We introduce a quantum-enhanced multimodal framework for Urdu sentiment analysis that integrates classical feature extractors with a variational quantum circuit (VQC) classifier. Raw text, audio, and visual signals are first processed by a cross-modal transformer to produce a unified embedding. These fused embeddings are then angle-encoded into a parameterized quantum state on a noisy intermediate-scale quantum (NISQ) processor. The VQC's trainable rotation gates are optimized via simultaneous perturbation stochastic approximation (SPSA) under realistic hardware-inspired noise models. Evaluated on UMSA-U, a curated dataset of 6,000 Urdu video clips with aligned transcripts, audio, and facial-expression annotations, our quantum-enhanced model achieves 84.2% overall accuracy and a macro-F1 score of 81.7% improving over both the classical cross-modal baseline (82.4%/79.6%) and a purely classical MLP head (83.1%/80.8%). Ablation studies demonstrate that quantum feature encoding yields more separable decision boundaries, and noise-robust SPSA tuning sustains performance on simulated hardware error rates up to 5%. These results showcase the promise of variational quantum classifiers for low-resource, multimodal language tasks and set a new benchmark for Urdu sentiment understanding on NISQ devices.
We introduce a quantum-enhanced multimodal framework for Urdu sentiment analysis that integrates classical feature extractors with a variational quantum circuit (VQC) classifier. Raw text, audio, and visual signals are first processed by a cross-modal transformer to produce a unified embedding. These fused embeddings are then angle-encoded into a parameterized quantum state on a noisy intermediate-scale quantum (NISQ) processor. The VQC's trainable rotation gates are optimized via simultaneous perturbation stochastic approximation (SPSA) under realistic hardware-inspired noise models. Evaluated on UMSA-U, a curated dataset of 6,000 Urdu video clips with aligned transcripts, audio, and facial-expression annotations, our quantum-enhanced model achieves 84.2% overall accuracy and a macro-F1 score of 81.7% improving over both the classical cross-modal baseline (82.4%/79.6%) and a purely classical MLP head (83.1%/80.8%). Ablation studies demonstrate that quantum feature encoding yields more separable decision boundaries, and noise-robust SPSA tuning sustains performance on simulated hardware error rates up to 5%. These results showcase the promise of variational quantum classifiers for low-resource, multimodal language tasks and set a new benchmark for Urdu sentiment understanding on NISQ devices.
For Urdu sentiment analysis, we present a quantum-enhanced multimodal system that combines a variational quantum circuit (VQC) classifier with traditional feature extractors. To create a cohesive embedding, a cross-modal transformer model first processes raw text, audio, and visual information. On a noisy intermediate-scale quantum (NISQ) processor, these fused embeddings are then angle-encoded into a parameterized quantum state. Simultaneous perturbation stochastic approximation (SPSA) is used to improve the trainable rotation gates of the VQC under realistic hardware-inspired noise models. Our quantum-enhanced model outperforms the classical cross-modal baseline(82.4%/79.6%)and a purely classical MLP head (83.1%/80.8%) with an overall accuracy of 84.2% and a macro-F1 score of 81.7% when tested on UMSA-U, a curated dataset of 6,000 Urdu video clips with aligned transcripts, audio, and facial expression annotations. The findings show that noise-robust SPSA tuning maintains performance on simulated hardware error rates up to 5%, while quantum feature encoding produces more separable decision boundaries. These findings establish a new standard for Urdu sentiment recognition on NISQ devices and demonstrate the potential of variational quantum classifiers for low-resource, multimodal language solutions.
Abstract Hybrid quantum–classical models for text classification are constrained by the mismatch between high-dimensional sentence embeddings and the limited number of qubits available in Noisy Intermediate-Scale Quantum (NISQ) hardware. Existing approaches rely on fixed dimensionality-reduction techniques such as PCA, which compress embeddings independently of the learning task and often remove semantic information essential for downstream classification. This work addresses this limitation by applying Neural Quantum Embedding (NQE) to sentence-level sentiment analysis. NQE jointly performs nonlinear neural compression and quantum-oriented encoding, producing compact embeddings optimized for variational circuits.We integrate NQE with a Quantum Neural Network based on a three-layer SU(4) ansatz. Experiments on three sentence-level sentiment datasets show that NQE substantially improves hybrid quantum performance, increasing accuracy by up to 38%, with corresponding improvements in precision, recall, and F1-score. Additional experiments with a classical neural network demonstrate that NQE also enhances classical performance, yielding accuracy gains of up to 6.3%. Although classical models achieve higher absolute accuracy due to greater representational capacity, the relative improvement introduced by NQE is significantly larger in the quantum setting, where embedding structure must align with strict hardware constraints.Overall, this study introduces a task-adaptive, learnable embedding mechanism that bridges the representational gap between classical embeddings and quantum circuits. The results show that NQE improves optimization stability, enhances quantum-state separability, and enables more effective hybrid sentiment classification within NISQ limitations
Multimodal emotion recognition can benefit from combining complementary information from facial images, speech, and text.However, integrating heterogeneous modalities obtained from independently collected datasets introduces challenges in data alignment and label consistency.This study presents a hybrid quantum-classical framework that combines modality-specific classical encoders with a quantum re-uploading variational classifier for six-class emotion recognition.Facial images, speech samples, and textual samples were obtained from separate publicly available datasets and aligned at the emotion-label level to construct a unified multimodal experimental setting.Image, speech, and text encoders generated modality-specific representations that were fused through a classical neural network and projected into a six-dimensional quantum input space.A six-qubit quantum circuit with three re-uploading layers repeatedly encoded the fused features before six-class classification.On a test set of 6,347 samples, the classical Image-Speech-Text fusion model achieved 73.94% accuracy and a 70.64% macro F1-score, whereas the proposed quantum reuploading model achieved 72.57% accuracy and a 68.76% macro F1-score.The quantum model used 8,706 trainable parameters compared with 15,440,006 for the classical multimodal model, representing a 99.94% reduction in trainable parameters.The results indicate that quantum re-uploading can provide competitive performance for multimodal emotion recognition while highlighting the limitations of label-level alignment across independently collected datasets.
Most multimodal learning methods improve how heterogeneous representations are aligned and fused, while post-fusion enhancement remains less explored. We propose Parallel Quantum Feature Augmentation (PQFA), a hybrid quantum-classical framework that applies multiple shallow variational quantum circuits to fused multimodal features. Text and image representations extracted by frozen RoBERTa and ViT encoders are processed through bidirectional cross-attention, attentive pooling, and adaptive gated fusion. The fused feature is then amplitude-encoded into parallel quantum circuits, whose measurement readouts are concatenated with the classical representation for prediction. We evaluate PQFA on MM-IMDb and N24News through controlled comparisons using the same encoders, fusion backbone, data splits, projection dimension, and augmentation output width. PQFA consistently outperforms both the fusion backbone without quantum augmentation and a width-matched MLP augmentation baseline, while using approximately 2.2K augmentation parameters compared with 24.0K for the MLP branch. Missing-modality experiments further show improved robustness when textual or visual inputs are incomplete, with particularly clear gains when the more informative textual modality is severely degraded. Controlled ablations and feature-space analyses indicate that the improvement cannot be reproduced by random feature mappings, increased classical width, or untrained quantum transformations. Quantum-state diagnostics additionally show stable predictive performance across the tested simulated noise levels and distinct branch-specific transformations of the encoded states. These results establish PQFA as an effective and parameter-efficient strategy for post-fusion augmentation in hybrid quantum-classical multimodal learning.
Multimodal emotion recognition can benefit from combining complementary information from facial images, speech, and text. However, integrating heterogeneous modalities obtained from independently collected datasets introduces challenges in data alignment and label consistency. This study presents a hybrid quantum–classical framework that combines modality-specific classical encoders with a quantum re-uploading variational classifier for six-class emotion recognition. Facial images, speech samples, and textual samples were obtained from separate publicly available datasets and aligned at the emotion-label level to construct a unified multimodal experimental setting. Image, speech, and text encoders generated modality-specific representations that were fused through a classical neural network and projected into a six-dimensional quantum input space. A six-qubit quantum circuit with three re-uploading layers repeatedly encoded the fused features before six-class classification. On a test set of 6,347 samples, the classical Image–Speech–Text fusion model achieved 73.94% accuracy and a 70.64% macro F1-score, whereas the proposed quantum re-uploading model achieved 72.57% accuracy and a 68.76% macro F1-score. The quantum model used 8,706 trainable parameters compared with 15,440,006 for the classical multimodal model, representing a 99.94% reduction in trainable parameters. The results indicate that quantum re-uploading can provide competitive performance for multimodal emotion recognition while highlighting the limitations of label-level alignment across independently collected datasets.
Multimodal vision-language systems typically fuse image and text embeddings through classical operators such as concatenation, attention, bilinear pooling, or tensor interactions. We propose Quantum Entangled Multimodal Fusion Networks (QEMFN), a hybrid quantum-classical framework that introduces parameterized entanglement as a structured inductive bias for multimodal fusion. Pretrained visual and textual features are projected into compact latent spaces, encoded as angle-parameterized quantum states, processed through intra-modal and paired cross-modal entangling circuits, and measured to produce fused representations for retrieval. Under matched parameter budgets and identical frozen CLIP backbones, QEMFN outperforms classical fusion baselines on COCO-5k and Flickr30k, including multilayer perceptron, tensor fusion, FiLM, cross-attention, compact transformer, and a dequantized paired-topology analogue. An ablation suite isolates the quantum module's contribution from the surrounding classical projections, and quantum-centric analyses report Meyer-Wallach entangling capability, expressibility, gradient variance against barren-plateau bounds, and entropy-performance correlation under controls for training progress alongside an intervention study on the entangling component. QEMFN is executed under shot-based estimation, a noise-modeled fake backend, and a real superconducting device with zero-noise extrapolation. This work does not claim quantum computational advantage; the contribution is the framework together with a controlled empirical and quantum-centric evaluation that positions trainable entanglement as an interpretable, hardware-executable fusion mechanism at scales accessible on contemporary devices.