Temporally-Aligned Evaluation for Audio-Driven Talking Head Generation

Audio-driven talking-head generation has advanced rapidly, yet existing evaluation protocols mainly rely on frame-wise metrics that assume strict temporal correspondence between generated and reference videos. This assumption does not match speech-driven facial motion, which naturally includes slight timing shifts, different speaking speeds, and stylistic variations. As a result, conventional metrics may treat harmless timing differences as quality errors, making it harder to fairly compare methods and understand their trade-offs. In this work, we argue that evaluation of dynamic generative models should be formulated as a sequence-alignment problem rather than independent frame comparison. We introduce a unified sequence-level reformulation that integrates Soft Dynamic Time Warping into established evaluation pipelines. By aligning feature trajectories while preserving temporal order, the proposed framework provides robustness to bounded temporal misalignments without altering the underlying perceptual, identity, or synchronization encoders. We show that frame-wise evaluation can be viewed as a special case under rigid alignment, while sequence-level alignment provides improved stability, lower sensitivity to timing differences, and clearer separation between modeling paradigms. Building on this principled formulation, we conduct a large-scale benchmark of 20 methods across seven datasets spanning canonical, in-the-wild, and style-diverse scenarios under standardized protocols. Extensive experiments show that temporally aligned metrics are more robust to timing differences, provide more consistent results across datasets, and better reveal systematic trade-offs between modeling paradigms, such as synchronization versus realism and expressiveness versus stability.

Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation

Audio-driven talking-head generation has achieved remarkable progress with recent models such as AniTalker, FLOAT, and Sonic. Despite their success, most existing approaches rely on a single static reference image to condition the entire video generation process at inference stage. This static conditioning paradigm often creates a mismatch between fixed identity features and dynamically evolving facial motion, leading to identity drift, temporal inconsistency, and degraded perceptual quality. We introduce Test-Time Self-Adaptive Conditioning (TT-SAC), a parameter-free inference framework that enables pretrained talking-head generators to adapt their conditioning representations during inference without retraining, gradient updates, or additional supervision. Instead of treating the reference portrait as immutable, TT-SAC composes the generator with its encoder in a feedback loop: the generator's own outputs are re-encoded to construct a refined conditioning representation that better aligns with the temporal dynamics of the synthesized sequence. A single adaptation step approximates a self-consistent equilibrium of the generative process, stabilizing identity and motion across time. We further provide theoretical analysis showing that test-time conditioning adaptation reduces feature variance and improves generative stability under mild Lipschitz assumptions, while exhibiting a principled bias-variance tradeoff that governs the optimal strength of adaptation. Extensive experiments on state-of-the-art talking-head generators and benchmark datasets demonstrate consistent improvements in lip-sync accuracy, temporal coherence, identity preservation, and perceptual fidelity. TT-SAC offers a model-agnostic and training-free strategy for enhancing generative video models, establishing test-time conditioning adaptation as an effective mechanism for stabilizing audio-driven portrait animation.

Trust-Aware Joint Feature-Prediction Discrepancy for Robust Domain Adaptation

Domain adaptation aims to mitigate performance degradation caused by distribution shifts between a labeled source domain and an unlabeled or sparsely labeled target domain. Most existing approaches estimate domain discrepancy either in feature space or in prediction space. However, these single-perspective strategies overlook a critical problem under domain shift: the reliability of the signals used for alignment. In practice, both learned representations and semantic predictions may become unreliable, and treating all target samples equally can lead to misleading alignment and suboptimal transfer. We introduce trust-aware domain adaptation, a principled framework that models domain discrepancy through the reliability of feature and prediction signals. Central to our approach is the Joint Feature-Prediction Discrepancy (JFPD), a unified formulation that jointly captures representation divergence and prediction divergence while weighting their contributions by sample-specific trust. Trust is quantified via two complementary mechanisms: uncertainty-aware trust, derived from prediction entropy to suppress unreliable predictions, and semantic-alignment trust, computed from prototype similarity in feature space to emphasize well-aligned representations. By prioritizing confident and semantically consistent samples while down-weighting noisy or ambiguous ones, JFPD provides a reliability-aware estimate of domain discrepancy. We further integrate JFPD into a training objective that guides adaptation toward trustworthy regions of the target domain. Experiments on standard benchmarks demonstrate that the proposed framework consistently achieves superior adaptation performance and yields discrepancy estimates that correlate with target-domain error. This work addresses, for the first time, the importance of modeling trust in the interaction between features and predictions for domain adaptation.

Uncertainty-DTW for Sequences and Visual Tokens

Aligning structured data is a fundamental problem in computer vision and machine learning, underlying tasks such as time series analysis, human action recognition, and visual representation learning. Existing alignment methods, including Dynamic Time Warping (DTW) and its differentiable variants, rely on deterministic similarity measures and are therefore sensitive to heterogeneous and noisy features. In this work, we introduce uncertainty-aware alignment, a probabilistic framework that models pairwise correspondences with heteroscedastic uncertainty and performs structured matching along alignment paths. Our formulation, uncertainty-DTW (uDTW), assigns each correspondence a Normal distribution and parametrizes each alignment path by a Maximum Likelihood Estimate objective consisting of (i) a precision-weighted matching term that suppresses unreliable features, and (ii) a log-variance regularization that prevents degenerate solutions. This yields a probabilistic alignment mechanism that is robust to noise and interpretable, as uncertainty directly reflects the reliability of matches. We further generalize this framework from temporal sequences to tokenized visual representations, enabling structured matching over sets of visual tokens. The learned uncertainty can be interpreted as a reverse-attention: semantically relevant regions exhibit low uncertainty and dominate the alignment, while ambiguous/noisy regions have high uncertainty. This provides a connection between alignment, attention, and uncertainty modeling. We evaluate the proposed framework across diverse domains. The results demonstrate consistent improvements over state-of-the-art methods and show that learned uncertainty correlates with semantic importance. These findings establish uncertainty-aware alignment as a general, robust, and interpretable framework for learning from structured data.

MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimation

6D object pose estimation in cluttered scenes remains challenging due to severe occlusion and sensor noise. We propose MAPRPose, a two-stage framework that leverages mask-aware correspondences for pose proposal and amodal-driven Region-of-Interest (ROI) prediction for robust refinement. In the Mask-Aware Pose Proposal (MAPP) stage, we lift 2D correspondences into 3D space to establish reliable keypoint matches and generate geometrically consistent pose hypotheses based on correspondence-level scoring, from which the top-$K$ candidates are selected. In the refinement stage, we introduce a tensorized render-and-compare pipeline integrated with an Amodal Mask Prediction and ROI Re-Alignment (AMPR) module. By reconstructing complete object geometry and dynamically adjusting the ROI, AMPR mitigates localization errors and spatial misalignment under heavy occlusion. Furthermore, our GPU-accelerated RGB-XYZ reprojection enables simultaneous refinement of all $N \times B$ pose hypotheses in a single forward pass. Evaluated on the BOP benchmark, MAPRPose achieves a state-of-the-art Average Recall (AR) of 76.5%, outperforming FoundationPose by 3.1% AR while delivering a 43x speedup in multi-object inference.

Subspace Kernel Learning on Tensor Sequences

Learning from structured multi-way data, represented as higher-order tensors, requires capturing complex interactions across tensor modes while remaining computationally efficient. We introduce Uncertainty-driven Kernel Tensor Learning (UKTL), a novel kernel framework for $M$-mode tensors that compares mode-wise subspaces derived from tensor unfoldings, enabling expressive and robust similarity measure. To handle large-scale tensor data, we propose a scalable Nyström kernel linearization with dynamically learned pivot tensors obtained via soft $k$-means clustering. A key innovation of UKTL is its uncertainty-aware subspace weighting, which adaptively down-weights unreliable mode components based on estimated confidence, improving robustness and interpretability in comparisons between input and pivot tensors. Our framework is fully end-to-end trainable and naturally incorporates both multi-way and multi-mode interactions through structured kernel compositions. Extensive evaluations on action recognition benchmarks (NTU-60, NTU-120, Kinetics-Skeleton) show that UKTL achieves state-of-the-art performance, superior generalization, and meaningful mode-wise insights. This work establishes a principled, scalable, and interpretable kernel learning paradigm for structured multi-way and multi-modal tensor sequences.

DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation

Indoor semantic segmentation is fundamental to computer vision and robotics, supporting applications such as autonomous navigation, augmented reality, and smart environments. Although RGB-D fusion leverages complementary appearance and geometric cues, existing methods often depend on computationally intensive cross-attention mechanisms and insufficiently model intra- and inter-modal feature relationships, resulting in imprecise feature alignment and limited discriminative representation. To address these challenges, we propose DiffPixelFormer, a differential pixel-aware Transformer for RGB-D indoor scene segmentation that simultaneously enhances intra-modal representations and models inter-modal interactions. At its core, the Intra-Inter Modal Interaction Block (IIMIB) captures intra-modal long-range dependencies via self-attention and models inter-modal interactions with the Differential-Shared Inter-Modal (DSIM) module to disentangle modality-specific and shared cues, enabling fine-grained, pixel-level cross-modal alignment. Furthermore, a dynamic fusion strategy balances modality contributions and fully exploits RGB-D information according to scene characteristics. Extensive experiments on the SUN RGB-D and NYUDv2 benchmarks demonstrate that DiffPixelFormer-L achieves mIoU scores of 54.28% and 59.95%, outperforming DFormer-L by 1.78% and 2.75%, respectively. Code is available at https://github.com/gongyan1/DiffPixelFormer.

Learning Time in Static Classifiers

Real-world visual data rarely presents as isolated, static instances. Instead, it often evolves gradually over time through variations in pose, lighting, object state, or scene context. However, conventional classifiers are typically trained under the assumption of temporal independence, limiting their ability to capture such dynamics. We propose a simple yet effective framework that equips standard feedforward classifiers with temporal reasoning, all without modifying model architectures or introducing recurrent modules. At the heart of our approach is a novel Support-Exemplar-Query (SEQ) learning paradigm, which structures training data into temporally coherent trajectories. These trajectories enable the model to learn class-specific temporal prototypes and align prediction sequences via a differentiable soft-DTW loss. A multi-term objective further promotes semantic consistency and temporal smoothness. By interpreting input sequences as evolving feature trajectories, our method introduces a strong temporal inductive bias through loss design alone. This proves highly effective in both static and temporal tasks: it enhances performance on fine-grained and ultra-fine-grained image classification, and delivers precise, temporally consistent predictions in video anomaly detection. Despite its simplicity, our approach bridges static and temporal learning in a modular and data-efficient manner, requiring only a simple classifier on top of pre-extracted features.

Video Understanding by Design: How Datasets Shape Architectures and Insights

Video understanding has advanced rapidly, fueled by increasingly complex datasets and powerful architectures. Yet existing surveys largely classify models by task or family, overlooking the structural pressures through which datasets guide architectural evolution. This survey is the first to adopt a dataset-driven perspective, showing how motion complexity, temporal span, hierarchical composition, and multimodal richness impose inductive biases that models should encode. We reinterpret milestones, from two-stream and 3D CNNs to sequential, transformer, and multimodal foundation models, as concrete responses to these dataset-driven pressures. Building on this synthesis, we offer practical guidance for aligning model design with dataset invariances while balancing scalability and task demands. By unifying datasets, inductive biases, and architectures into a coherent framework, this survey provides both a comprehensive retrospective and a prescriptive roadmap for advancing general-purpose video understanding.

Progressive Bird's Eye View Perception for Safety-Critical Autonomous Driving: A Comprehensive Survey

Bird's-Eye-View (BEV) perception has become a foundational paradigm in autonomous driving, enabling unified spatial representations that support robust multi-sensor fusion and multi-agent collaboration. As autonomous vehicles transition from controlled environments to real-world deployment, ensuring the safety and reliability of BEV perception in complex scenarios - such as occlusions, adverse weather, and dynamic traffic - remains a critical challenge. This survey provides the first comprehensive review of BEV perception from a safety-critical perspective, systematically analyzing state-of-the-art frameworks and implementation strategies across three progressive stages: single-modality vehicle-side, multimodal vehicle-side, and multi-agent collaborative perception. Furthermore, we examine public datasets encompassing vehicle-side, roadside, and collaborative settings, evaluating their relevance to safety and robustness. We also identify key open-world challenges - including open-set recognition, large-scale unlabeled data, sensor degradation, and inter-agent communication latency - and outline future research directions, such as integration with end-to-end autonomous driving systems, embodied intelligence, and large language models.