Conventional Euclidean fusion paradigms in multimodal sentiment analysis (MSA) fail to capture non-Euclidean correlations and probabilistic uncertainty across modalities, often leading to misaligned affective representations and limited robustness under real-world variability. To overcome these challenges, we introduce the novel Quantum-Inspired Geometric and Energy-Based Fusion (QEGF) framework that unifies geometric sentiment representation with probabilistic uncertainty modeling for more reliable affective perception. First, the Quantum-Inspired Geometric Fusion (QGF) operator represents each modality as a trace-normalized Symmetric Positive-Definite (SPD) density descriptor, enabling second-order correlation modeling and adaptive gating via a spectral entropy statistic from each trace-normalized SPD descriptor. This design decouples structural encoding from semantic refinement, significantly mitigating performance degradation under noisy and corrupted inputs, and achieving a 4.55% Acc-2 gain over Cross-Attention in domain shift scenarios. Second, Energy-Based Uncertainty Modeling (EBUM) introduces a contrastive energy objective with a batch-level energy-dispersion signal, stabilizing convergence and yielding a lower Brier score (0.172 to 0.135) in the output-level calibration diagnostic under domain shift. Comprehensive evaluations across major benchmarks confirm that QEGF achieves state-of-the-art performance and superior resilience, laying a pathway toward more interpretable and resilient affective human-machine interaction.
Recent advances in sensor technology have led to an explosion of Spatial High-Dimensional Data (SHD), including spatial transcriptomics and hyperspectral imaging, the two domains studied in this work. These data capture complex interactions between intrinsic sample properties and spatial microenvironments by incorporating location information through accumulation, embedding, or aggregation. Existing methods typically assume homogeneous spatial interaction patterns, overlooking critical asymmetries in SHD: (i) view asymmetry between spatial patterns and high-dimensional attributes, and (ii) spatial asymmetry in the internal pathways of high-dimensional data. To address this gap, we propose DIaS, a data-centric decoupling framework that disentangles spatial-induced, intrinsic, and harmonized information signals to better model the richness of SHD. Specifically, DIaS employs a Gaussian process for spatial embedding, leveraging uncertainty quantification to dynamically infer spatial pathways. During disentanglement, SHD is decomposed into three mutually regularized views to minimize dependence between spatial attributes and intrinsic features. To balance the asymmetric contributions of spatial and intrinsic information, we introduce an asymmetric harmonization mechanism, which adaptively aligns spatial and intrinsic representations to identify salient and diverse multi-view prototypes. Experiments on 18 benchmarks in spatial transcriptomics and hyperspectral imaging, together with downstream task evaluations, demonstrate state-of-the-art performance and the effectiveness of DIaS in alleviating information asymmetry within these two domains. The demo code of this work is publicly available at https://github.com/hexiao0275/DIaS.
Video analytics pipelines (VAPs) have been a paradigm for large-scale video analytics. Due to temporal redundancy in video, frame filtering is widely used in VAPs to reduce analysis workload. While prior works have identified decoding as a significant overhead and proposed pre-decoding filtering to mitigate it, we find that codec reference dependencies still force decoders to process many unselected frames, manifesting an over-decoding trap that bounds end-to-end throughput. This limitation stems from the reference-based design in modern codecs, which requires decoding preceding frames to reconstruct any selected one. As a result, over-decoding has become the practical bottleneck in VAPs using modern decoders, highlighting a critical but under-explored problem. To address this issue, we propose ParaDeco, a high-throughput video analytics framework featuring a novel frame-level parallel generative decoder. Unlike traditional decoders, ParaDeco adopts a decode-what-matters approach with decoupled frame dependencies. To decode arbitrary frames independently, ParaDeco generates frame-wise features as standalone skeletons using compressed video metadata, then predicts pseudo frames maintaining semantic consistency with original frames. Moreover, ParaDeco identifies which frames truly matter for analysis via delicate contribution-based frame filtering. We implement ParaDeco on a cloud server and evaluate it on large-scale real-world surveillance video datasets. Our experimental results show that ParaDeco achieves a 2.76× speedup on averagparse e compared to state-of-the-art VAPs.
Despite recent advances in human-object interaction (HOI) animation generation, text-driven HOI synthesis remains a fundamental challenge in computer vision. This task demands fine-grained language comprehension and accurate modeling of physically plausible interactions. In this work, we introduce HOIAnimator, a novel diffusion-based framework with strong text-perception capabilities for generating realistic and complex HOI animations from natural language descriptions. We propose a unified semantic–physical generative framework that integrates three key components: (1) Structured Text Embedding (STE) that decomposes descriptions into fine-grained semantic cues; (2) Dual Perceptive Diffusion Models (DPDM) that decouple and co-model human and object dynamics via Perceptive Message Passing (PMP); and (3) an Interaction Contact Field (ICF) that enforces continuous contact-aware constraints. Experiments on BEHAVE and OMOMO datasets show that our approach outperforms state-of-the-art methods in semantic alignment, physical realism, and interaction diversity.
