arXiv subjects

Ardhendu Behera

Publications and source records attributed to Ardhendu Behera.

At least 19 recordsLinked to original sources

arXiv2026

Fine-Grained Action Recognition with Cross-Attentive Latent Sparse Experts

Fine-grained human action recognition (FHAR) must distinguish visually similar actions that differ mainly in body configuration, timing, or local appearance. RGB representations retain visual context but often suppress joint-level geometry, whereas skeleton representations encode kinematics but discard dense spatial detail. We introduce FineX, which factorizes fine-grained cues into RGB appearance, pose heatmap geometry, and skeletal-graph topology. Pairwise cross-attention enables symmetric, stream-preserving information exchange, followed by a streamwise latent sparse Mixture-of-Experts that routes each representation to a content-dependent subset of shared experts, regularized by a load-balancing objective. FineX achieves state-of-the-art results on Gym99, Gym288, and Diving48. On the long-tailed Gym288, it raises mean class accuracy from 68.6% to 76.2% (+7.6 points) without textual supervision or large-scale vision-language pre-training, demonstrating the benefit of structured visual-pose-graph fusion and conditional expert refinement for FHAR.

cs.CV↗

arXiv2026

Language-Structured Relational Q-Learning for Threat-Aware Control in Safety-Critical Driving

Natural-language-based scenario generation offers an intuitive means of describing rare and complex driving interactions, yet it is still uncertain whether training with language-structured data leads to truly adaptive control policies. We propose Language-Structured Relational Q-Learning, instantiated through an Ego-Centric Relational Q-Network (ERQ-Net), which jointly learns inter-vehicle relevance and action values from dynamic traffic graphs. Language descriptions define surrounding-vehicle behaviours during training, while prompts and semantic actor roles are hidden from the policy. ERQ-Net must therefore infer threat relevance solely from observable kinematics and interactions. Across 2,500 safety-critical scenarios, language-structured training improves test success from 49-52% to 55-58% and increases adversary-focused attention from 1.2x to 2.1x, demonstrating emergent threat awareness. However, this representational gain does not consistently translate into adaptive control: trained policies perform similarly to the best constant action, while a portfolio of simple policies solves 76% of scenarios. We formalise this discrepancy as a recognition-control gap and show that reward reweighting and margin shaping do not eliminate the resulting policy collapse. Evaluations of realism, criticality, semantic accuracy, and transfer of state-interface representations to CARLA further highlight both the strengths and the constraints of language-structured relational policy learning in safety-critical driving scenarios.

cs.CV↗

arXiv2026

Geometry-Aware Superpixel Graph Transformer with Metadata for Skin Lesion Classification

Automated skin cancer classification from dermoscopic images remains challenging due to heterogeneous lesion structure, strong intra-class variability, and subtle visual differences between benign and malignant cases. Existing CNN/ViT pipelines typically rely on global or patch-level features and often combine patient metadata via late fusion, which limits spatially grounded multimodal reasoning. We present a novel region-based graph learning framework that explicitly models lesions as graphs of spatially coherent superpixel regions represented as frozen CNN features. To capture fine-grained lesion arrangements, we encode inter-regional geometry as edge attributes and introduce a dedicated metadata context node connected to all regions, providing structured integration of demographic/clinical variables within the same relational space. Node representations are updated using our edge-aware graph transformer followed by attention-driven propagation, and a final graph-level embedding for benign-malignant classification. Experiments on four public benchmarks demonstrate that explicit region-level relational modeling and graph-native multimodal fusion yield consistent gains over the state-of-the-art. Consequently, we establish a new graph-centric perspective in which CNN features are modeled as relational nodes and improved through contextual integration, yielding more expressive and robust classifications.

cs.CV↗

arXiv2026

ATRACT: A Trustworthy Robotic Autonomous system to support Casualty Triage

At a time when drones are increasingly associated with hostile operations, we re-purpose them for humanitarian and life-saving applications. However, adapting search and rescue drones for battlefield triage remains extremely challenging; the technology must perform reliably to support frontline medics who are forced to operate under extreme uncertainty, restricted access, and significant personal risk. Due to growing vulnerabilities of casualty evacuation in conflicting zones, this paper presents ATRACT (A Trustworthy Robotic Autonomous system to support Casualty Triage), a novel human-in-the-loop decision support system to enable early battlefield triage during the critical post-trauma period. ATRACT integrates drone-captured video with wearable sensor input for multi-modal learning to support casualty-state assessment, thereby addressing the limitations of existing systems. Drone video captures fine-grained behavioural cues, such as pose, posture, while body-worn sensors provide complementary physiological signals, including heart rate, breathing rate, and movement. By combining two modalities, ATRACT provides evidence to support the early judgement of medics when direct access to the casualty is delayed, risky, or restricted. To mitigate the data realism gap pertaining to injured actions, a conditional variational autoencoder is devised for data augmentation. Experimental results on our drone captured dataset show that proposed pipeline achieves 85.7% accuracy for action classification; while our lightweight CNN visual encoder remains competitive with stronger pre-trained video backbones. Overall, the results support ATRACT as a practically meaningful step towards remote triage in contested environments, where multi-modal sensing, human oversight and trustworthy decision support can improve casualty prioritisation, and lessen the exposure of frontline medics.

cs.HC↗

arXiv2026

Towards Label-Free Single-Cell Phenotyping Using Multi-Task Learning

Label-free single-cell imaging offers a scalable, non-invasive alternative to fluorescence-based cytometry, yet inferring molecular phenotypes directly from bright-field morphology remains challenging. We present a unified Deep Learning (DL) framework that jointly performs White Blood Cell (WBC) classification and continuous protein-expression regression from label-free Differential Phase Contrast (DPC) images. Our model employs a Hybrid architecture that fuses convolutional fine-grained texture features with transformer-based global representations through a learnable cross-branch gating module, enabling robust morpho-molecular inference from DPC images. To support downstream interpretability, we further incorporate a Large Language Model (LLM) that generates concise, biologically grounded summaries of the predicted cell states. Experiments on the Berkeley Single Cell Computational Microscopy (BSCCM) and Blood Cells Image benchmarks demonstrate strong performance, achieving a 91.3% WBC classification accuracy and a 0.72 Pearson correlation for CD16 expression regression on BSCCM. These results underscore the promise of label-free single-cell imaging for cost-effective hematological profiling, enabling simultaneous phenotype identification and quantitative biomarker estimation without fluorescent staining. The source code is available at https://github.com/saqibnaziir/Single-Cell-Phenotyping.

cs.CV↗

arXiv2026

TAG-Head: Time-Aligned Graph Head for Plug-and-Play Fine-grained Action Recognition

Fine-grained human action recognition (FHAR) is challenging because visually similar actions differ by subtle spatio-temporal cues. Many recent systems enhance discriminability with extra modalities (e.g., pose, text, optical flow), but this increases annotation burden and computational cost. We introduce TAG-Head, a lightweight spatio-temporal graph head that upgrades standard 3D backbones (SlowFast, R(2+1)D-34, I3D, etc.) for FHAR using RGB only. Our pipeline first applies a Transformer encoder with learnable 3D positional encodings to the backbone tokens, capturing long-range dependencies across space and time. The resulting features are then refined by a graph in which (i) fully-connected intra-frame edges to resolve subtle appearance differences within frames, and (ii) time-aligned temporal edges that connect features at the same spatial location across frames to stabilise motion cues without over-smoothing. The head is compact (little parameter/FLOP overhead), plug-and-play across backbones, and trained end-to-end with the backbone. Extensive evaluations on FineGym (Gym99 and Gym288) and HAA500 show that TAG-Head sets a new state-of-the-art among RGB-only models and surpasses many recent multimodal approaches (video + pose + text) that rely on privileged information. Ablations disentangle the contributions of the Transformer and the graph topology, and complexity analyses confirm low latency. TAG-Head advances FHAR by explicitly coupling global context with high-resolution spatial interactions and low-variance temporal continuity inside a slim, composable graph head. The simplicity of the design enables straightforward adoption in practical systems that favour RGB-only sensors, while delivering performance gains typically associated with heavier or multimodal models. Code will be released on GitHub.

cs.CV↗

arXiv2026

HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology

Immunohistochemistry (IHC) is essential for assessing specific immune biomarkers like Human Epidermal growth-factor Receptor 2 (HER2) in breast cancer. However, the traditional protocols of obtaining IHC stains are resource-intensive, time-consuming, and prone to structural damages. Virtual staining has emerged as a scalable alternative, but it faces significant challenges in preserving fine-grained cellular structures while accurately translating biochemical expressions. Current state-of-the-art methods still rely on Generative Adversarial Networks (GANs) or standard convolutional U-Net diffusion models that often struggle with "structure and staining trade-offs". The generated samples are either structurally relevant but blurry, or texturally realistic but have artifacts that compromise their diagnostic use. In this paper, we introduce HistDiT, a novel latent conditional Diffusion Transformer (DiT) architecture that establishes a new benchmark for visual fidelity in virtual histological staining. The novelty introduced in this work is, a) the Dual-Stream Conditioning strategy that explicitly maintains a balance between spatial constraints via VAE-encoded latents and semantic phenotype guidance via UNI embeddings; b) the multi-objective loss function that contributes to sharper images with clear morphological structure; and c) the use of the Structural Correlation Metric (SCM) to focus on the core morphological structure for precise assessment of sample quality. Consequently, our model outperforms existing baselines, as demonstrated through rigorous quantitative and qualitative evaluations.

eess.IV↗

arXiv2026

Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters

Recent adapter-based CLIP tuning (e.g., Tip-Adapter) is a strong few-shot learner, achieving efficiency by caching support features for fast prototype matching. However, these methods rely on global uni-modal feature vectors, overlooking fine-grained patch relations and their structural alignment with class text. To bridge this gap without incurring inference costs, we introduce a novel asymmetric training-only framework. Instead of altering the lightweight adapter, we construct a high-capacity auxiliary Heterogeneous Graph Teacher that operates solely during training. This teacher (i) integrates multi-scale visual patches and text prompts into a unified graph, (ii) performs deep cross-modal reasoning via a Modality-aware Graph Transformer (MGT), and (iii) applies discriminative node filtering to extract high-fidelity class features. Crucially, we employ a cache-aware dual-objective strategy to supervise this relational knowledge directly into the Tip-Adapter's key-value cache, effectively upgrading the prototypes while the graph teacher is discarded at test time. Thus, inference remains identical to Tip-Adapter with zero extra latency or memory. Across standard 1-16-shot benchmarks, our method consistently establishes a new state-of-the-art. Ablations confirm that the auxiliary graph supervision, text-guided reasoning, and node filtering are the essential ingredients for robust few-shot adaptation. Code is available at https://github.com/MR-Sherif/TOGA.git.

cs.CV↗

arXiv2025

Advancing Cache-Based Few-Shot Classification via Patch-Driven Relational Gated Graph Attention

Few-shot image classification remains difficult under limited supervision and visual domain shift. Recent cache-based adaptation approaches (e.g., Tip-Adapter) address this challenge to some extent by learning lightweight residual adapters over frozen features, yet they still inherit CLIP's tendency to encode global, general-purpose representations that are not optimally discriminative to adapt the generalist to the specialist's domain in low-data regimes. We address this limitation with a novel patch-driven relational refinement that learns cache adapter weights from intra-image patch dependencies rather than treating an image embedding as a monolithic vector. Specifically, we introduce a relational gated graph attention network that constructs a patch graph and performs edge-aware attention to emphasize informative inter-patch interactions, producing context-enriched patch embeddings. A learnable multi-aggregation pooling then composes these into compact, task-discriminative representations that better align cache keys with the target few-shot classes. Crucially, the proposed graph refinement is used only during training to distil relational structure into the cache, incurring no additional inference cost beyond standard cache lookup. Final predictions are obtained by a residual fusion of cache similarity scores with CLIP zero-shot logits. Extensive evaluations on 11 benchmarks show consistent gains over state-of-the-art CLIP adapter and cache-based baselines while preserving zero-shot efficiency. We further validate battlefield relevance by introducing an Injured vs. Uninjured Soldier dataset for casualty recognition. It is motivated by the operational need to support triage decisions within the "platinum minutes" and the broader "golden hour" window in time-critical UAV-driven search-and-rescue and combat casualty care.

cs.CV↗

arXiv2025

Deep Multi-modal Breast Cancer Detection Network

Automated breast cancer detection via computer vision techniques is challenging due to the complex nature of breast tissue, the subtle appearance of cancerous lesions, and variations in breast density. Mainstream techniques primarily focus on visual cues, overlooking complementary patient-specific textual features that are equally important and can enhance diagnostic accuracy. To address this gap, we introduce Multi-modal Cancer Detection Network (MMDCNet) that integrates visual cues with clinical data to improve breast cancer detection. Our approach processes medical images using computer vision techniques while structured patient metadata patterns are learned through a custom fully connected network. The extracted features are fused to form a comprehensive representation, allowing the model to leverage both visual and clinical information. The final classifier is trained based on the joint features embedding space of visual and clinical cues and experiments prove enhanced performance, improving accuracy from 79.38\% to 90.87\% on a Mini-DDSM dataset. Additionally, our approach achieves 97.05\% accuracy on an image-only dataset, highlighting the robustness and effectiveness of visual feature extraction. These findings emphasise the potential of multi-modal learning in medical diagnostics, paving the way for future research on optimising data integration strategies and refining AI-driven clinical decision support systems.

q-bio.QM↗

arXiv2024

High-Order Evolving Graphs for Enhanced Representation of Traffic Dynamics

We present an innovative framework for traffic dynamics analysis using High-Order Evolving Graphs, designed to improve spatio-temporal representations in autonomous driving contexts. Our approach constructs temporal bidirectional bipartite graphs that effectively model the complex interactions within traffic scenes in real-time. By integrating Graph Neural Networks (GNNs) with high-order multi-aggregation strategies, we significantly enhance the modeling of traffic scene dynamics, providing a more accurate and detailed analysis of these interactions. Additionally, we incorporate inductive learning techniques inspired by the GraphSAGE framework, enabling our model to adapt to new and unseen traffic scenarios without the need for retraining, thus ensuring robust generalization. Through extensive experiments on the ROAD and ROAD Waymo datasets, we establish a comprehensive baseline for further developments, demonstrating the potential of our method in accurately capturing traffic behavior. Our results emphasize the value of high-order statistical moments and feature-gated attention mechanisms in improving traffic behavior analysis, laying the groundwork for advancing autonomous driving technologies. Our source code is available at: https://github.com/Addy-1998/High_Order_Graphs

cs.CV↗

arXiv2022

SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization

Over the past few years, a significant progress has been made in deep convolutional neural networks (CNNs)-based image recognition. This is mainly due to the strong ability of such networks in mining discriminative object pose and parts information from texture and shape. This is often inappropriate for fine-grained visual classification (FGVC) since it exhibits high intra-class and low inter-class variances due to occlusions, deformation, illuminations, etc. Thus, an expressive feature representation describing global structural information is a key to characterize an object/ scene. To this end, we propose a method that effectively captures subtle changes by aggregating context-aware features from most relevant image-regions and their importance in discriminating fine-grained categories avoiding the bounding-box and/or distinguishable part annotations. Our approach is inspired by the recent advancement in self-attention and graph neural networks (GNNs) approaches to include a simple yet effective relation-aware feature transformation and its refinement using a context-aware attention mechanism to boost the discriminability of the transformed feature in an end-to-end learning process. Our model is evaluated on eight benchmark datasets consisting of fine-grained objects and human-object interactions. It outperforms the state-of-the-art approaches by a significant margin in recognition accuracy.

cs.CV↗

arXiv2022

Retinal Structure Detection in OCTA Image via Voting-based Multi-task Learning

Automated detection of retinal structures, such as retinal vessels (RV), the foveal avascular zone (FAZ), and retinal vascular junctions (RVJ), are of great importance for understanding diseases of the eye and clinical decision-making. In this paper, we propose a novel Voting-based Adaptive Feature Fusion multi-task network (VAFF-Net) for joint segmentation, detection, and classification of RV, FAZ, and RVJ in optical coherence tomography angiography (OCTA). A task-specific voting gate module is proposed to adaptively extract and fuse different features for specific tasks at two levels: features at different spatial positions from a single encoder, and features from multiple encoders. In particular, since the complexity of the microvasculature in OCTA images makes simultaneous precise localization and classification of retinal vascular junctions into bifurcation/crossing a challenging task, we specifically design a task head by combining the heatmap regression and grid classification. We take advantage of three different \textit{en face} angiograms from various retinal layers, rather than following existing methods that use only a single \textit{en face}. To facilitate further research, part of these datasets with the source code and evaluation benchmark have been released for public access:https://github.com/iMED-Lab/VAFF-Net.

eess.IV↗

arXiv2022

Benchmarking Deep Reinforcement Learning Algorithms for Vision-based Robotics

This paper presents a benchmarking study of some of the state-of-the-art reinforcement learning algorithms used for solving two simulated vision-based robotics problems. The algorithms considered in this study include soft actor-critic (SAC), proximal policy optimization (PPO), interpolated policy gradients (IPG), and their variants with Hindsight Experience replay (HER). The performances of these algorithms are compared against PyBullet's two simulation environments known as KukaDiverseObjectEnv and RacecarZEDGymEnv respectively. The state observations in these environments are available in the form of RGB images and the action space is continuous, making them difficult to solve. A number of strategies are suggested to provide intermediate hindsight goals required for implementing HER algorithm on these problems which are essentially single-goal environments. In addition, a number of feature extraction architectures are proposed to incorporate spatial and temporal attention in the learning process. Through rigorous simulation experiments, the improvement achieved with these components are established. To the best of our knowledge, such a benchmarking study is not available for the above two vision-based robotics problems making it a novel contribution in the field.

cs.RO↗

arXiv2021

An attention-driven hierarchical multi-scale representation for visual recognition

Convolutional Neural Networks (CNNs) have revolutionized the understanding of visual content. This is mainly due to their ability to break down an image into smaller pieces, extract multi-scale localized features and compose them to construct highly expressive representations for decision making. However, the convolution operation is unable to capture long-range dependencies such as arbitrary relations between pixels since it operates on a fixed-size window. Therefore, it may not be suitable for discriminating subtle changes (e.g. fine-grained visual recognition). To this end, our proposed method captures the high-level long-range dependencies by exploring Graph Convolutional Networks (GCNs), which aggregate information by establishing relationships among multi-scale hierarchical regions. These regions consist of smaller (closer look) to larger (far look), and the dependency between regions is modeled by an innovative attention-driven message propagation, guided by the graph structure to emphasize the neighborhoods of a given region. Our approach is simple yet extremely effective in solving both the fine-grained and generic visual classification problems. It outperforms the state-of-the-arts with a significant margin on three and is very competitive on other two datasets.

cs.CV↗

arXiv2021

Attend and Guide (AG-Net): A Keypoints-driven Attention-based Deep Network for Image Recognition

This paper presents a novel keypoints-based attention mechanism for visual recognition in still images. Deep Convolutional Neural Networks (CNNs) for recognizing images with distinctive classes have shown great success, but their performance in discriminating fine-grained changes is not at the same level. We address this by proposing an end-to-end CNN model, which learns meaningful features linking fine-grained changes using our novel attention mechanism. It captures the spatial structures in images by identifying semantic regions (SRs) and their spatial distributions, and is proved to be the key to modelling subtle changes in images. We automatically identify these SRs by grouping the detected keypoints in a given image. The ``usefulness'' of these SRs for image recognition is measured using our innovative attentional mechanism focusing on parts of the image that are most relevant to a given task. This framework applies to traditional and fine-grained image recognition tasks and does not require manually annotated regions (e.g. bounding-box of body parts, objects, etc.) for learning and prediction. Moreover, the proposed keypoints-driven attention mechanism can be easily integrated into the existing CNN models. The framework is evaluated on six diverse benchmark datasets. The model outperforms the state-of-the-art approaches by a considerable margin using Distracted Driver V1 (Acc: 3.39%), Distracted Driver V2 (Acc: 6.58%), Stanford-40 Actions (mAP: 2.15%), People Playing Musical Instruments (mAP: 16.05%), Food-101 (Acc: 6.30%) and Caltech-256 (Acc: 2.59%) datasets.

cs.CV↗

arXiv2021

Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification

Deep convolutional neural networks (CNNs) have shown a strong ability in mining discriminative object pose and parts information for image recognition. For fine-grained recognition, context-aware rich feature representation of object/scene plays a key role since it exhibits a significant variance in the same subcategory and subtle variance among different subcategories. Finding the subtle variance that fully characterizes the object/scene is not straightforward. To address this, we propose a novel context-aware attentional pooling (CAP) that effectively captures subtle changes via sub-pixel gradients, and learns to attend informative integral regions and their importance in discriminating different subcategories without requiring the bounding-box and/or distinguishable part annotations. We also introduce a novel feature encoding by considering the intrinsic consistency between the informativeness of the integral regions and their spatial structures to capture the semantic correlation among them. Our approach is simple yet extremely effective and can be easily applied on top of a standard classification backbone network. We evaluate our approach using six state-of-the-art (SotA) backbone networks and eight benchmark datasets. Our method significantly outperforms the SotA approaches on six datasets and is very competitive with the remaining two.

cs.CV↗

arXiv2021

Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition

There is significant progress in recognizing traditional human activities from videos focusing on highly distinctive actions involving discriminative body movements, body-object and/or human-human interactions. Driver's activities are different since they are executed by the same subject with similar body parts movements, resulting in subtle changes. To address this, we propose a novel framework by exploiting the spatiotemporal attention to model the subtle changes. Our model is named Coarse Temporal Attention Network (CTA-Net), in which coarse temporal branches are introduced in a trainable glimpse network. The goal is to allow the glimpse to capture high-level temporal relationships, such as 'during', 'before' and 'after' by focusing on a specific part of a video. These branches also respect the topology of the temporal dynamics in the video, ensuring that different branches learn meaningful spatial and temporal changes. The model then uses an innovative attention mechanism to generate high-level action specific contextual information for activity recognition by exploring the hidden states of an LSTM. The attention mechanism helps in learning to decide the importance of each hidden state for the recognition task by weighing them when constructing the representation of the video. Our approach is evaluated on four publicly accessible datasets and significantly outperforms the state-of-the-art by a considerable margin with only RGB video as input.

cs.CV↗