论文检索

Siddhant Gole, Akash Pal, Amit More, S Divakar Bhat, Subhasis Chaudhuri, Biplab Banerjee

Continual Test-Time Adaptation (CTTA) for semantic segmentation is vital for deploying vision models in dynamic environments with persistent domain shifts. Existing methods often degrade over time as self-supervised updates amplify early prediction errors. We attribute this fragility to a geometric limitation: Euclidean feature spaces, with polynomial volume growth, lead to distorted semantic representations and crowded, unstable decision boundaries. We propose HyperProtoSeg, a hyperbolic prototypical segmentation network that learns geometrically optimal class prototypes in the Poincare ball. Leveraging the exponential expansion of hyperbolic space, it enforces large and uniform inter-class margins with low distortion, yielding well separated and curvature-stable embeddings. For robust online adaptation, we introduce Hyperbolic Boundary Consistency Adaptation (HBCA), which partitions pixels by cross-view consistency into confident "core" and uncertain "boundary" sets. HBCA applies geodesic distance minimization for confident regions and a novel Hyperbolic Directional Consistency Loss for uncertain ones, preventing error amplification. Experiments on challenging synthetic- to-real benchmarks (Cityscapes - ACDC, IDD - IDD-AW, SHIFT) show that HyperProtoSeg + HBCA achieves an average improvement of (1.94%,4.02%,1.24%) over state-of-the-art CTTA methods under severe structural shifts.

Sofian Chaybouti, Sanath Narayan, Yasser Dahou, Phúc H. Lê Khắc, Ankit Singh, Ngoc Huynh, Wamiq Reyaz Para, Hilde Kuehne, Hakim Hacid

Vision foundation models trained via multi-teacher distillation offer a promising path toward unified visual representations, yet the learning dynamics and data efficiency of such approaches remain underexplored. In this paper, we systematically study multi-teacher distillation for vision foundation models and identify key factors that enable training at lower computational cost. We introduce SigLino, an efficient family of agglomerative vision foundation models that distill knowledge from SigLIP2 and DINOv3 simultaneously into Dense and Mixture-of-Experts students. We show that (1) our Asymmetric Relation-Knowledge Distillation loss preserves the geometric properties of each teacher while enabling effective knowledge transfer, (2) token-balanced batching that packs varying-resolution images into sequences with uniform token budgets stabilizes representation learning across resolutions without sacrificing performance, (3) hierarchical clustering and sampling of training data--typically reserved for self-supervised learning--substantially improves sample efficiency over random sampling for multi-teacher distillation, and (4) the resulting representations transfer effectively to early-fusion Grounding-VLMs, outperforming models trained from scratch. By combining these findings, we curate OpenLVD200M, a 200M-image corpus that demonstrates superior efficiency for multi-teacher distillation. Instantiated in a Mixture-of-Experts, our SigLino-MoE initializes an early-fusion Grounding-VLM that replaces the conventional ViT-LLM stack, demonstrating improved performance compared to a model trained from scratch. We release OpenLVD200M and distilled checkpoints.

Yanying Li, Jinyang Li, Shengfeng He, Yangyang Xu, Junyu Dong, Yong Du

We present NimbusGS, a unified framework for reconstructing high-quality 3D scenes from degraded multi-view inputs captured under diverse and mixed adverse weather conditions. Unlike existing methods that target specific weather types, NimbusGS addresses the broader challenge of generalization by modeling the dual nature of weather: a continuous, view-consistent medium that attenuates light, and dynamic, view-dependent particles that cause scattering and occlusion. To capture this structure, we decompose degradations into a global transmission field and per-view particulate residuals. The transmission field represents static atmospheric effects shared across views, while the residuals model transient disturbances unique to each input. To enable stable geometry learning under severe visibility degradation, we introduce a geometry-guided gradient scaling mechanism that mitigates gradient imbalance during the self-supervised optimization of 3D Gaussian representations. This physically grounded formulation allows NimbusGS to disentangle complex degradations while preserving scene structure, yielding superior geometry reconstruction and outperforming task-specific methods across diverse and challenging weather conditions.

Yiyao Zhu, Ying Xue, Haiming Zhang, Guangfeng Jiang, Wending Zhou, Xu Yan, Jiantao Gao, Yingjie Cai, Bingbing Liu, Zhen Li 等

Vision-based autonomous driving has gained much attention due to its low costs and excellent performance. Compared with dense BEV (Bird's Eye View) or sparse query models, Gaussian-centric method is a comprehensive yet sparse representation by describing scene with 3D semantic Gaussians. In this paper, we introduce DLWM, a novel paradigm with Dual Latent World Models specifically designed to enable holistic gaussian-centric pre-training in autonomous driving using two stages. In the first stage, DLWM predicts 3D Gaussians from queries by self-supervised reconstructing multi-view semantic and depth images. Equipped with fine-grained contextual features, in the second stage, two latent world models are trained separately for temporal feature learning, including Gaussian-flow-guided latent prediction for downstream occupancy perception and forecasting tasks, and ego-planning-guided latent prediction for motion planning. Extensive experiments in SurroundOcc and nuScenes benchmarks demonstrate that DLWM shows significant performance gains across Gaussian-centric 3D occupancy perception, 4D occupancy forecasting and motion planning tasks.

Qiwei Liang, Boyang Cai, Minghao Lai, Sitong Zhuang, Tao Lin, Yan Qin, Yixuan Ye, Jiaming Liang, Renjing Xu

Despite strong results on recognition and segmentation, current 3D visual pre-training methods often underperform on robotic manipulation. We attribute this gap to two factors: the lack of state-action-state dynamics modeling and the unnecessary redundancy of explicit geometric reconstruction. We introduce AFRO, a self-supervised framework that learns dynamics-aware 3D representations without action or reconstruction supervision. AFRO casts state prediction as a generative diffusion process and jointly models forward and inverse dynamics in a shared latent space to capture causal transition structure. To prevent feature leakage in action learning, we employ feature differencing and inverse-consistency supervision, improving the quality and stability of visual features. When combined with Diffusion Policy, AFRO substantially increases manipulation success rates across 16 simulated and 4 real-world tasks, outperforming existing pre-training approaches. The framework also scales favorably with data volume and task complexity. Qualitative visualizations indicate that AFRO learns semantically rich, discriminative features, offering an effective pre-training solution for 3D representation learning in robotics. Project page: https://kolakivy.github.io/AFRO/

Yuan Zhang, Sihao Dou, Kai Hu, Shuhua Deng, Chunhong Cao, Fen Xiao, Xieping Gao

Endoscopic video analysis is essential for early gastrointestinal screening but remains hindered by limited high-quality annotations. While self-supervised video pre-training shows promise, existing methods developed for natural videos prioritize dense spatio-temporal modeling and exhibit motion bias, overlooking the static, structured semantics critical to clinical decision-making. To address this challenge, we propose Focus-to-Perceive Representation Learning (FPRL), a cognition-inspired hierarchical framework that emulates clinical examination. FPRL first focuses on intra-frame lesion-centric regions to learn static semantics, and then perceives their evolution across frames to model contextual semantics. To achieve this, FPRL employs a hierarchical semantic modeling mechanism that explicitly distinguishes and collaboratively learns both types of semantics. Specifically, it begins by capturing static semantics via teacher-prior adaptive masking (TPAM) combined with multi-view sparse sampling. This approach mitigates redundant temporal dependencies and enables the model to concentrate on lesion-related local semantics. Following this, contextual semantics are derived through cross-view masked feature completion (CVMFC) and attention-guided temporal prediction (AGTP). These processes establish cross-view correspondences and effectively model structured inter-frame evolution, thereby reinforcing temporal semantic continuity while preserving global contextual integrity. Extensive experiments on 11 endoscopic video datasets show that FPRL achieves superior performance across diverse downstream tasks, demonstrating its effectiveness in endoscopic video representation learning. The code is available at https://github.com/MLMIP/FPRL.

Tian Wen, Zhiqin Yang, Yonggang Zhang, Xuefeng Jiang, Hao Peng, Yuwei Wang, Bo Han

Federated learning (FL) suffers from performance degradation due to the inevitable presence of noisy annotations in distributed scenarios. Existing approaches have advanced in distinguishing noisy samples from the dataset for label correction by leveraging loss values. However, noisy samples recognition relying on scalar loss lacks reliability for FL under heterogeneous scenarios. In this paper, we rethink this paradigm from a representation perspective and propose FedRG(**Fed**erated under **R**epresentation **G**emometry), which follows **"the principle of "representation geometry priority"** to recognize noisy labels. Firstly, FedRG creates label-agnostic spherical representations by using self-supervision. It then iteratively fits a spherical von Mises-Fisher (vMF) mixture model to this geometry to capture semantic clusters. This geometric evidence is integrated with a semantic-label soft mapping mechanism to derive a distribution divergence between the label-free and annotated label-conditioned feature space, which robustly identifies noisy samples and updates the semantic-label mappings with the newly separated clean dataset. Lastly, we employ an additional personalized noise absorption matrix on noisy labels to achieve robust optimization. Extensive experimental results demonstrate that FedRG outperforms state-of-the-art methods for FL with data heterogeneity under diverse noisy clients scenarios.

Tianhao Han, Haoyang Zhang, Liang Xie, Haochen Chang, Kun Gao, Yuan Cheng, Pengfei Ren, Erwei Yin

Manually annotating accurate 3D hand poses is extremely time-consuming and labor-intensive. Existing self-supervised hand pose estimation methods leverage the discrepancy between input images and rendered outputs, or multi-view consistency constraints, as the driving force to optimize networks and progressively refine pose accuracy. However, these methods are highly susceptible to noisy pseudo-labels and overlook the importance of fully exploiting fine-grained spatial correlations, which undermines the stability of model training. To address these issues, we propose UST-Hand, a self-supervised learning framework that estimates uncertainty distribution of hand pose and constructs a probabilistic point cloud feature space, which enables the complex spatiotemporal relationship modeling. UST-Hand employs a conditional normalizing flow model to capture hand pose distributions and samples diverse hypotheses, facilitating robust learning under noisy pseudo-labels supervision with enhanced stability. These multi-hypothesis are mapped to a unified probabilistic 3D point cloud space for multi-view and temporal feature interaction, comprehensively exploring hand motion patterns and fine-grained spatial correlations. Extensive experiments on three challenging datasets demonstrate that UST-Hand achieves state-of-the-art performance, outperforming existing self-supervised methods by up to 37.8% in Mean Per Vertex Position Error (MPVPE).

Jianyuan Wang, Minghao Chen, Shangzhan Zhang, Nikita Karaev, Johannes Schönberger, Patrick Labatut, Piotr Bojanowski, David Novotny, Andrea Vedaldi, Christian Rupprecht

We introduce VGGT-Ω, a feed-forward model for 3D reconstruction that improves accuracy, efficiency, and capabilities for both static and dynamic scenes. Prior models such as VGGT have shown that feed-forward 3D reconstruction is, in many cases, competitive with traditional optimization-based methods. Here, we show that the accuracy and robustness of these models scale predictably with model capacity and data size. To enable training 3D reconstruction models at an unprecedented scale, we introduce architectural changes that improve training efficiency and scalability, a high-quality data annotation pipeline that supports dynamic scenes, and a self-supervised learning protocol. We significantly simplify VGGT's architecture by using a single dense prediction head with multi-task supervision, removing expensive high-resolution convolutional layers, and introducing efficient scene tokens for feature aggregation in lieu of global attention. These changes allow us to train VGGT-Ω with 15 x more supervised data than prior work and to leverage vast amounts of unlabeled videos, while requiring only ~30% of VGGT's training memory. VGGT-Ω achieves strong results for 3D reconstruction of static and dynamic scenes across multiple benchmarks, e.g., improving over the previous best camera estimation accuracy by 77% on Sintel.

Shengkai Sun, Zhiyong Cheng, Zefan Zhang, Jianfeng Dong, Zhihui Li, Meng Wang

Recently, masked skeleton reconstruction models have emerged as strong action representation learners, driving significant progress in self-supervised skeleton-based action recognition. However, existing state-of-the-art methods must predict an exceedingly large number of spatiotemporal patches, significantly prolonging training time. Besides, by treating all spatiotemporal regions equally during reconstruction, these models are distracted from learning the critical motion patterns that underlie action semantics. To address these challenges, we propose Adaptive Masked Reconstruction (AMR), a faster and stronger pre-training framework. We first decouple the decoder from the encoder, enabling flexible prediction of larger spatiotemporal patches and dramatically reducing reconstruction complexity. Given that larger patches contain more complex information, which is challenging to predict and consequently degrades performance, we accordingly introduce an adaptive guidance module. This module identifies regions of high motion informativeness, guiding the model to focus on the most discriminative parts of each patch and alleviating reconstruction difficulty. Experiments on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD datasets demonstrate that AMR not only accelerates pre-training substantially but also improves downstream recognition accuracy, surpassing current state-of-the-art approaches.

Lei Zhou, Haoyu Wu, Akshat Dave, Dimitris Samaras

We introduce a test-time framework for multiview Transformers (MVTs) that incorporates priors (e.g., camera poses, intrinsics, and depth) to improve 3D tasks without retraining or modifying pre-trained image-only networks. Rather than feeding priors into the architecture, we cast them as constraints on the predictions and optimize the network at inference time. The optimization loss consists of a self-supervised objective and prior penalty terms. The self-supervised objective captures the compatibility among multi-view predictions and is implemented using photometric or geometric loss between renderings from other views and each view itself. Any available priors are converted into penalty terms on the corresponding output modalities. Across a series of 3D vision benchmarks, including point map estimation and camera pose estimation, our method consistently improves performance over base MVTs by a large margin. On the ETH3D, 7-Scenes, and NRGBD datasets, our method reduces the point-map distance error by more than half compared with the base image-only models. Our method also outperforms retrained prior-aware feed-forward methods, demonstrating the effectiveness of our test-time constrained optimization (TCO) framework for incorporating priors into 3D vision tasks. The code is available at https://github.com/cvlab-stonybrook/TCO.

Shashanka Venkataramanan, Valentinos Pariza, Mohammadreza Salehi, Lukas Knobel, Elias Ramzi, Spyros Gidaris, Andrei Bursuc, Yuki M Asano

We present Franca (pronounced Fran-ka): free one; the first fully open-source (data, code, weights) vision foundation model that matches and in many cases surpasses the performance of state-of-the-art proprietary models, e.g., DINOv2, CLIP, SigLIPv2, etc. Our approach is grounded in a transparent training pipeline inspired by Web-SSL and uses publicly available data: ImageNet-21K and a subset of ReLAION-2B. Beyond model release, we tackle critical limitations in self-supervised learning clustering methods. Existing approaches assign image features to large codebooks via clustering algorithms such as Sinkhorn-Knopp, but they often overlook the inherent ambiguity in cluster semantics. To address this, we introduce a multi-head clustering projector based on nested Matryoshka representations. This design progressively refines features into increasingly fine-grained clusters without increasing the model size, producing higher-quality dense representations. Additionally, we propose a novel positional disentanglement strategy that explicitly removes positional biases from dense representations.This leads to consistent gains on several downstream benchmarks, demonstrating the utility of cleaner feature spaces. Our contributions establish a new standard for transparent, high-performance vision models and open a path toward more reproducible and generalizable foundation models for the broader AI community.

Yangshi Ge, Zheng Liu, Feng Lu

Deep learning-based gaze estimation methods tend to suffer from substantial performance drop in real-world scenarios with varying users and environments. To tackle this issue, most recent approaches employ Unsupervised Domain Adaptation (UDA) to bridge the gap between source and target domains. However, this paradigm is misaligned with real-world scenarios, where the system typically needs to adapt to only a single new user. Therefore, this paper advocates a more practical paradigm: Unsupervised Personal Adaptation (UPA), which calibrates a pre-trained model using a few unlabeled images from a single new user. Conventional UDA methods do not guarantee improvements for every user and often yield lower average performance in this setting. To address this problem, we propose Render-to-Adapt (R2A), a self-supervised framework specifically designed for the UPA task. Given a pretrained gaze model, R2A utilizes a gaze-conditioned renderer to synthesize new images based on the model's gaze predictions, and enforces eye-region consistency as a label-free signal to enhance personalized gaze estimation. We evaluate R2A on a re-designed cross-dataset personal adaptation benchmark. Experimental results show that R2A consistently improves performance across all individuals and significantly outperforms existing SOTA methods.

Yang Liu, Qianqian Xu, Peisong Wen, Siran Dai, Xilin Zhao, Qingming Huang

Recent studies have made notable progress in video representation learning by transferring image-pretrained models to video tasks, typically with complex temporal modules and video fine-tuning. However, fine-tuning heavy modules may compromise inter-video semantic separability, i.e., the essential ability to distinguish objects across videos. While reducing the tunable parameters hinders their intra-video temporal consistency, which is required for stable representations of the same object within a video. This dilemma indicates a potential trade-off between the intra-video temporal consistency and inter-video semantic separability during image-to-video transfer. To this end, we propose the Consistency-Separability Trade-off Transfer Learning (Co-Settle) framework, which applies a lightweight projection layer on top of the frozen image-pretrained encoder to adjust representation space with a temporal cycle consistency objective and a semantic separability constraint. We further provide a theoretical support showing that the optimized projection yields a better trade-off between the two properties under appropriate conditions. Experiments on eight image-pretrained models demonstrate consistent improvements across multiple levels of video tasks with only five epochs of self-supervised training. The code is available at https://github.com/yafeng19/Co-Settle.

Xiaofeng Cong, Yu-Xin Zhang, Hao Shen, Yeying Jin, Junming Hou, Jie Gui

Underwater images often exhibit dominant blue-green hues due to wavelength-dependent light attenuation. While existing enhancement methods have achieved promising performance, they typically overlook the subjective nature of visual preferences. To address this gap, we propose SDUIE, a level-aware Semi-supervised Diffusion framework for Underwater Image Enhancement that enables dual control through both quantitative and textual inputs. SDUIE-Quant allows continuous, numerical adjustment of enhancement levels via low-rank adaptation weight merging within a dual-branch diffusion model. This model comprises a supervised branch trained on synthetic underwater-terrestrial pairs and a self-supervised branch designed to preserve the natural hues of real-world underwater scenes. Building on this, SDUIE-Text introduces intuitive, language-guided control by aligning semantic prompts with visual enhancement effects, leveraging the learned fusion weights. This dual-modality design offers both precise control and flexible, user-preferred enhancement. Experimental results demonstrate that SDUIE achieves state-of-the-art results while better preserving the aesthetic qualities often missed by conventional methods. The source code is in https://github.com/Xiaofeng-life/SDUIE.

Zhiwen Chen, Junhui Hou, Zhiyu Zhu, Jinjian Wu, Guangming Shi

Learning versatile, fine-grained representations from irregular event streams is pivotal yet nontrivial, primarily due to the heavy annotation that hinders scalability in dataset size, semantic richness, and application scope. To mitigate this dilemma, we launch a novel self-supervised pretraining method that distills visual foundation models (VFMs) to push the boundaries of event representation at scale. Specifically, we curate an extensive synchronized image-event collection to amplify cross-modal alignment. Nevertheless, due to inherent mismatches in sparsity and granularity between image-event domains, existing distillation paradigms are prone to semantic collapse in event representations, particularly at high resolutions. To bridge this gap, we propose to extend the alignment objective to semantic structures provided off-the-shelf by VFMs, indicating a broader receptive field and stronger supervision. The key ingredient of our method is a structure-aware distillation loss that grounds higher-quality image-event correspondences for alignment, optimizing dense event representations. Extensive experiments demonstrate that our approach takes a great leap in downstream benchmarks, significantly surpassing traditional methods and existing pretraining techniques. This breakthrough manifests in enhanced generalization, superior data efficiency and elevated transferability. The source code will be available.

Ashish Kumar, A. N. Rajagopalan

Recent advances in Gaussian Splatting (GS) have significantly improved 3D scene reconstruction and novel view synthesis. However, most existing methods typically assume that training inputs are captured under stable and achromatic lighting conditions . In contrast, scenes recorded under temporally varying color light, as in "disco lights" commonly seen in events, performances, and decorative settings, introduce severe ambiguities in both scene photometry and geometry. We propose Disco-GS, a framework that leverages GS for reconstructing the 3D scene while simultaneously recovering the underlying canonical appearance from videos captured under dynamic lighting conditions. Disco-GS estimates the effective per-pixel transient light, which, when applied to the canonical image, results in the observed color image of the scene, thereby enabling self-supervised learning. Disco-GS is an end-to-end framework that does not rely on any prior knowledge, such as color values, ambient lighting conditions, or scene properties. It effectively handles both global and spatially localized transient color variations. It also enables controllable brightness manipulation of the canonical scene, facilitating applications such as simulating low-light and well-lit scene conditions. To the best of our knowledge, Disco-GS is the first method to simultaneously perform 3D scene reconstruction and canonical appearance recovery from inputs captured under artificially varying, disco-style colored light. To enable quantitative and qualitative evaluations, we also introduce the Disco dataset, a collection of 25 videos of real-world scenes exhibiting diverse and random color variations. Extensive experiments demonstrate the robustness and fidelity of Disco-GS. The dataset is available at: https://github.com/akumar005/Disco-GS.

Ryousuke Yamada, Kohsuke Ide, Yoshihiro Fukuhara, Hirokatsu Kataoka, Gilles Puy, Andrei Bursuc, Yuki M. Asano

Despite recent progress in 3D self-supervised learning, collecting large-scale 3D scene scans remains expensive and labor-intensive. In this work, we investigate whether 3D representations can be learned from unlabeled videos recorded without any real 3D sensors. We present Laplacian-Aware Multi-level 3D Clustering with Sinkhorn-Knopp (LAM3C), a self-supervised framework that learns from video-generated point clouds reconstructed from unlabeled videos. We first introduce RoomTours, a video-generated point cloud dataset constructed by collecting room-walkthrough videos from the web (e.g., real-estate tours) and generating 49,219 scenes using an off-the-shelf feed-forward reconstruction model. We also propose a noise-regularized loss that stabilizes representation learning by enforcing local geometric smoothness and ensuring feature stability under noisy point clouds. Remarkably, without using any real 3D scans, LAM3C achieves better performance than previous self-supervised methods on indoor semantic and instance segmentation. These results suggest that unlabeled videos represent an abundant source of data for 3D self-supervised learning. Our source code is available at https://github.com/ryosuke-yamada/lam3c.

Di Zhang, Zhangpeng Gong, Xiaobo Pang, Jiashuai Liu, Junbo Lu, Hao Cui, Jiusong Ge, Zhi Zeng, Kai Yi, Yinghua Li 等

Foundation models have achieved success in computational pathology, demonstrating generalization across histopathology tasks. However, existing models overlook the heterogeneous and non-uniform organization of regions of interest (ROIs) because they rely on natural image backbones not tailored for tissue morphology. Consequently, they fail to capture the coherent tissue architecture beyond patches, limiting interpretability and clinical relevance. To address these challenges, we present Cross-modal Adaptive Region Encoder (CARE), a foundation model for pathology that partitions WSIs into several morphologically relevant regions. Specifically, CARE employs a two-stage pretraining strategy: (1) a self-supervised unimodal pretraining stage that learns morphological representations from 34,277 whole-slide images (WSIs) without segmentation annotations, and (2) a cross-modal alignment stage that leverages RNA and protein profiles to refine the construction and representation of adaptive regions. This molecular guidance enables CARE to identify biologically relevant patterns and generate irregular yet coherent tissue regions, selecting the representative area as ROI. CARE supports a broad range of pathology-related tasks, using either the ROI feature or the slide-level feature obtained by aggregating adaptive regions. Based on only one-tenth of the pretraining data typically used by mainstream foundation models, CARE achieves superior average performance across 33 downstream benchmarks, including morphological classification, molecular prediction, and survival analysis, and outperforms other foundation model baselines overall.

Kewei Wu, Chong Liang, Zhao Xie, Dan Guo

Masked visual modeling is a self-supervised learning task that does not use visual annotations. It aims to learn discriminative representations via a mask-reconstruction task. A single mask ratio in reconstruction may fail to capture complex semantics, which motivates dynamic masking strategies. In this work, we propose Progressive Mask Distillation (PMD), which utilizes dynamic mask ratios to facilitate progressive semantic learning from easy to hard. PMD integrates three key components: a progressive student distiller, a difficulty-aware region enhancer, and a cross-layer feature aligner. First, to capture dynamic visual semantics, we design a progressive student distiller that trains multiple student models with progressively increasing mask ratios. The early-phase student (with a low mask ratio) learns easy, low-level semantics from more visible tokens. This learned knowledge then guides the next-phase student (with a higher mask ratio) to capture hard, high-level semantics from fewer visible tokens. This progressive distillation mechanism enhances detail reconstruction at a high mask ratio. Second, to alleviate insufficient learning of semantic regions, we design a difficulty-aware region enhancer. We first smooth the region reconstruction loss to reduce large fluctuations across training epochs. The smoothed loss is then used to learn region-level weights, prioritizing accurate learning of regions with large reconstruction losses. Third, to further bridge the semantic gap across network layers, we design cross-layer feature alignment. This module aligns features across shallow, middle, and deep encoder layers, ensuring that shallow-layer features incorporate semantic information from deeper layers. Extensive experiments demonstrate that our method achieves state-of-the-art performance on the Something-Something V2, Kinetics-400, UCF-101, and HMDB-51 datasets.