (UOT) is crucial for efficient marine robotics, large scale ecological monitoring, and ocean exploration; however, progress has been hindered by the scarcity of large, multimodal, and diverse datasets. Existing benchmarks remain small and RGB only, limiting robustness under severe color distortion, turbidity, and low visibility conditions. We introduce MUOT_3M, the first pseudo multimodal UOT benchmark comprising 3 million frames from 3,030 videos (27.8h) annotated with 32 tracking attributes, 677 fine grained classes, and synchronized RGB, estimated enhanced RGB, estimated depth, and language modalities validated by a marine biologist. Building upon MUOT_3M, we propose MUTrack, a SAM-based multimodal to unimodal tracker featuring visual geometric alignment, vision language fusion, and four level knowledge distillation that transfers multimodal knowledge into a unimodal student model. Extensive evaluations across five UOT benchmarks demonstrate that MUTrack achieves up to 8.40% higher AUC and 7.80% higher precision than the strongest SOTA baselines while running at 24 FPS. MUOT_3M and MUTrack establish a new foundation for scalable, multimodally trained yet practically deployable underwater tracking.

cs.CV↗

arXiv2025

Rethinking Memory Design in SAM-Based Visual Object Tracking

\noindent Memory has become the central mechanism enabling robust visual object tracking in modern segmentation-based frameworks. Recent methods built upon Segment Anything Model 2 (SAM2) have demonstrated strong performance by refining how past observations are stored and reused. However, existing approaches address memory limitations in a method-specific manner, leaving the broader design principles of memory in SAM-based tracking poorly understood. Moreover, it remains unclear how these memory mechanisms transfer to stronger, next-generation foundation models such as Segment Anything Model 3 (SAM3). In this work, we present a systematic memory-centric study of SAM-based visual object tracking. We first analyze representative SAM2-based trackers and show that most methods primarily differ in how short-term memory frames are selected, while sharing a common object-centric representation. Building on this insight, we faithfully reimplement these memory mechanisms within the SAM3 framework and conduct large-scale evaluations across ten diverse benchmarks, enabling a controlled analysis of memory design independent of backbone strength. Guided by our empirical findings, we propose a unified hybrid memory framework that explicitly decomposes memory into short-term appearance memory and long-term distractor-resolving memory. This decomposition enables the integration of existing memory policies in a modular and principled manner. Extensive experiments demonstrate that the proposed framework consistently improves robustness under long-term occlusion, complex motion, and distractor-heavy scenarios on both SAM2 and SAM3 backbones. Code is available at: https://github.com/HamadYA/SAM3_Tracking_Zoo. \textbf{This is a preprint. Some results are being finalized and may be updated in a future revision.}

cs.CV↗

arXiv2025

Cytoplasmic Strings Analysis in Human Embryo Time-Lapse Videos using Deep Learning Framework

Infertility is a major global health issue, and while in-vitro fertilization has improved treatment outcomes, embryo selection remains a critical bottleneck. Time-lapse imaging enables continuous, non-invasive monitoring of embryo development, yet most automated assessment methods rely solely on conventional morphokinetic features and overlook emerging biomarkers. Cytoplasmic Strings, thin filamentous structures connecting the inner cell mass and trophectoderm in expanded blastocysts, have been associated with faster blastocyst formation, higher blastocyst grades, and improved viability. However, CS assessment currently depends on manual visual inspection, which is labor-intensive, subjective, and severely affected by detection and subtle visual appearance. In this work, we present, to the best of our knowledge, the first computational framework for CS analysis in human IVF embryos. We first design a human-in-the-loop annotation pipeline to curate a biologically validated CS dataset from TLI videos, comprising 13,568 frames with highly sparse CS-positive instances. Building on this dataset, we propose a two-stage deep learning framework that (i) classifies CS presence at the frame level and (ii) localizes CS regions in positive cases. To address severe imbalance and feature uncertainty, we introduce the Novel Uncertainty-aware Contractive Embedding (NUCE) loss, which couples confidence-aware reweighting with an embedding contraction term to form compact, well-separated class clusters. NUCE consistently improves F1-score across five transformer backbones, while RF-DETR-based localization achieves state-of-the-art (SOTA) detection performance for thin, low-contrast CS structures. The source code will be made publicly available at: https://github.com/HamadYA/CS_Detection.

cs.CV↗

arXiv2025

Spatio-Temporal State Space Model For Efficient Event-Based Optical Flow

Event cameras unlock new frontiers that were previously unthinkable with standard frame-based cameras. One notable example is low-latency motion estimation (optical flow), which is critical for many real-time applications. In such applications, the computational efficiency of algorithms is paramount. Although recent deep learning paradigms such as CNN, RNN, or ViT have shown remarkable performance, they often lack the desired computational efficiency. Conversely, asynchronous event-based methods including SNNs and GNNs are computationally efficient; however, these approaches fail to capture sufficient spatio-temporal information, a powerful feature required to achieve better performance for optical flow estimation. In this work, we introduce Spatio-Temporal State Space Model (STSSM) module along with a novel network architecture to develop an extremely efficient solution with competitive performance. Our STSSM module leverages state-space models to effectively capture spatio-temporal correlations in event data, offering higher performance with lower complexity compared to ViT, CNN-based architectures in similar settings. Our model achieves 4.5x faster inference and 8x lower computations compared to TMA and 2x lower computations compared to EV-FlowNet with competitive performance on the DSEC benchmark. Our code will be available at https://github.com/AhmedHumais/E-STMFlow

cs.CV↗

arXiv2025

MVTD: A Benchmark Dataset for Maritime Visual Object Tracking

Visual Object Tracking (VOT) is a fundamental task with widespread applications in autonomous navigation, surveillance, and maritime robotics. Despite significant advances in generic object tracking, maritime environments continue to present unique challenges, including specular water reflections, low-contrast targets, dynamically changing backgrounds, and frequent occlusions. These complexities significantly degrade the performance of state-of-the-art tracking algorithms, highlighting the need for domain-specific datasets. To address this gap, we introduce the Maritime Visual Tracking Dataset (MVTD), a comprehensive and publicly available benchmark specifically designed for maritime VOT. MVTD comprises 182 high-resolution video sequences, totaling approximately 150,000 frames, and includes four representative object classes: boat, ship, sailboat, and unmanned surface vehicle (USV). The dataset captures a diverse range of operational conditions and maritime scenarios, reflecting the real-world complexities of maritime environments. We evaluated 14 recent SOTA tracking algorithms on the MVTD benchmark and observed substantial performance degradation compared to their performance on general-purpose datasets. However, when fine-tuned on MVTD, these models demonstrate significant performance gains, underscoring the effectiveness of domain adaptation and the importance of transfer learning in specialized tracking contexts. The MVTD dataset fills a critical gap in the visual tracking community by providing a realistic and challenging benchmark for maritime scenarios. Dataset and Source Code can be accessed here "https://github.com/AhsanBaidar/MVTD".

cs.CV↗

arXiv2025

CLDTracker: A Comprehensive Language Description for Visual Tracking

VOT remains a fundamental yet challenging task in computer vision due to dynamic appearance changes, occlusions, and background clutter. Traditional trackers, relying primarily on visual cues, often struggle in such complex scenarios. Recent advancements in VLMs have shown promise in semantic understanding for tasks like open-vocabulary detection and image captioning, suggesting their potential for VOT. However, the direct application of VLMs to VOT is hindered by critical limitations: the absence of a rich and comprehensive textual representation that semantically captures the target object's nuances, limiting the effective use of language information; inefficient fusion mechanisms that fail to optimally integrate visual and textual features, preventing a holistic understanding of the target; and a lack of temporal modeling of the target's evolving appearance in the language domain, leading to a disconnect between the initial description and the object's subsequent visual changes. To bridge these gaps and unlock the full potential of VLMs for VOT, we propose CLDTracker, a novel Comprehensive Language Description framework for robust visual Tracking. Our tracker introduces a dual-branch architecture consisting of a textual and a visual branch. In the textual branch, we construct a rich bag of textual descriptions derived by harnessing the powerful VLMs such as CLIP and GPT-4V, enriched with semantic and contextual cues to address the lack of rich textual representation. Experiments on six standard VOT benchmarks demonstrate that CLDTracker achieves SOTA performance, validating the effectiveness of leveraging robust and temporally-adaptive vision-language representations for tracking. Code and models are publicly available at: https://github.com/HamadYA/CLDTracker

cs.CV↗

arXiv2025

Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation

In Computational Pathology (CPath), the introduction of Vision-Language Models (VLMs) has opened new avenues for research, focusing primarily on aligning image-text pairs at a single magnification level. However, this approach might not be sufficient for tasks like cancer subtype classification, tissue phenotyping, and survival analysis due to the limited level of detail that a single-resolution image can provide. Addressing this, we propose a novel multi-resolution paradigm leveraging Whole Slide Images (WSIs) to extract histology patches at multiple resolutions and generate corresponding textual descriptions through advanced CPath VLM. We introduce visual-textual alignment at multiple resolutions as well as cross-resolution alignment to establish more effective text-guided visual representations. Cross-resolution alignment using a multimodal encoder enhances the model's ability to capture context from multiple resolutions in histology images. Our model aims to capture a broader range of information, supported by novel loss functions, enriches feature representation, improves discriminative ability, and enhances generalization across different resolutions. Pre-trained on a comprehensive TCGA dataset with 34 million image-language pairs at various resolutions, our fine-tuned model outperforms state-of-the-art (SOTA) counterparts across multiple datasets and tasks, demonstrating its effectiveness in CPath. The code is available on GitHub at: https://github.com/BasitAlawode/MR-PLIP

cs.CV↗

arXiv2025

snnTrans-DHZ: A Lightweight Spiking Neural Network Architecture for Underwater Image Dehazing

Underwater image dehazing is critical for vision-based marine operations because light scattering and absorption can severely reduce visibility. This paper introduces snnTrans-DHZ, a lightweight Spiking Neural Network (SNN) specifically designed for underwater dehazing. By leveraging the temporal dynamics of SNNs, snnTrans-DHZ efficiently processes time-dependent raw image sequences while maintaining low power consumption. Static underwater images are first converted into time-dependent sequences by repeatedly inputting the same image over user-defined timesteps. These RGB sequences are then transformed into LAB color space representations and processed concurrently. The architecture features three key modules: (i) a K estimator that extracts features from multiple color space representations; (ii) a Background Light Estimator that jointly infers the background light component from the RGB-LAB images; and (iii) a soft image reconstruction module that produces haze-free, visibility-enhanced outputs. The snnTrans-DHZ model is directly trained using a surrogate gradient-based backpropagation through time (BPTT) strategy alongside a novel combined loss function. Evaluated on the UIEB benchmark, snnTrans-DHZ achieves a PSNR of 21.68 dB and an SSIM of 0.8795, and on the EUVP dataset, it yields a PSNR of 23.46 dB and an SSIM of 0.8439. With only 0.5670 million network parameters, and requiring just 7.42 GSOPs and 0.0151 J of energy, the algorithm significantly outperforms existing state-of-the-art methods in terms of efficiency. These features make snnTrans-DHZ highly suitable for deployment in underwater robotics, marine exploration, and environmental monitoring.

cs.CV↗

arXiv2025

Underwater Image Enhancement by Convolutional Spiking Neural Networks

Underwater image enhancement (UIE) is fundamental for marine applications, including autonomous vision-based navigation. Deep learning methods using convolutional neural networks (CNN) and vision transformers advanced UIE performance. Recently, spiking neural networks (SNN) have gained attention for their lightweight design, energy efficiency, and scalability. This paper introduces UIE-SNN, the first SNN-based UIE algorithm to improve visibility of underwater images. UIE-SNN is a 19- layered convolutional spiking encoder-decoder framework with skip connections, directly trained using surrogate gradient-based backpropagation through time (BPTT) strategy. We explore and validate the influence of training datasets on energy reduction, a unique advantage of UIE-SNN architecture, in contrast to the conventional learning-based architectures, where energy consumption is model-dependent. UIE-SNN optimizes the loss function in latent space representation to reconstruct clear underwater images. Our algorithm performs on par with its non-spiking counterpart methods in terms of PSNR and structural similarity index (SSIM) at reduced timesteps ($T=5$) and energy consumption of $85\%$. The algorithm is trained on two publicly available benchmark datasets, UIEB and EUVP, and tested on unseen images from UIEB, EUVP, LSUI, U45, and our custom UIE dataset. The UIE-SNN algorithm achieves PSNR of $17.7801~dB$ and SSIM of $0.7454$ on UIEB, and PSNR of $23.1725~dB$ and SSIM of $0.7890$ on EUVP. UIE-SNN achieves this algorithmic performance with fewer operators ($147.49$ GSOPs) and energy ($0.1327~J$) compared to its non-spiking counterpart (GFLOPs = $218.88$ and Energy=$1.0068~J$). Compared with existing SOTA UIE methods, UIE-SNN achieves an average of $6.5\times$ improvement in energy efficiency. The source code is available at \href{https://github.com/vidya-rejul/UIE-SNN.git}{UIE-SNN}.

eess.IV↗

arXiv2025

AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis

The preservation of aquatic biodiversity is critical in mitigating the effects of climate change. Aquatic scene understanding plays a pivotal role in aiding marine scientists in their decision-making processes. In this paper, we introduce AquaticCLIP, a novel contrastive language-image pre-training model tailored for aquatic scene understanding. AquaticCLIP presents a new unsupervised learning framework that aligns images and texts in aquatic environments, enabling tasks such as segmentation, classification, detection, and object counting. By leveraging our large-scale underwater image-text paired dataset without the need for ground-truth annotations, our model enriches existing vision-language models in the aquatic domain. For this purpose, we construct a 2 million underwater image-text paired dataset using heterogeneous resources, including YouTube, Netflix, NatGeo, etc. To fine-tune AquaticCLIP, we propose a prompt-guided vision encoder that progressively aggregates patch features via learnable prompts, while a vision-guided mechanism enhances the language encoder by incorporating visual context. The model is optimized through a contrastive pretraining loss to align visual and textual modalities. AquaticCLIP achieves notable performance improvements in zero-shot settings across multiple underwater computer vision tasks, outperforming existing methods in both robustness and interpretability. Our model sets a new benchmark for vision-language applications in underwater environments. The code and dataset for AquaticCLIP are publicly available on GitHub at xxx.

cs.CV↗